CN113468689A - Cutting process optimization method, optimization model training method and device - Google Patents

Cutting process optimization method, optimization model training method and device Download PDF

Info

Publication number
CN113468689A
CN113468689A CN202110771535.9A CN202110771535A CN113468689A CN 113468689 A CN113468689 A CN 113468689A CN 202110771535 A CN202110771535 A CN 202110771535A CN 113468689 A CN113468689 A CN 113468689A
Authority
CN
China
Prior art keywords
cutting
cutting process
training
data set
sample data
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.)
Granted
Application number
CN202110771535.9A
Other languages
Chinese (zh)
Other versions
CN113468689B (en
Inventor
张雷
吴晓强
王勇
王利华
侍红岩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University of Commerce
Inner Mongolia University for Nationlities
Original Assignee
Tianjin University of Commerce
Inner Mongolia University for Nationlities
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin University of Commerce, Inner Mongolia University for Nationlities filed Critical Tianjin University of Commerce
Priority to CN202110771535.9A priority Critical patent/CN113468689B/en
Publication of CN113468689A publication Critical patent/CN113468689A/en
Application granted granted Critical
Publication of CN113468689B publication Critical patent/CN113468689B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/08—Probabilistic or stochastic CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/08—Thermal analysis or thermal optimisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces

Abstract

The invention provides a cutting process optimization method, an optimization model training method and an optimization model training device, relates to the technical field of intelligent manufacturing, and further relates to the technical field of big data. The cutting process optimization model training method comprises the following steps: constructing an initial cutting process optimization model, wherein the initial cutting process optimization model comprises an initial cutting force optimization module and an initial cutting temperature optimization module; obtaining a cut and cut process training sample data set; processing training samples in the training sample data set of the cutting process by using a sample generation method, and generating an expanded cutting process training sample data set so as to increase the number of training samples for training the initial cutting process optimization model; and training the initial shaving process optimization model by using the shaving process training sample data set and the augmented shaving process training sample data set to obtain the shaving process optimization model.

Description

Cutting process optimization method, optimization model training method and device
Technical Field
The present disclosure relates to the field of intelligent manufacturing technologies, and further relates to the field of big data technologies, and in particular, to a cutting process optimization method, an optimization model training device, and a computer-readable storage medium.
Background
With the continuous deepening of the intelligent manufacturing technology and the continuous development of the digital twin technology, the interaction of the manufacturing shop information and the physical world promotes the intellectualization of the shop. The digital twinning technology realizes accurate mapping of a physical entity in a digital space, runs through the full life cycle of equipment, and can complete optimization design, debugging and operation and maintenance by means of a model feedback manufacturing process. Meanwhile, the digital twinning technology is used for effectively collecting data, and in the cutting and machining process, reasonable optimization of operation parameters has important significance in reducing machining energy consumption, reducing machining cost, improving machining efficiency and guaranteeing machining quality. In order to ensure that the precision of a final product meets the design requirement, how to obtain a cutting process optimization method to reduce the dependence of manual experience and improve the process stability becomes a difficult problem which is continuously sought to be solved by designers.
Disclosure of Invention
Technical problem to be solved
Based on the above problems, the present disclosure provides a cutting process optimization method, an optimization model training method, and an optimization model training device, so as to alleviate technical problems of poor cutting process optimization level and the like in the prior art.
(II) technical scheme
According to one aspect of the disclosure, a cutting process optimization model training method is provided, which includes:
constructing an initial cutting process optimization model, wherein the initial cutting process optimization model comprises an initial cutting force optimization module and an initial cutting temperature optimization module;
obtaining a cut and cut process training sample data set;
processing training samples in the training sample data set of the cutting process by using a sample generation method, and generating an expanded cutting process training sample data set so as to increase the number of training samples for training the initial cutting process optimization model; and
and training the initial shaving process optimization model by using the shaving process training sample data set and the augmented shaving process training sample data set to obtain the shaving process optimization model.
In the embodiment of the present disclosure, the cutting process training sample set includes a pre-cutting process training sample set, where the pre-cutting process training sample in the pre-cutting process training sample set includes cutting process parameter information, where the cutting process parameter information includes cutting rotational speed information, cutting feed information, and cutting depth information;
processing the training samples in the cutting process training sample data set by using a sample generation method, and generating an amplification cutting process training sample data set comprises:
and processing the cutting process parameter information in the pre-training sample by using the sample generation method, and generating an amplification pre-cutting process training sample data set, wherein the amplification pre-cutting process training sample data set comprises a plurality of amplification pre-cutting process training samples.
In this embodiment of the present disclosure, the training of the initial skiving process optimization model using the skiving process training sample data set and the augmented skiving process training sample data set, and obtaining the skiving process optimization model includes:
training the initial cutting force optimization module by utilizing the pre-cutting process training sample data set to obtain a pre-training initial cutting force optimization module;
and training the initial cutting temperature optimization module by utilizing the amplification pre-cutting process training sample data set to obtain a pre-training initial cutting temperature optimization module.
In the embodiment of the present disclosure, the cutting process parameter information corresponds to cutting force information and cutting temperature information, and the cutting force information and the cutting temperature information vary with the cutting process parameter information.
In the embodiment of the disclosure, the cutting force information is obtained by measuring the cutting process through a force measuring device; and the cutting temperature information is obtained by measuring the cutting machining process through a temperature measuring device.
In an embodiment of the present disclosure, the force measuring device is a rotary force meter or a piezoelectric sensing force meter; the temperature measuring device is a thermal sensor thermometer or a thermal imager.
In an embodiment of the disclosure, the sample generation method includes one or a combination of a finite element simulation method or an empirical model method.
According to another aspect of the present disclosure, a cutting process optimization method is provided, where the method is implemented according to a cutting process optimization model obtained by training in any one of the above training methods, the cutting process optimization model includes a cutting force optimization module and a cutting temperature optimization module, and the method includes:
inputting the parameters of the cutting process to be optimized into a cutting force optimization module of the cutting process optimization model to obtain cutting force optimization parameters;
and inputting the optimal parameters of the cutting force into a cutting temperature optimization module of the cutting process optimization model to obtain optimal cutting process parameters, wherein the optimal cutting process parameters are used for guiding the cutting machining process.
According to another aspect of the present disclosure, a cutting process optimization model training device is provided, including:
the system comprises a building module, a cutting temperature optimizing module and a cutting force optimizing module, wherein the building module is used for building an initial cutting process optimizing model, and the initial cutting process optimizing model comprises an initial cutting force optimizing module and an initial cutting temperature optimizing module;
the acquisition module acquires a cutting process training sample data set;
the sample generating module is used for processing the cutting process training sample data set by using a sample generating method and generating an expanded cutting process training sample data set so as to increase the number of training samples for training the initial cutting process optimization model; and
and the training module is used for training the initial cutting process optimization model by utilizing the cutting process training sample data set and the augmented cutting process training sample data set to obtain the cutting process optimization model, wherein the cutting process optimization model comprises a cutting force optimization module and a cutting temperature optimization module.
According to another aspect of the present disclosure, a computer-readable storage medium is provided, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the cutting process optimization model training method according to any one of the above-mentioned methods are implemented.
(III) advantageous effects
According to the technical scheme, the electric skin wiping sampling device disclosed by the invention has at least one or part of the following beneficial effects:
(1) the operation parameters are reasonably optimized, the processing energy consumption is reduced, the processing cost is reduced, the processing efficiency is improved, and the processing quality is ensured; and
(2) by optimizing the cutting process, the dependence of manual experience can be reduced, and the process stability is improved.
Drawings
Fig. 1 is a schematic flow chart of a method of optimizing a model training method according to an embodiment of the present disclosure.
Fig. 2 is a schematic diagram of machining of the cutting teeth of the cutting process optimization method and device according to the embodiment of the present disclosure.
Fig. 3 is a schematic diagram of dynamic changes of cutting edges of cutting teeth participating in cutting in the method and device for optimizing the cutting process according to the embodiment of the disclosure.
Fig. 4 is a schematic view of a cutting edge at a set time in the method and device for optimizing a cutting process according to the embodiment of the present disclosure.
Fig. 5 is a schematic frame diagram of a cutting process optimization method according to an embodiment of the present disclosure.
Fig. 6 is a schematic diagram of a thermodynamic coupling digital twin model in a cutting process of the cutting process optimization method according to the embodiment of the disclosure.
Fig. 7 is a schematic view of a micro-segment tooth and a micro-segment blade of the cutting process optimization method according to the embodiment of the disclosure.
Fig. 8 is a schematic view of a local coordinate system of a micro-segment tooth or a micro-segment blade of the cutting process optimization method according to the embodiment of the disclosure.
Fig. 9 is a schematic view of a spatial geometric relationship between micro-segment teeth or micro-segment blades of the cutting process optimization method according to the embodiment of the present disclosure.
Fig. 10 is a schematic diagram of each velocity relationship on an equivalent cross section of the cutting process optimization method according to the embodiment of the present disclosure.
Detailed Description
The cutting tooth machining is used as a gear machining mode with great potential, machining parameters (main shaft rotating speed, cutting depth, feeding rate and the like) set by experience lack of theoretical basis, and the machining parameters cannot be adjusted in the machining process, so that the cutting force fluctuation is large, the cutting temperature is high, and the efficient and stable cutting tooth machining cannot be realized. Aiming at the problem, a digital twin based cutting parameter dynamic regulation and control method is provided. Firstly, the change of cutting force and cutting temperature in the cutting process is mainly considered, a mechanism-data hybrid driving method is adopted, a thermodynamic coupling digital twin model in the cutting process is established, and the dynamic consistency of the digital twin model and the physical space cutting process is realized. Secondly, performing reduced order representation on the thermal coupling digital twin model by adopting a principal component analysis method and a Gaussian process regression method, establishing a proxy model, training effective big data by adopting a deep learning algorithm, establishing a mapping relation model of cutting parameters, cutting force and cutting temperature, and realizing dynamic prediction of the cutting force and the cutting temperature. And thirdly, based on the dynamic prediction results of the cutting force and the cutting temperature, performing multi-target optimization on cutting parameters by adopting heuristic algorithms such as cuckoo and the like, and realizing dynamic regulation and control of processing parameters in the cutting process. Finally, the effectiveness of the method provided by the text is verified through a cutting tooth machining experiment, and research results have important theoretical guiding significance for realizing high efficiency and stability of cutting tooth machining.
The method, the optimization model training method and the device are reliable in process, and can reasonably optimize operation parameters, reduce machining energy consumption, reduce machining cost, improve machining efficiency and guarantee machining quality; by the cutting process optimization method, the dependence of manual experience can be reduced, the process stability can be improved, and the main defects and shortcomings of the existing cutting process optimization method can be overcome.
For the purpose of promoting a better understanding of the objects, aspects and advantages of the present disclosure, reference is made to the following detailed description taken in conjunction with the accompanying drawings.
In an embodiment of the present disclosure, a method for training a cutting process optimization model is provided, as shown in fig. 1 to 10, the method includes:
constructing an initial cutting process optimization model, wherein the initial cutting process optimization model comprises an initial cutting force optimization module and an initial cutting temperature optimization module;
obtaining a cut and cut process training sample data set;
processing training samples in the training sample data set of the cutting process by using a sample generation method, and generating an expanded cutting process training sample data set so as to increase the number of training samples for training the initial cutting process optimization model; and
and training the initial shaving process optimization model by using the shaving process training sample data set and the augmented shaving process training sample data set to obtain the shaving process optimization model.
In the embodiment of the present disclosure, the cutting process training sample set includes a pre-cutting process training sample set, where the pre-cutting process training sample in the pre-cutting process training sample set includes cutting process parameter information, where the cutting process parameter information includes cutting rotational speed information, cutting feed information, and cutting depth information;
processing the training samples in the cutting process training sample data set by using a sample generation method, and generating an amplification cutting process training sample data set comprises:
and processing the cutting process parameter information in the pre-training sample by using the sample generation method, and generating an amplification pre-cutting process training sample data set, wherein the amplification pre-cutting process training sample data set comprises a plurality of amplification pre-cutting process training samples.
In this embodiment of the present disclosure, the training of the initial skiving process optimization model using the skiving process training sample data set and the augmented skiving process training sample data set, and obtaining the skiving process optimization model includes:
training the initial cutting force optimization module by utilizing the pre-cutting process training sample data set to obtain a pre-training initial cutting force optimization module;
and training the initial cutting temperature optimization module by utilizing the amplification pre-cutting process training sample data set to obtain a pre-training initial cutting temperature optimization module.
In the embodiment of the present disclosure, the cutting process parameter information corresponds to cutting force information and cutting temperature information, and the cutting force information and the cutting temperature information vary with the cutting process parameter information.
In the embodiment of the disclosure, the cutting force information is obtained by measuring the cutting process through a force measuring device; and the cutting temperature information is obtained by measuring the cutting machining process through a temperature measuring device.
In an embodiment of the present disclosure, the force measuring device is a rotary force meter or a piezoelectric sensing force meter; the temperature measuring device is a thermal sensor thermometer or a thermal imager.
In an embodiment of the disclosure, the sample generation method includes one or a combination of a finite element simulation method or an empirical model method.
Specifically, in the embodiment of the present disclosure, as shown in fig. 2, similar to a gear machining manner such as hobbing and gear shaping, when a gear is machined in a cutting tooth machining manner, a cutting tooth cutter and a gear workpiece rotate simultaneously, and a motion relationship between the cutting tooth cutter and the gear workpiece is equal to that between two gears engaged with each other. During cutting, the axis of the cutter and the axis of the workpiece form an axis intersection angle, and the size of the axis intersection angle is determined by the helical angle of the cutter and the helical angle of the workpiece. According to the position and motion relation of the tooth cutting tool and the gear workpiece, the gear tooth surface is cut and machined gradually, wherein the machining in the tooth height direction needs to be carried out by multiple radial feeding, and the machining in the tooth width direction is completed by axial feeding.
In the embodiment of the present disclosure, as shown in fig. 3, the cutting process is different from other gear processing manners, and the number of teeth participating in cutting in the cutting process is dynamically changed. According to the tooth cutting tool design theory, the cutting edge of the tool tooth is a space curve, and the length of the cutting edge participating in cutting changes constantly.
In the disclosed embodiment, as shown in fig. 4, at a certain time, the cutting edge state of the cutting is involved. In the figure, Ps、PrAnd PeRespectively representing the cutting plane, the base plane and the equivalent cross-section, tpRepresenting the tangential vector of the cutting edge involved in cutting, npNormal vector representing rake face,/pRepresents the vector in the direction of the intersection line of the equivalent cross section and the rake face, lrRepresenting the vector in the direction of the intersection of the equivalent section and the base plane, lpAnd lrThe included angle between the two is the equivalent section front angle gammae，vxIndicates the cutting speed at the cutting edge participating in cutting, and vxPerpendicular to lr. It can be known that the cutting rake angle in the cutting process also changes constantly.
In the embodiment of the present disclosure, as shown in fig. 5, in the cutting tooth machining process, the number of teeth involved in machining, the length of the cutting edge, and the cutting rake angle all have temporal changes, which causes that the cutting force and the cutting temperature change constantly, and the cutting force and the cutting temperature change directly affect the machining accuracy of the cutting tooth. In the prior art, as the rule of the influence of the cutting parameters on the cutting force, the cutting temperature and the machining quality is not mastered, the cutting parameters can only be set through trial cutting for many times or by experience, and the set cutting parameters cannot be guaranteed to meet the machining quality requirement. The digital twin can dynamically predict and intervene in real time the physical entity or process by building a mirror model of the physical entity or process in the digital space. Therefore, a frame of a digital twin-based dynamic regulation and control method for cutting parameters is constructed. The frame mainly comprises a cutting process in a physical space, a thermal coupling digital twin model in a digital space, cutting big data in a digital-physical space, a mapping relation model of cutting parameters, cutting force and cutting temperature, a multi-objective cutting parameter optimization model and the like.
Furthermore, in the physical space, by means of sensing devices such as a rotary dynamometer and a thermal imager, the cutting force and the cutting temperature in the cutting process are collected in real time and serve as important components of large cutting data, and data bases are provided for virtual models in the digital space. In the digital space, a thermodynamic coupling digital twin model is established aiming at the cutting process in the physical space, and the dynamic consistency of the digital twin model and the cutting force and the cutting temperature in the cutting process is ensured. The dynamic prediction of the cutting force and the cutting temperature in the cutting process is realized by performing reduced order representation on a thermal coupling digital twin model, establishing a proxy model of the model, training the proxy model by means of large data such as calculation data, simulation data, actual measurement data and the like in a digital-physical space, and obtaining a mapping relation model of cutting parameters (rotating speed, feeding amount and cutting depth of a cutter) and the cutting force and the cutting temperature. And establishing a multi-objective slicing parameter optimization model according to the dynamic prediction result, realizing dynamic optimization of the slicing parameters in the slicing process, and further feeding the optimal slicing parameter combination back to the slicing process in the physical space in real time.
In the frame constructed by the method, the physical space executes the cutting process and generates large data of cutting force and cutting temperature, the digital space is synchronous with the physical space in a virtual-real mode, the cutting force and the cutting temperature can be dynamically predicted, multi-target optimization is carried out on cutting parameters, and dynamic control on the cutting parameters in the cutting process can be realized through dynamic evolution and cyclic iteration of a closed-loop process jointly formed by the digital space and the physical space.
In an embodiment of the present disclosure, the constructing a thermal coupling digital twin model of the cutting according to the cutting process data and the cutting force thermal data includes: dividing a cutting edge into micro-segment edges, and further establishing a cutting force analysis model of the micro-segment edges; dividing a cutting edge into micro-segment teeth, and further establishing a cutting temperature analysis model of the micro-segment teeth; establishing a time-varying model of the cutting edge actually participating in the processing according to the cutting edge length of the cutting edge actually participating in the processing of the tooth surface to be processed; and coupling the cutting force analysis model, the cutting temperature analysis model and the time-varying model to obtain a thermodynamic coupling digital twin model.
In the embodiment of the present disclosure, as shown in fig. 6, in the cutting process, the number of teeth and the length of the cutting edge participating in cutting, and the rule of the change of the cutting rake angle with time are difficult to describe by using an analytical expression. The method based on the cutting principle can only represent the cutting force and the cutting temperature at a certain moment, and cannot represent the dynamic cutting force and the cutting temperature in the cutting process. Therefore, a mechanism-data hybrid driving method is proposed herein to establish a thermodynamic coupling digital twin model of the cutting process. Firstly, based on an oblique angle cutting principle, adopting the ideas of a micro-segment blade and a micro-segment tooth to establish a cutting force analysis model of the micro-segment blade and a cutting temperature analysis model of the micro-segment tooth; and then, establishing a time-varying model of the tooth number, the cutting edge length and the cutting rake angle which participate in cutting in the cutting process by adopting a Gaussian process regression method. And finally, integrating and fusing the analytic model and the time-varying model to obtain a thermal coupling digital twin model in the cutting process, wherein the thermal coupling digital twin model is used for representing the cutting force and the cutting temperature which are dynamically changed in the cutting process.
In the embodiment of the present disclosure, as shown in fig. 7, although the number of teeth, the length of the cutting edge, and the rake angle of cutting involved in the cutting process are time-varying, the cutting force and the cutting temperature generation mechanism are the same for each tooth involved in cutting and each segment of cutting edge on the tooth. Therefore, the cutter teeth of the tooth cutting cutter are dispersed into a plurality of small parts along the cutting edge, each small part of cutter teeth is called a micro-segment tooth, the cutting edge of each micro-segment tooth is called a micro-segment edge, and each micro-segment edge can be similar to a straight edge.
In the embodiment of the present disclosure, as shown in fig. 8, the cutting characteristics of the micro segment teeth and the micro segment blades completely conform to the bevel cutting characteristics, and therefore, the cutting process of the micro segment teeth and the micro segment blades is equivalent to a bevel cutting process, and the cutting force and the cutting temperature are calculated based on the bevel cutting principle. In order to establish a cutting force model of the micro-segment blade and a cutting temperature model of the micro-segment tooth, a local coordinate system C is established by taking any point on a certain micro-segment blade as an origin and taking the cutting speed direction as an x axisO. In the figure, a straight line segment AB represents a certain micro-segment edge, a point A is the initial end point of the micro-segment edge, the origin of coordinates O is coincident with any point E on the micro-segment edge, and the direction of an X axis and the cutting speed v are selectedxThe directions are coincident, then the micro-segment edge AB and the cutting speed vxThe plane is the cutting plane PsI.e. the plane xOy. Passing through point E and perpendicular to cutting speed vxIs defined as a base plane PrI.e. the plane yOz. The plane passing through the point E and perpendicular to both the cutting plane and the base plane is defined as the orthogonal plane PoI.e. the plane xOz. For the micro-segment edge AB, the plane where the ABCD is located is a rake face, and the flow velocity v of the chips along the rake face is determinedchIs decomposed into cutting speed vxAnd shear velocity vsTwo parts, the velocity vectors in the three directions are on the same plane, which is called the equivalent section Pe. The straight-line section OF is the intersection line OF the equivalent cross section and the base plane. According to the metal cutting principle, the cutting force of the micro-segment blade and the cutting temperature of the micro-segment tooth can be measured at the equivalent section PeThe above calculation results.
In the embodiment of the present disclosure, as shown in fig. 9, in order to establish a cutting force model of a micro segment blade and a cutting temperature model of a micro segment tooth, a detailed analysis needs to be performed on a spatial geometric relationship of the micro segment blade or the micro segment tooth on the basis of 8. In the figure, the plane CFSU represents a normal plane, the plane is perpendicular to the micro-segment blade AB, the plane OGH represents an equivalent section, and the angle BET is formed by the micro-segment blade AB and a base plane PrAnd the cutting plane PsThe crossing line OT is formed, and the angle BET is known as the cutting edge inclination angle lambda according to the metal cutting principles. The angle ECB is formed by a straight line EC in the chip flowing direction and a normal plane and a rake face intersection line CB, and the angle can be known by the metal cutting principleECB is the flow chip angle psiλ. The angle HEG is composed of an intersection EG of the equivalent section and the rake face and an intersection EH of the equivalent section and the base plane, and the angle HEG is the equivalent section rake angle gamma according to the metal cutting principlee. The angle EWG is composed of a straight line EW and a WG, wherein the straight line EW is consistent with the direction of a shearing speed, the straight line WG is parallel to the direction of the shearing speed, and the angle EWG is the shearing angle phi according to the metal cutting principlee. The intersecting lines of the plane CFSU and the rake face and the base plane are respectively straight lines CB and US, a point B crossing point is taken as a construction line KB which is parallel to the straight line US, and the & lt KBC is a normal plane front angle gamman。
Further, as can be seen from the spatial geometry in fig. 9, the shear force F to which the chip is subjectedsIn the same direction as EW, friction force FfThe direction of the cutting edge is consistent with the direction of EG, namely the shearing force and the friction force applied to the cutting chip are both in an equivalent cross section, the acting force F of the cutting chip to the rake facenAlso within the equivalent cross-section. At the same time, FnAlso in the normal plane, then FnThe direction of (a) should be consistent with a straight line CQ, wherein the straight line CQ is an intersection line of the equivalent cross section and the normal plane, so that the straight line CQ is perpendicular to the rake face. Order to
Figure BDA0003153697500000091
Then the < EQC is the friction angle betae. Because the straight line CQ is perpendicular to the plane ECB and the straight line LM is the projection of CQ in the xOz plane, LM is perpendicular to the straight line EL, and then < MLN ═ MEL can be known. The angle MEL is composed of a straight line ME and an EL, wherein the straight line EL is an intersection line of the rake face and the orthogonal plane, the straight line ME is an intersection line of the base plane and the orthogonal plane, and the angle MEL is an orthogonal plane front angle gammaoIf < MLN ═ gammao。
On the basis of the relationship of each cutting angle on the micro-segment blade or the micro-segment tooth, a cutting force analysis model of the micro-segment blade is obtained through derivation:
FOs＝[Fx,Fy,Fz]T (1)
in the formula (I), the compound is shown in the specification,
Figure BDA0003153697500000092
Figure BDA0003153697500000101
Figure BDA0003153697500000102
in the above formula, akcDenotes the thickness of cut, akwDenotes the cutting width, σsIndicating the yield strength of the workpiece material.
The cutting speed v of the cutting edge participating in cutting in fig. 4 can be obtained according to the design principle of the curved surface conjugate serrated knifexComprises the following steps:
vx＝ω2×r2-ω1×r1-f (5)
in the formula (I), the compound is shown in the specification,
Figure BDA0003153697500000103
in the above formula, ω1And ω1Vector sum scalar, omega, representing the rotational speed of the gear workpiece, respectively2And ω2Vector and scalar quantities respectively representing the rotational speed of the tooth cutting tool, f and f respectively represent vector and scalar quantities of the feed speed, r1And r2Respectively representing the work tooth surface in the work coordinate system and the conjugate surface in the tool coordinate system, i1、j1、k1Unit vectors, k, representing the three coordinate axes of the workpiece coordinate system, respectively2And a represents the center distance between the tooth cutting tool and the gear workpiece.
In the embodiment of the present disclosure, the cutting temperature calculation for the micro-segment teeth as shown in fig. 10 is performed at the equivalent cross section PeThe chip is a continuous chip, and plastic flow of the chip occurs in the shear deformation region. Chip flow velocity vchCutting ofVelocity vxAnd shear slip velocity in the shear deformation region. The relationship between the respective speeds can be expressed by the following formula:
Figure BDA0003153697500000104
in the formula, vnRepresenting the velocity component, v, perpendicular to the shear bands1And vs2Representing the shear slip velocity in the shear deformation region. And further obtaining a cutting temperature analytic model of the micro-segment teeth:
Figure BDA0003153697500000111
in the formula, RchfDenotes the proportion of frictional heat flowing into chips,. mu.denotes the coefficient of friction at the blade-chip contact surface,. sigmaroDenotes the maximum compressive stress, λ, experienced by the rake facewDenotes the thermal conductivity of the workpiece material, ρ denotes the density of the workpiece material, c denotes the specific heat capacity of the workpiece material, l denotes the tool-chip contact length, ξ denotes an index, TtIndicating the initial temperature of the tool.
In the embodiment of the disclosure, the time-varying model is known from a design principle of a tooth cutting tool, and in a cutting process, intrusion of a certain tooth of the tool into a tooth surface to be machined indicates that the tooth participates in cutting, so that the number n (t) of the teeth participating in cutting at any time can be judged by whether interference occurs between a blade scanning surface of the tooth and the tooth surface to be machined. Tooth surface model S of given gear workpiecegTool tooth edge scanning model sigma, tool rotation speed ntThe feed amount f, the cutting depth a and the cutting time t, and the number of the cutter teeth participating in cutting at any moment can be obtained according to the method:
N(t)＝F1(Sg，Σ，nt，f，a，t) (9)
in the formula, F1The mapping relation between N (t) and the relevant variable is shown.
Furthermore, the cutting edge at any time can be obtained by dispersing the edge scanning surface according to timeRelative to the spatial position of the tooth surface to be machined, therefore, the length of the cutting edge participating in cutting at any time, i.e., the number of the micro-segment teeth or the number of the micro-segment edges n (t), can be judged by observing the interference area of the cutting edge and the tooth surface to be machined. Similarly, a tooth surface model S of the gear workpiece is givengCutting edge curve C of cutter tooth and rotating speed n of cuttertThe feeding amount f, the cutting depth a and the cutting time t can be obtained according to the method, the length of the cutting edge participating in cutting at any moment can be obtained, the cutting edge is divided into a plurality of parts along the cutting edge and the number of the micro-segment teeth or the number of the micro-segment edges participating in cutting can be obtained by counting:
n(t)＝F2(Sg，C，nt，f，a，t) (10)
in the formula, F2And (d) representing the mapping relation between n (t) and the relevant variable.
Aiming at each micro-segment edge, a measuring coordinate system of the cutting angle of the cutter is constructed on the basis of the tangential vector and the cutting speed of the micro-segment edge, and according to the metal cutting theory, the included angle between the intersection line of the main section and the base plane and the tangent line of the intersection line of the main section and the rake face is the cutting rake angle, so the cutting rake angle gamma (n) of all micro-segment edges participating in cutting at any time can be obtained by adopting the method, and is expressed by a formula:
γ(n)＝F3(n，Sg，C，nt，f，a，t) (11)
in the formula, F3Represents the mapping relationship between gamma (n) and the relevant variable.
Since the three mapping relationships cannot be expressed by analytical expressions, n (t), and γ (n) at each time can be obtained one by one in a discrete manner. In the calculation process, a person is required to observe the interference condition of the blade scanning surface, the cutting edge and the tooth surface to be processed through naked eyes, the calculation efficiency is low, and the method can not be applied to real-time calculation in the cutting process. And then training the three mapping relations by adopting a machine learning algorithm and taking the result obtained by discrete calculation as basic data. From the discrete results obtained by the calculation, the mapping relationship between n (t), and γ (n) and the time t is nonlinear. Because the Gaussian process has the advantage of approximately expressing the nonlinear mapping relation, the Gaussian process is adopted to approximately express the three nonlinear mapping relations.
In the embodiment of the present disclosure, the sample data of the number of tool teeth participating in cutting in the cutting process follows gaussian distribution, and the probability function is:
N(t)～GP(m，k) (12)
wherein m represents a mean value, k represents a covariance
k＝k(t,t′) (13)
Ignoring measurement noise, establishing a prior distribution of n (t) in a given sample data set D according to bayesian principles:
N～N(m,K) (14)
according to the nature of the gaussian process, N (t) of sample data and N x (t) of test data follow a joint gaussian distribution:
Figure BDA0003153697500000121
then, N*The conditional probability distribution of (a) is:
Figure BDA0003153697500000123
in the formula, K represents a covariance matrix
Figure BDA0003153697500000122
K*＝[k(t*,t1) k(t*,t2) … k(t*,tn)] (18)
K**＝k(t*,t*) (19)
By using a Bayesian posterior probability formula, a Gaussian process regression prediction model can be obtained:
Figure BDA0003153697500000131
Figure BDA0003153697500000132
in the formula (I), the compound is shown in the specification,
Figure BDA0003153697500000133
and cov (N)*) Respectively represent N*Mean and variance of. Using the "3 sigma principle" of Gaussian distribution, N*The confidence interval for a predicted value of 99.73% is:
Figure BDA0003153697500000134
similarly, the micro-segment edge or the tooth number of the micro-segment and the change value of the cutting rake angle thereof along with the time in the cutting process can be predicted by the method. The prediction processes of the three variables are basically consistent, and the difference is the determination of the mean and covariance functions of Gaussian distribution.
Since there is no prior information for the three variables, all take m to 0, and the sample data needs to be processed into zero-mean data before training with the sample data. The determination of the covariance function is very important, and directly determines the regression effect and prediction accuracy of the Gaussian process. Firstly, determining a corresponding covariance function according to the characteristics of a sample data set; secondly, establishing a conditional probability negative log-likelihood function of the sample data, and enabling the conditional probability negative log-likelihood function to solve a partial derivative of the hyper-parameter; and finally, minimizing the partial derivative by adopting a conjugate gradient method to obtain an optimal solution of the hyper-parameter.
In the embodiment of the disclosure, the thermal coupling digital twin model fusion is to organically combine the cutting force, the cutting temperature analysis model and the time-varying model, so as to obtain the thermal coupling digital twin model in the cutting process, which is expressed by a formula:
Figure BDA0003153697500000135
in the formula (I), the compound is shown in the specification,
Figure BDA0003153697500000136
shows the coupling relation between the cutting force and the cutting temperature,
Figure BDA0003153697500000137
Figure BDA0003153697500000138
in the formula (I), the compound is shown in the specification,
Figure BDA0003153697500000139
the cutting force of the micro-segment blade at the kth section on the Kth cutter tooth under the global coordinate system is expressed as a vector, the analysis model part is the cutting force under the local coordinate system of the micro-segment blade, and a conversion matrix M from the local coordinate system to the global coordinate system, which is established by an author in earlier stage, is adoptedwOAnd obtaining the cutting force of the k-th micro-segment blade in the global coordinate system:
Figure BDA0003153697500000141
in this way, the cutting force in the global coordinate system at any time is calculated by simultaneous equations (24) and (26). The cutting temperature is a scalar, and according to the principle that heat is transferred from a high-temperature region to a low-temperature region, the average value of the cutting temperatures of the micro-segment teeth at any moment is determined by a formula (25) to be the cutting temperature at the moment.
In the embodiment of the present disclosure, the thermodynamic coupling digital twin model established in the cutting process includes both a cutting force and cutting temperature mechanism calculation model of the micro-segment blade or the micro-segment tooth, and also includes a data-driven tool tooth number participating in cutting, a micro-segment blade or micro-segment tooth number, and a time-varying model of a cutting rake angle. In the cutting process, the number of cutter teeth, micro-segment blades or micro-segment teeth and the dynamic value of a cutting rake angle which participate in cutting are estimated in real time through a data-driven time-varying model, the cutting force and the cutting temperature of each segment of micro-segment blades or micro-segment teeth are calculated through an analytic model based on a mechanism, and finally the dynamic change values of the cutting force and the cutting temperature in the cutting process are calculated through a thermal coupling digital twinning model.
In the embodiment of the disclosure, the relation between the cutting parameters and the cutting force and the cutting temperature is mapped to perform order reduction characterization on a thermodynamic coupling digital twin model by adopting a principal component analysis method, and a proxy model is established, wherein the input parameters are cutting process parameters (rotating speed, feeding amount and cutting depth) and cutting time (or rotating angle, rotating number and the like), and the output parameters are the maximum value, the average value and the root mean square of the cutting force and the cutting temperature. The method comprises the steps of training big data such as calculation data, simulation data and measured data by adopting a deep learning algorithm (an extreme learning machine), establishing a mapping relation model between cutting parameters and cutting force, maximum value, mean value and root mean square of cutting temperature in a unit range (one rotation of a main shaft), and realizing dynamic prediction of the cutting force and the cutting temperature.
In the embodiment of the disclosure, the multi-objective optimization and dynamic regulation of the cutting parameters are optimization objectives of minimizing cutting force fluctuation and cutting temperature in a unit range (a knife) in the cutting process, a dynamic multi-objective optimization model of the cutting parameters is established by taking the rotating speed, the cutting depth and the feeding amount of the knife as optimization parameters, the cutting parameters are solved by adopting heuristic algorithms such as NSGA-II and the like, and the optimal cutting parameter combination is fed back to the cutting tooth machining process in a physical space, so that the dynamic regulation and control of the cutting parameters are realized.
According to another aspect of the present disclosure, a dynamic cutting process parameter regulation and control system based on digital twinning is provided, which includes:
the data acquisition module is used for acquiring the cutting process data of the physical space and monitoring the cutting process through the acquisition system to obtain cutting force thermal data;
the coupling processing module is used for constructing a thermal coupling digital twin model of the cutting according to the cutting process data and the cutting thermal data;
the order reduction processing module is used for performing order reduction representation on the thermodynamic coupling digital twin model by adopting a principal component analysis method to obtain a mapping relation model;
the prediction processing module is used for predicting the process parameters of the current physical space through the mapping relation model to obtain a prediction result; and
the optimization processing module is used for carrying out multi-target optimization on the cutting process parameters by adopting a heuristic algorithm according to the prediction result to obtain an optimization result; and sending the optimization result to the cutting execution system of the current physical space for execution, and realizing dynamic adjustment and control of cutting technological parameters in the cutting process.
According to another aspect of the present disclosure, a cutting process optimization method is provided, where the method is implemented according to a cutting process optimization model obtained by training in any one of the above training methods, the cutting process optimization model includes a cutting force optimization module and a cutting temperature optimization module, and the method includes:
inputting the parameters of the cutting process to be optimized into a cutting force optimization module of the cutting process optimization model to obtain cutting force optimization parameters;
and inputting the optimal parameters of the cutting force into a cutting temperature optimization module of the cutting process optimization model to obtain optimal cutting process parameters, wherein the optimal cutting process parameters are used for guiding the cutting machining process.
According to another aspect of the present disclosure, a cutting process optimization model training device is provided, including:
the system comprises a building module, a cutting temperature optimizing module and a cutting force optimizing module, wherein the building module is used for building an initial cutting process optimizing model, and the initial cutting process optimizing model comprises an initial cutting force optimizing module and an initial cutting temperature optimizing module;
the acquisition module acquires a cutting process training sample data set;
the sample generating module is used for processing the cutting process training sample data set by using a sample generating method and generating an expanded cutting process training sample data set so as to increase the number of training samples for training the initial cutting process optimization model; and
and the training module is used for training the initial cutting process optimization model by utilizing the cutting process training sample data set and the augmented cutting process training sample data set to obtain the cutting process optimization model, wherein the cutting process optimization model comprises a cutting force optimization module and a cutting temperature optimization module.
According to another aspect of the present disclosure, a computer-readable storage medium is provided, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the cutting process optimization model training method according to any one of the above-mentioned methods are implemented.
So far, the embodiments of the present disclosure have been described in detail with reference to the accompanying drawings. It is to be noted that, in the attached drawings or in the description, the implementation modes not shown or described are all the modes known by the ordinary skilled person in the field of technology, and are not described in detail. Further, the above definitions of the various elements and methods are not limited to the various specific structures, shapes or arrangements of parts mentioned in the examples, which may be easily modified or substituted by those of ordinary skill in the art.
From the above description, those skilled in the art should clearly understand the cutting process optimization method, the optimization model training method and the device of the present disclosure.
In conclusion, the cutting process optimization method, the optimization model training method and the optimization model training device are reliable in process, and can reasonably optimize operation parameters, reduce machining energy consumption, reduce machining cost, improve machining efficiency and guarantee machining quality; by the cutting process optimization method, the dependence of manual experience can be reduced, the process stability can be improved, and the main defects and shortcomings of the existing cutting process optimization method can be overcome.
It should also be noted that directional terms, such as "upper", "lower", "front", "rear", "left", "right", and the like, used in the embodiments are only directions referring to the drawings, and are not intended to limit the scope of the present disclosure. Throughout the drawings, like elements are represented by like or similar reference numerals. Conventional structures or constructions will be omitted when they may obscure the understanding of the present disclosure.
And the shapes and sizes of the respective components in the drawings do not reflect actual sizes and proportions, but merely illustrate the contents of the embodiments of the present disclosure. Furthermore, in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim.
Unless otherwise indicated, the numerical parameters set forth in the specification and attached claims are approximations that can vary depending upon the desired properties sought to be obtained by the present disclosure. In particular, all numbers expressing quantities of ingredients, reaction conditions, and so forth used in the specification and claims are to be understood as being modified in all instances by the term "about". Generally, the expression is meant to encompass variations of ± 10% in some embodiments, 5% in some embodiments, 1% in some embodiments, 0.5% in some embodiments by the specified amount.
Furthermore, the word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements.
The use of ordinal numbers such as "first," "second," "third," etc., in the specification and claims to modify a corresponding element does not by itself connote any ordinal number of the element or any ordering of one element from another or the order of manufacture, and the use of the ordinal numbers is only used to distinguish one element having a certain name from another element having a same name.
In addition, unless steps are specifically described or must occur in sequence, the order of the steps is not limited to that listed above and may be changed or rearranged as desired by the desired design. The embodiments described above may be mixed and matched with each other or with other embodiments based on design and reliability considerations, i.e., technical features in different embodiments may be freely combined to form further embodiments.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. Also in the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the disclosure, various features of the disclosure are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various disclosed aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that is, the claimed disclosure requires more features than are expressly recited in each claim. Rather, as the following claims reflect, disclosed aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this disclosure.
The above-mentioned embodiments are intended to illustrate the objects, aspects and advantages of the present disclosure in further detail, and it should be understood that the above-mentioned embodiments are only illustrative of the present disclosure and are not intended to limit the present disclosure, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.

Claims (10)

1. A cutting process optimization model training method comprises the following steps:
constructing an initial cutting process optimization model, wherein the initial cutting process optimization model comprises an initial cutting force optimization module and an initial cutting temperature optimization module;
obtaining a cut and cut process training sample data set;
processing training samples in the training sample data set of the cutting process by using a sample generation method, and generating an expanded cutting process training sample data set so as to increase the number of training samples for training the initial cutting process optimization model; and
and training the initial shaving process optimization model by using the shaving process training sample data set and the augmented shaving process training sample data set to obtain the shaving process optimization model.
2. The cutting process optimization model training method according to claim 1, wherein,
the cutting process training sample data set comprises a pre-cutting process training sample data set, wherein the pre-cutting process training sample in the pre-cutting process training sample data set comprises cutting process parameter information, and the cutting process parameter information comprises cutting rotation speed information, cutting feed information and cutting depth information;
processing the training samples in the cutting process training sample data set by using a sample generation method, and generating an amplification cutting process training sample data set comprises:
and processing the cutting process parameter information in the pre-training sample by using the sample generation method, and generating an amplification pre-cutting process training sample data set, wherein the amplification pre-cutting process training sample data set comprises a plurality of amplification pre-cutting process training samples.
3. The cutting process optimization model training method according to claim 2, wherein,
training the initial shaving process optimization model by using the shaving process training sample data set and the augmented shaving process training sample data set, and obtaining the shaving process optimization model comprises the following steps:
training the initial cutting force optimization module by utilizing the pre-cutting process training sample data set to obtain a pre-training initial cutting force optimization module;
and training the initial cutting temperature optimization module by utilizing the amplification pre-cutting process training sample data set to obtain a pre-training initial cutting temperature optimization module.
4. The cutting process optimization model training method according to claim 2, wherein the cutting process parameter information corresponds to cutting force information and cutting temperature information, and the cutting force information and the cutting temperature information vary with the cutting process parameter information.
5. The optimized model training method for a skiving process according to claim 4, wherein the skiving force information is obtained by measuring a skiving process by a force measuring device; and the cutting temperature information is obtained by measuring the cutting machining process through a temperature measuring device.
6. The cutting process optimization model training method according to claim 5, wherein the force measuring device is a rotary force gauge or a piezoelectric sensing force gauge; the temperature measuring device is a sensor thermometer or a thermal imager.
7. The cutting process optimization model training method according to claim 1, wherein the sample generation method comprises one or a combination of a finite element simulation method or an empirical model method.
8. A method for optimizing a skiving process, wherein the method is implemented according to a skiving process optimization model trained by the training method according to any one of claims 1 to 7, the skiving process optimization model comprises a skiving force optimization module and a skiving temperature optimization module, and the method comprises the following steps:
inputting the parameters of the cutting process to be optimized into a cutting force optimization module of the cutting process optimization model to obtain cutting force optimization parameters;
and inputting the optimal parameters of the cutting force into a cutting temperature optimization module of the cutting process optimization model to obtain optimal cutting process parameters, wherein the optimal cutting process parameters are used for guiding the cutting machining process.
9. A cutting process optimization model training device comprises:
the system comprises a building module, a cutting temperature optimizing module and a cutting force optimizing module, wherein the building module is used for building an initial cutting process optimizing model, and the initial cutting process optimizing model comprises an initial cutting force optimizing module and an initial cutting temperature optimizing module;
the acquisition module acquires a cutting process training sample data set;
the sample generating module is used for processing the cutting process training sample data set by using a sample generating method and generating an expanded cutting process training sample data set so as to increase the number of training samples for training the initial cutting process optimization model; and
and the training module is used for training the initial cutting process optimization model by utilizing the cutting process training sample data set and the augmented cutting process training sample data set to obtain the cutting process optimization model, wherein the cutting process optimization model comprises a cutting force optimization module and a cutting temperature optimization module.
10. A computer-readable storage medium, wherein a computer program is stored thereon, which, when being executed by a processor, carries out the steps of the pareto process optimization model training method according to any one of claims 1 to 7.
CN202110771535.9A 2021-07-08 2021-07-08 Cutting process optimization method, optimization model training method and device Active CN113468689B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110771535.9A CN113468689B (en) 2021-07-08 2021-07-08 Cutting process optimization method, optimization model training method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110771535.9A CN113468689B (en) 2021-07-08 2021-07-08 Cutting process optimization method, optimization model training method and device

Publications (2)

Publication Number Publication Date
CN113468689A true CN113468689A (en) 2021-10-01
CN113468689B CN113468689B (en) 2023-06-23

Family

ID=77879004

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110771535.9A Active CN113468689B (en) 2021-07-08 2021-07-08 Cutting process optimization method, optimization model training method and device

Country Status (1)

Country Link
CN (1) CN113468689B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7933679B1 (en) * 2007-10-23 2011-04-26 Cessna Aircraft Company Method for analyzing and optimizing a machining process
CN104239624A (en) * 2014-09-05 2014-12-24 西安交通大学 Optimal design method for internal structure of machine tool body
CN110704974A (en) * 2019-09-30 2020-01-17 江苏科技大学 Modeling and using method of process model based on digital twin drive
CN111914385A (en) * 2020-02-26 2020-11-10 内蒙古民族大学 Thermal-force coupling modeling and analysis in process of equal-rake arc cutting tooth cutting
CN112861739A (en) * 2021-02-10 2021-05-28 中国科学技术大学 End-to-end text recognition method, model training method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7933679B1 (en) * 2007-10-23 2011-04-26 Cessna Aircraft Company Method for analyzing and optimizing a machining process
CN104239624A (en) * 2014-09-05 2014-12-24 西安交通大学 Optimal design method for internal structure of machine tool body
CN110704974A (en) * 2019-09-30 2020-01-17 江苏科技大学 Modeling and using method of process model based on digital twin drive
CN111914385A (en) * 2020-02-26 2020-11-10 内蒙古民族大学 Thermal-force coupling modeling and analysis in process of equal-rake arc cutting tooth cutting
CN112861739A (en) * 2021-02-10 2021-05-28 中国科学技术大学 End-to-end text recognition method, model training method and device

Also Published As

Publication number Publication date
CN113468689B (en) 2023-06-23

Similar Documents

Publication Publication Date Title
CN101412196B (en) Turning force prediction method based on cutting-tool angle and cutting amount parametric variation
Ozturk et al. Modeling of 5-axis milling processes
Jin et al. Analytical thermal models of oblique moving heat source for deep grinding and cutting
CN107944176A (en) A kind of rose cutter multi-axis milling titanium alloy Prediction Method of Milling Forces
CN103955169B (en) Method for predicting milling force of five-axis numerical control side milling
CN102622489B (en) Five-axis side milling cutting force predicting method based on ACIS platform
Soori et al. Minimization of surface roughness in 5-axis milling of turbine blades
CN107330138A (en) A kind of Milling Force Analytic modeling method of flat helical end millses
Zhang et al. A new algorithm for the numerical simulation of machined surface topography in multiaxis ball-end milling
CN106334972A (en) Method for judging cutting edge contact in ball-end mill plane machining
Ferry et al. Cutter-workpiece engagement calculations by parallel slicing for five-axis flank milling of jet engine impellers
CN113486520B (en) Digital twinning-based dynamic regulation and control method, system and device for cutting technological parameters
CN111914385A (en) Thermal-force coupling modeling and analysis in process of equal-rake arc cutting tooth cutting
CN113705057A (en) Ultrasonic vibration assisted milling force modeling method based on finite element simulation
Liang et al. Investigation of tool errors and their influences on tooth surface topography for face-hobbed hypoid gears
CN114818201A (en) Engine cylinder head milling surface quality prediction method based on mechanism and data driving
Lu et al. Smoothing rotary axes movements for ball-end milling based on the gradient-based differential evolution method
Lu et al. Tool path generation for five-axis machining of blisks with barrel cutters
Kahya et al. Precision and energy-efficient ball-end milling of Ti6Al4V turbine blades using particle swarm optimization
Wang et al. Prediction of milling force based on numerical simulation of oblique cutting
CN108255134A (en) A kind of difficult-to-machine material high-speed turning prediction of Turning Force with Artificial method for considering chamfered edge geometry
Zhang et al. Tool path optimisation for flank milling ruled surface based on the distance function
Zhou et al. Multistep method for grinding face-gear by worm
CN113468689A (en) Cutting process optimization method, optimization model training method and device
Hendriko et al. Implementation of analytical boundary simulation method for cutting force prediction model in five-axis milling

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