CN117592223B - Intelligent design method of hole machining tool for aerospace materials - Google Patents
Intelligent design method of hole machining tool for aerospace materials Download PDFInfo
- Publication number
- CN117592223B CN117592223B CN202410075852.0A CN202410075852A CN117592223B CN 117592223 B CN117592223 B CN 117592223B CN 202410075852 A CN202410075852 A CN 202410075852A CN 117592223 B CN117592223 B CN 117592223B
- Authority
- CN
- China
- Prior art keywords
- cutting
- cutter
- data
- tool
- machining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003754 machining Methods 0.000 title claims abstract description 97
- 238000013461 design Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 64
- 239000011825 aerospace material Substances 0.000 title claims description 34
- 238000005520 cutting process Methods 0.000 claims abstract description 239
- 239000000463 material Substances 0.000 claims abstract description 118
- 239000011248 coating agent Substances 0.000 claims abstract description 36
- 238000000576 coating method Methods 0.000 claims abstract description 36
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 74
- 238000012549 training Methods 0.000 claims description 33
- 238000012795 verification Methods 0.000 claims description 19
- 230000000694 effects Effects 0.000 claims description 16
- 238000004519 manufacturing process Methods 0.000 claims description 15
- 239000000126 substance Substances 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000013524 data verification Methods 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 7
- 101100366707 Arabidopsis thaliana SSL11 gene Proteins 0.000 claims description 6
- 101100366710 Arabidopsis thaliana SSL12 gene Proteins 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000003746 surface roughness Effects 0.000 claims description 4
- 101100366711 Arabidopsis thaliana SSL13 gene Proteins 0.000 claims description 3
- 102100025026 E3 ubiquitin-protein ligase TRIM68 Human genes 0.000 claims description 3
- 101100370400 Homo sapiens TRIM68 gene Proteins 0.000 claims description 3
- 101100366561 Panax ginseng SS11 gene Proteins 0.000 claims description 3
- 101100366562 Panax ginseng SS12 gene Proteins 0.000 claims description 3
- 101100366563 Panax ginseng SS13 gene Proteins 0.000 claims description 3
- 101000879465 Solanum tuberosum Sucrose synthase Proteins 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 239000011247 coating layer Substances 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 239000010410 layer Substances 0.000 description 43
- 238000004088 simulation Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 8
- 238000005457 optimization Methods 0.000 description 6
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 4
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 4
- 238000012938 design process Methods 0.000 description 4
- 239000002699 waste material Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 3
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 2
- -1 and physical Substances 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 229910000838 Al alloy Inorganic materials 0.000 description 1
- 229920000049 Carbon (fiber) Polymers 0.000 description 1
- 229910001069 Ti alloy Inorganic materials 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000004917 carbon fiber Substances 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/26—Composites
-
- 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
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- 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
- G06F2119/06—Power analysis or power 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
- G06F2119/08—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Mathematical Analysis (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses an aerospace material-oriented intelligent design method for a hole machining cutter, which comprises the following steps: selecting a cutter material and a cutter coating according to the performance requirement of a hole machining cutter, and designing the geometric shape of the cutter based on the shape and the size of a hole to be machined; combining design data of the cutter, simulating a chip forming process through finite element analysis, and obtaining cutting force and cutting temperature of the cutter with different design parameters under different machining conditions; performing cutter machining based on the determined cutter machining material, size and shape, and installing a vibration sensor, a non-contact temperature sensor and an industrial camera at a machining device for data acquisition; based on the finished tool being machined. According to the invention, the cutting of the cutter is simulated, and the simulated data assist the actual cutting of the cutter, so that the process of cutter design is accelerated, a recommended cutting parameter list can be constructed, and the quality of the cutter is improved.
Description
Technical Field
The invention belongs to the technical field of hole machining tool design, relates to a hole machining tool design method, and particularly relates to an aerospace material-oriented intelligent hole machining tool design method, which is used for realizing data collection and analysis in the tool machining process by combining finite element analysis, data acquisition, data modeling, data analysis and other technologies, reasoning about reasonable cutting parameters of a new tool, and improving tool design efficiency and cutting performance.
Background
Hole processing is an important process in machining, and has wide application in the fields of aerospace, automobile manufacturing, mold manufacturing and the like. Hole-making tools are typically referred to as drills having sharp cutting edges that, in use, are rotated and applied with axial force to form a circular hole in a workpiece. In the punching production of aerospace materials, the performance and quality of a hole machining tool directly influence the safety and reliability of aerospace structural parts. Aerospace materials refer to materials with the characteristics of high strength, high toughness, high heat resistance and the like, such as titanium alloy, aluminum alloy, nickel-based alloy, carbon fiber composite materials and the like. Because aerospace materials generally have high strength and good thermal properties, drill bits are required to have sufficient hardness, wear resistance, and thermal stability to have good cutting performance and life when processing high strength materials.
However, the existing tool design method for hole machining has some problems and disadvantages. Firstly, the existing tool design method often needs to collect and sort a large amount of data, including geometric parameters of the tool, material parameters of the tool, cutting parameters of the tool, material parameters of the workpiece, shape parameters of the workpiece, and the like, and the collection and sorting of the data needs to consume a large amount of time and manpower resources. Secondly, the existing tool design method needs to combine the collected data to carry out multiple trial cutting on the processing material so as to verify the cutting performance and service life of the tool, and the multiple trial cutting not only causes material waste, but also seriously affects the processing process of the tool design. Again, existing tool design methods fail to collect data on the ongoing tool processing and infer from this data the reasonable cutting parameters of the new tool, such as cutting speed, feed, depth of cut, etc., which have important effects on the cutting performance and life of the tool.
In summary, the existing hole processing tools have problems of low efficiency and resource waste in design and practical application, and particularly have more remarkable problems in the field of high-strength and high-heat-resistance aerospace material processing. Therefore, developing a method capable of intelligently and efficiently designing a hole machining tool to improve efficiency and quality of the hole machining tool design, reduce cost and time of the tool design, and fully utilize data in the tool machining process to optimize cutting parameters of the tool is a technical problem to be solved.
Disclosure of Invention
Object of the invention
Aiming at the defects and shortcomings in the prior art, the invention provides an aerospace material-oriented intelligent design method for a hole machining tool, which aims to solve the problems of low design efficiency, resource waste and insufficient design accuracy caused by the fact that the existing hole machining tool design method mainly relies on experience and trial cutting. By establishing a common tool database, establishing a mathematical model through simulation data, reasoning and verifying other data of the database, different tool parameters and performances can be compared and evaluated, and simulation and prediction are carried out through known data to obtain unknown data, further reasoning and optimization can be carried out on the known data, and accuracy of the known data is improved. And predicting the performance of the cutter through the data verification result, constructing a cutting parameter recommendation list according to the cutter performance prediction result, quickly determining a proper design scheme, saving time, reducing the production cost such as consumable cost, equipment maintenance cost and the like. The invention has higher intelligent degree, can more intelligently and efficiently assist the cutter design and carry out cutter cutting parameter recommendation, and ensures the production efficiency and the stability of cutter quality.
(II) technical scheme
In order to achieve the aim of the invention and solve the technical problems, the invention adopts the following technical scheme:
An aerospace material-oriented intelligent design method for a hole machining tool is characterized by at least comprising the following steps of:
SS1, determining performance requirements of a hole machining tool to be designed, including at least cutting force, cutting temperature, cutting stability and cutting life indexes, according to physical and chemical characteristics of the aerospace material to be machined and the shape, size and surface quality requirements of a hole to be machined, selecting a tool body material and a coating material coated on the surface of the tool body, and determining the geometric shape and corresponding geometric size of the hole machining tool to be designed based on the shape and size of the hole to be machined;
The method comprises the steps of SS2, constructing a finite element model of a workpiece based on physical and chemical characteristics of an aerospace material to be processed, constructing a cutter with a finite element model by combining design data of a hole machining cutter determined in the step SS1, defining boundary conditions, initial conditions and material properties of the finite element model of the workpiece and the finite element model of the cutter respectively, simulating contact and friction between the cutter and the workpiece through finite element analysis, simulating a chip forming process, setting different cutting working parameters and different cutter design parameters, obtaining relevant data of cutting force, cutting temperature, workpiece surface quality and workpiece machining deformation rule of the cutter with different design parameters under different machining conditions, analyzing cutting performance and machining effect of the cutter, evaluating cutting stability and cutting life of the cutter, and preferentially determining the cutter design parameters according to analysis results;
SS3. Based on the design parameters determined in step SS1, including at least the tool body material, coating material, geometry, and dimensions associated therewith, completing the physical machining of the tool using the tool machining device;
SS4. For the finished product cutter processed in step SS3, checking the sharpening precision and the precision allowance thereof by using a detection device to evaluate the performance and the processing effect of the finished product cutter, then using the finished product cutter to process holes on aerospace materials and collect vibration, temperature and image information of the cutter in the hole processing process in real time, and comparing and analyzing the collected actual cutting data with the simulated cutting data obtained in step SS2 to verify the consistency of the simulated cutting and the actual cutting;
SS5, establishing a database covering common cutter body materials, coating materials, workpiece materials and physical, chemical and mechanical attribute data thereof, constructing a mathematical prediction model by adopting a neural network algorithm according to the simulated cutting data obtained in the step SS2 and the actual cutting data obtained in the step SS4, classifying, optimizing and predicting the cutter body materials, the coating materials and the workpiece materials in the database based on the mathematical prediction model on the basis of fully training and verifying the mathematical prediction model, and simultaneously reasoning and verifying other data of the database including material combination, cutter performance and/or cutting parameters based on the mathematical prediction model;
and SS6, determining cutting parameters and cutting conditions to be predicted according to actual production and processing requirements, standardizing the determined cutting parameters and cutting conditions to be predicted, inputting a mathematical prediction model established and verified in step SS5, predicting the performance of the hole processing tool according to the input data verification result, evaluating cutting force, cutting temperature, cutting stability and/or cutting life indexes of the hole processing tool under different cutting parameters, and constructing a cutting parameter list of the recommended hole processing tool.
Preferably, in step SS1, according to the performance requirement of the hole processing tool, the tool body material and the coating material coated on the surface of the tool body are selected, and the geometry and the corresponding geometry of the hole processing tool to be designed are determined based on the shape and the size of the hole to be processed, and the method at least comprises the following steps:
SS11, determining the performance requirements of a hole machining tool to be designed by analyzing the specific requirements of the tool, wherein the performance requirements comprise the requirements of an aerospace material to be machined, the shape, the size and the surface quality of the hole to be machined;
SS12, selecting a proper cutter body material according to the characteristics of the aerospace material to be processed and the processing requirements of the hole to be processed;
SS13, designing the geometric shape and the corresponding geometric dimension of a cutter based on the shape and the dimension of a hole to be machined and combining the rigidity and the technological property of a cutter body material, wherein the geometric shape and the corresponding geometric dimension at least comprise a blade part structure, a cutter blade angle and a cutter core diameter;
SS14. For the processing of aerospace materials, suitable tool coating materials are selected for improving the wear resistance, heat resistance and cutting performance of the tool.
Preferably, in step SS2, the step of combining the determined design data of the hole machining tool and analyzing the simulated chip forming process by constructing a finite element model to obtain relevant data of cutting force, cutting temperature, workpiece surface quality and workpiece machining deformation rule of the hole machining tool with different design parameters under different machining conditions at least comprises the following steps:
SS21, respectively constructing finite element models of a workpiece and a cutter according to the determined aerospace material to be processed, the determined cutter body material, the determined coating material, the determined cutter shape and the determined relative size;
And SS22, based on the constructed finite element model, setting a cutting working parameter, setting a relative motion track between a cutter and a workpiece, and boundary conditions, initial conditions and material properties of the cutter and the workpiece, performing simulated trial cutting between the cutter and the workpiece, obtaining relevant data of cutting force, cutting temperature, workpiece surface quality and workpiece processing deformation rule in the cutting process, simulating the formation, fracture, flow direction and temperature change of chips according to the temperature rise, the stress and the power change generated in the cutting process, analyzing the cutting performance and the processing effect of the cutter, evaluating the cutting stability and the cutting life of the cutter, and preferentially determining the design parameters of the cutter according to the analysis result.
Preferably, in step SS3, the processing of the tool based on the determined material, coating material, shape and size of the tool body, and the mounting of the vibration sensor, non-contact temperature sensor and industrial camera at the tool processing device for data acquisition comprises the following steps:
SS31, adjusting and fixing the cutter body material according to the processing requirement, starting a cutter processing device, adjusting the technological parameters and starting cutter entity processing;
SS32. Selecting a fixed point near the spindle of the tool processing device to mount the vibration sensor, and ensuring that the sensor is in close contact with the device to accurately sense the vibration signal;
selecting an infrared thermometer and installing the infrared thermometer at a proper position to ensure that the surface temperature of an object can be accurately measured;
selecting a suitable industrial camera, and installing the industrial camera at a machining device according to the requirement to acquire image data in the machining process, including a cutting process and a chip shape;
and SS33, collecting and monitoring specific data of the vibration sensor, the infrared thermometer and the industrial camera, and timely adjusting parameters of the numerical control machining program to ensure the machining precision and quality of the cutter.
Preferably, in step SS4, based on the finished tool after machining, evaluating the performance and machining effect of the tool and comparing the simulated cutting data with the actual cutting data, verifying the consistency of the simulated cutting and the actual cutting includes the steps of:
SS41, performing performance evaluation on the cutter by using detection equipment, and checking sharpening precision and precision allowance;
SS42, performing hole machining on the aerospace material by using a finished cutter, collecting vibration, temperature and image information of the cutter in the hole machining process in real time, measuring, calculating and estimating the cutting performance of the finished cutter, and evaluating the machining effect and performance of the cutter in actual cutting;
SS43, comparing the simulated cutting data obtained in step SS2 with the actual cutting data obtained in step SS42 by using the average absolute percentage error metric method, and checking the consistency of the simulated and actual data, wherein the specific formula is as follows:
wherein n is the number of data points, Σ represents summation, MAPE is calculated data, MAPE is small, and the consistency of analog data and actual data is high;
the relative error is not influenced by the measuring unit, so that the relative error measurement method can better measure the consistency of the predicted data;
SS44. Analyzing the variability between simulated and actual cutting data, determining the source of the variability by comparing the characteristics and conditions of the simulated and actual cutting data, including machining parameters, tool wear, material properties.
Preferably, in the step SS5, a database of the common tool body materials, coating materials, workpiece materials, and physical, chemical, and mechanical attribute data thereof is established, and a mathematical prediction model is established according to the simulated cutting data obtained in the step SS2 and the actual cutting data obtained in the step SS4, so as to reasoning and verify other data of the database, including the following steps:
SS51, establishing physical, chemical and mechanical attribute data of the common tool materials, coating layers and workpiece materials, including basic material attribute, processing parameters, cutting force and cutting temperature;
SS52. Sorting and classifying the data to create a unified database comprising data structure design, data format definition, data dictionary;
SS53, according to actual cutting data and simulated cutting data collected, adopting a neural network algorithm to establish a mathematical prediction model, classifying, predicting and optimizing the cutter material, the coating material and the workpiece material through the mathematical prediction model:
SS54, inputting data to be verified into the established mathematical prediction model, and obtaining an output result of the mathematical prediction model;
SS55, evaluating and comparing the result of the reasoning verification according to the output result of the mathematical prediction model, and verifying the validity and reliability of the model by evaluating and comparing the result of the reasoning verification;
and SS56, comparing the difference between the reasoning result and the expected result, understanding the reason of the difference, and further adjusting the mathematical prediction model parameters according to the actual situation.
Further, according to the collected actual cutting data and simulated cutting data, a mathematical prediction model is established by adopting a neural network algorithm, and the cutter body material, the coating material and the workpiece material are classified, predicted and optimized by the mathematical prediction model, and the method comprises the following steps of:
SS531, selecting input variables and output variables of a neural network, and determining the basic structure and topology of a mathematical prediction model;
SS532, selecting an activation function and determining modeling details;
SS533 dividing the original data into a training set, a verification set and a test set, wherein the training set is used for training a model, the verification set is used for adjusting model parameters, and the test set is used for evaluating the generalization capability of the model;
and SS534, training the neural network model according to the divided training set, and continuously adjusting model parameters through a back propagation algorithm to reduce model training errors and verification errors.
Further, training the neural network model according to the divided training set, continuously adjusting model parameters through a back propagation algorithm, and reducing model training errors and verification errors, wherein the method comprises the following specific steps:
SS5341. Calculate output layer error:
for each training sample, the error of the output layer is calculated, using the mean square error as a loss function:
Wherein is the predicted value of the neural network to the kth output,/> is the true value of the training sample, and k is the node number of the output layer;
Starting from the output layer, propagating errors layer by layer to the hidden layer, updating the weight and bias of each layer, and outputting the layer errors:
；
Where is the derivative of the activation function,/> is the weighted input of the output layer,/> is the error of the output layer node k,/> is the hidden layer to output layer weight,/> is the error of the hidden layer node j;
SS5342 using the calculated errors, updating the weights and bias parameters in the network by gradient descent:
Updating output layer weights and offsets:
；
；
Updating hidden layer weights and offsets:
；
；
Where is the bias of the hidden layer,/> is the output of the hidden layer,/> is the bias of the output layer,/> is the weight of the input layer to the hidden layer,/> is the input variable of the input layer,/> is the activation function,/> is the learning rate for controlling the step size of the weight update.
Preferably, in step SS6, the performance prediction of the tool is performed according to the input data verification result, and a list of recommended cutting parameters is quickly constructed, including the following steps:
SS61, determining cutting parameters and cutting condition ranges to be predicted according to actual requirements;
SS62, carrying out standardized characteristic pretreatment on the input cutting parameters and cutting conditions, so that the cutting parameters and cutting conditions are suitable for inputting a mathematical prediction model;
SS63, predicting based on the input cutting parameters and conditions by using a verified mathematical prediction model to obtain corresponding performance indexes, wherein the performance indexes at least comprise cutting force, power consumption and surface roughness;
SS64, carrying out reverse normalization treatment on the prediction result to obtain an actual performance index;
SS65, constructing a recommended cutting parameter list by combining the predicted performance indexes with actual requirements.
(III) technical effects
Compared with the prior art, the intelligent design method of the hole machining tool for the aerospace material has the following beneficial and remarkable technical effects:
1. According to the invention, through finite element analysis, the chip forming process is simulated, so that simulation data such as cutting force, cutting temperature and the like of cutters with different design parameters under different processing conditions are combined with actual data acquired by a vibration sensor, a non-contact temperature sensor and an industrial camera, and the simulation data can discover problems in the design processing process in advance and are correspondingly improved and optimized, so that the production risk and cost are reduced;
the actual data is compared with the simulation data, so that simulation parameters can be adjusted in a targeted manner, the iterative design process is accelerated, the goal of optimizing the design is reached more quickly, the design process can be assisted, the actual cutting times are reduced, the design period is shortened, and the design efficiency is improved;
2. According to the invention, the common tool database is established, the mathematical prediction model is established through the simulation data, other data of the database is inferred and verified, different tool parameters and performances can be compared and evaluated, the unknown data can be obtained through simulation and prediction of the known data, further inference and optimization can be carried out on the known data, and the accuracy of the known data is improved;
3. According to the invention, the performance of the cutter is predicted through the data verification result, and the recommended cutting parameter list is quickly constructed, so that a proper design scheme can be quickly determined, a worker can directly design and process according to the recommended parameters, and meanwhile, the worker can be assisted to find the optimal cutting parameters according to the recommended cutting parameter list, so that the cutting quality is improved, and the optimal cutting parameters are selected, so that the time can be saved, and the production cost such as consumable cost, equipment maintenance cost and the like can be reduced;
4. The invention has higher intelligent degree, can more intelligently and efficiently assist the cutter design and carry out cutter cutting parameter recommendation, and ensures the production efficiency and the stability of cutter quality.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for intelligently designing an aerospace material-oriented hole machining tool according to an embodiment of the invention.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used to illustrate the embodiments and, together with the description, serve to explain the principles of the embodiments, and with reference to these descriptions, one skilled in the art will recognize other possible implementations and advantages of the present invention, wherein elements are not drawn to scale, and like reference numerals are generally used to designate like elements.
Example 1
According to the embodiment 1 of the invention, an aerospace material-oriented intelligent design method for a hole machining tool is provided. The invention is further described with reference to the accompanying drawings and the specific embodiments, as shown in fig. 1, an intelligent design method for a hole machining tool for aerospace materials according to an embodiment of the invention comprises the following steps:
SS1, determining performance requirements of a hole machining tool to be designed, including at least cutting force, cutting temperature, cutting stability and cutting life indexes, according to physical and chemical characteristics of the aerospace material to be machined and the shape, size and surface quality requirements of a hole to be machined, selecting a tool body material and a coating material coated on the surface of the tool body, and determining the geometric shape and corresponding geometric size of the hole machining tool to be designed based on the shape and size of the hole to be machined;
The method comprises the steps of SS2, constructing a finite element model of a workpiece based on physical and chemical characteristics of an aerospace material to be processed, constructing a cutter with a finite element model by combining design data of a hole machining cutter determined in the step SS1, defining boundary conditions, initial conditions and material properties of the finite element model of the workpiece and the finite element model of the cutter respectively, simulating contact and friction between the cutter and the workpiece through finite element analysis, simulating a chip forming process, setting different cutting working parameters and different cutter design parameters, obtaining relevant data of cutting force, cutting temperature, workpiece surface quality and workpiece machining deformation rule of the cutter with different design parameters under different machining conditions, analyzing cutting performance and machining effect of the cutter, evaluating cutting stability and cutting life of the cutter, and preferentially determining the cutter design parameters according to analysis results;
SS3. Based on the design parameters determined in step SS2, including at least the tool body material, coating material, geometry, and dimensions associated therewith, completing the physical machining of the tool using the tool machining device;
SS4. For the finished product cutter processed in step SS3, checking the sharpening precision and the precision allowance thereof by using a detection device to evaluate the performance and the processing effect of the finished product cutter, then using the finished product cutter to process holes on aerospace materials and collect vibration, temperature and image information of the cutter in the hole processing process in real time, and comparing and analyzing the collected actual cutting data with the simulated cutting data obtained in step SS2 to verify the consistency of the simulated cutting and the actual cutting;
SS5, establishing a database covering common cutter body materials, coating materials, workpiece materials and physical, chemical and mechanical attribute data thereof, constructing a mathematical prediction model by adopting a neural network algorithm according to the simulated cutting data obtained in the step SS2 and the actual cutting data obtained in the step SS4, classifying, optimizing and predicting the cutter body materials, the coating materials and the workpiece materials in the database based on the mathematical prediction model on the basis of fully training and verifying the mathematical prediction model, and simultaneously reasoning and verifying other data of the database including material combination, cutter performance and/or cutting parameters based on the mathematical prediction model;
and SS6, determining cutting parameters and cutting conditions to be predicted according to actual production and processing requirements, standardizing the determined cutting parameters and cutting conditions to be predicted, inputting a mathematical prediction model established and verified in step SS5, predicting the performance of the hole processing tool according to the input data verification result, evaluating cutting force, cutting temperature, cutting stability and/or cutting life indexes of the hole processing tool under different cutting parameters, and quickly constructing a cutting parameter list of the recommended hole processing tool.
In summary, through finite element analysis and simulation of the chip forming process, the invention obtains the cutting force, cutting temperature and other simulation data of the cutters with different design parameters under different processing conditions, and combines the actual data collected by the vibration sensor, the non-contact temperature sensor and the industrial camera, and the simulation data can discover the problems in the design processing process in advance and carry out corresponding improvement and optimization, thereby reducing the production risk and cost; the actual data is compared with the simulation data, so that simulation parameters can be adjusted in a targeted manner, the iterative design process is accelerated, the goal of optimizing the design is reached more quickly, the design process can be assisted, the actual cutting times are reduced, the design period is shortened, and the design efficiency is improved; according to the invention, the common tool database is established, the mathematical model is established through the simulation data, other data of the database is verified by reasoning, different tool parameters and performances can be compared and evaluated, the unknown data can be obtained through simulation and prediction of the known data, further reasoning and optimization can be carried out on the known data, and the accuracy of the known data is improved; according to the invention, the performance of the cutter is predicted through the data verification result, and the recommended cutting parameter list is quickly constructed, so that a proper design scheme can be quickly determined, a worker can directly design and process according to the recommended parameters, and meanwhile, the worker can be assisted to find the optimal cutting parameters according to the recommended cutting parameter list, so that the cutting quality is improved, and the production cost such as time saving, consumable cost reduction, equipment maintenance cost reduction and the like can be reduced by selecting the optimal cutting parameters; the invention has higher intelligent degree, can more intelligently and efficiently assist the cutter design and carry out cutter cutting parameter recommendation, and ensures the production efficiency and the stability of cutter quality.
Example 2
On the basis of the embodiment 1, the embodiment focuses on the example of further optimization of the steps SS 1-SS 4 in the aerospace material-oriented hole machining tool intelligent design method.
In a preferred embodiment of the present invention, in the step SS1, according to the performance requirement of the hole processing tool, the tool body material and the coating material coated on the surface of the tool body are selected, and the geometry and the corresponding geometry of the hole processing tool to be designed are determined based on the shape and the size of the hole to be processed, and the method at least comprises the following steps:
SS11, determining the performance requirements of a hole machining tool to be designed by analyzing the specific requirements of the tool, wherein the performance requirements comprise the requirements of an aerospace material to be machined, the shape, the size and the surface quality of the hole to be machined;
SS12, selecting a proper cutter body material according to the characteristics of the aerospace material to be processed and the processing requirements of the hole to be processed;
SS13, designing the geometric shape and the corresponding geometric dimension of a cutter based on the shape and the dimension of a hole to be machined and combining the rigidity and the technological property of a cutter body material, wherein the geometric shape and the corresponding geometric dimension at least comprise a blade part structure, a cutter blade angle and a cutter core diameter;
And SS14. For the processing of aerospace materials, proper cutter coating materials are selected for improving the wear resistance, heat resistance and cutting performance of the cutter, the friction coefficient between the cutter and a workpiece can be reduced by coating the cutter, the surface roughness and cutting force in the processing process are reduced, and the processing quality and efficiency are improved.
It should be noted that, selecting different materials according to the specific requirements of the tool can improve the cutting efficiency and reduce the processing cost; the proper geometric shape of the cutter is designed according to the shape and the size of the machined hole, so that the cutter can be better adapted to the machining requirement, and the machining precision is improved; selecting an appropriate working coating can increase the useful life of the tool.
In a preferred embodiment of the present invention, in the step SS2, the step of combining the determined design data of the hole machining tool and analyzing the simulated chip forming process by constructing a finite element model to obtain the relevant data of the cutting force, the cutting temperature, the workpiece surface quality and the workpiece machining deformation rule of the hole machining tool with different design parameters under different machining conditions at least includes the following steps:
SS21, respectively constructing finite element models of a workpiece and a cutter according to the determined aerospace material to be processed, the determined cutter body material, the determined coating material, the determined cutter shape and the determined relative size;
And SS22, based on the constructed finite element model, setting a cutting working parameter, setting a relative motion track between a cutter and a workpiece, and boundary conditions, initial conditions and material properties of the cutter and the workpiece, performing simulated trial cutting between the cutter and the workpiece, obtaining relevant data of cutting force, cutting temperature, workpiece surface quality and workpiece processing deformation rule in the cutting process, simulating the formation, fracture, flow direction and temperature change of chips according to the temperature rise, the stress and the power change generated in the cutting process, analyzing the cutting performance and the processing effect of the cutter, evaluating the cutting stability and the cutting life of the cutter, and preferentially determining the design parameters of the cutter according to the analysis result.
It is to be noted that, the finite element software replaces a large amount of trial cutting, so that the waste of materials in the trial cutting process is avoided, the time is saved, and the design and processing period is shortened; the finite element software can provide theoretical basis for actual processing, and avoid the irreproducibility of the technology and the uncontrollable quality of parts caused by unilateral experience in the traditional processing.
In a preferred embodiment of the present invention, in the step SS3, the processing of the tool based on the determined material, coating material, shape and size of the tool body, and the installation of the vibration sensor, non-contact temperature sensor and industrial camera at the tool processing device for data acquisition includes the following steps:
SS31, adjusting and fixing the cutter body material according to the processing requirement, starting a cutter processing device, adjusting the technological parameters and starting cutter entity processing;
SS32. Selecting a fixed point near the spindle of the tool processing device to mount the vibration sensor, and ensuring that the sensor is in close contact with the device to accurately sense the vibration signal;
selecting an infrared thermometer and installing the infrared thermometer at a proper position to ensure that the surface temperature of an object can be accurately measured;
selecting a suitable industrial camera, and installing the industrial camera at a machining device according to the requirement to acquire image data in the machining process, including a cutting process and a chip shape;
and SS33, collecting and monitoring specific data of the vibration sensor, the infrared thermometer and the industrial camera, and timely adjusting parameters of the numerical control machining program to ensure the machining precision and quality of the cutter.
In a preferred embodiment of the present invention, in the step SS4, based on the finished tool after machining, the performance and the machining effect of the tool are evaluated and the simulated cutting data are compared with the actual cutting data, and the verification of the consistency of the simulated cutting and the actual cutting includes the steps of:
SS41, performing performance evaluation on the cutter by using detection equipment, and checking sharpening precision and precision allowance;
SS42, performing hole machining on the aerospace material by using a finished cutter, collecting vibration, temperature and image information of the cutter in the hole machining process in real time, measuring, calculating and estimating the cutting performance of the finished cutter, and evaluating the machining effect and performance of the cutter in actual cutting;
SS43, comparing the simulated cutting data obtained in step SS2 with the actual cutting data obtained in step SS42 by using the average absolute percentage error metric method, and checking the consistency of the simulated and actual data, wherein the specific formula is as follows:
Wherein n is the number of data points, Σ represents summation, MAPE is calculated data, MAPE is small, and the consistency of analog data and actual data is high; the relative error is not influenced by the measuring unit, so that the relative error measurement method can better measure the consistency of the predicted data;
SS44. Analyzing the variability between simulated and actual cutting data, determining the source of the variability by comparing the characteristics and conditions of the simulated and actual cutting data, including machining parameters, tool wear, material properties.
It should be noted that, in the relative error measurement method, an average value of percentage errors between the analog value and the actual value is calculated and converted into a percentage form, so that the percentage errors are closer to actual prediction errors, and the percentage data can directly reflect the error level between the analog value and the actual value.
Example 3
On the basis of the embodiment 1, the embodiment focuses on an example of further optimization of steps SS5 and SS6 in the aerospace material-oriented hole machining tool intelligent design method.
In a preferred embodiment of the present invention, in the step SS5, a database of the materials of the body, the coating materials, the workpiece materials, and the physical, chemical, and mechanical attribute data of the materials is established, and a mathematical prediction model is established according to the simulated cutting data obtained in the step SS2 and the actual cutting data obtained in the step SS4, and other data of the database is verified by reasoning, including the following steps:
SS51, establishing physical, chemical and mechanical attribute data of the common tool materials, coating layers and workpiece materials, including basic material attribute, processing parameters, cutting force and cutting temperature;
SS52. Sorting and classifying the data to create a unified database comprising data structure design, data format definition, data dictionary;
SS53, according to actual cutting data and simulated cutting data collected, adopting a neural network algorithm to establish a mathematical prediction model, and classifying, predicting and optimizing the cutter material, the coating material and the workpiece material through the mathematical prediction model;
SS54, inputting data to be verified into the established mathematical prediction model, and obtaining an output result of the mathematical prediction model;
SS55, evaluating and comparing the result of the reasoning verification according to the output result of the mathematical prediction model, and verifying the validity and reliability of the model by evaluating and comparing the result of the reasoning verification;
and SS56, comparing the difference between the reasoning result and the expected result, understanding the reason of the difference, and further adjusting the mathematical prediction model parameters according to the actual situation.
It should be noted that, the difference between the reasoning result and the expected result is analyzed, so that the working principle and the decision process of the model can be better understood and explained, and the model parameters are adjusted by understanding the deviation of the model, so that the accuracy and the performance of the model can be improved.
Further, according to the collected actual cutting data and simulated cutting data, a mathematical prediction model is established by adopting a neural network algorithm, and the cutter body material, the coating material and the workpiece material are classified, predicted and optimized by the mathematical prediction model, and the method comprises the following steps of:
SS531, selecting input variables and output variables of a neural network, and determining the basic structure and topology of a mathematical prediction model;
SS532, selecting an activation function and determining modeling details;
SS533 dividing the original data into a training set, a verification set and a test set, wherein the training set is used for training a model, the verification set is used for adjusting model parameters, and the test set is used for evaluating the generalization capability of the model;
and SS534, training the neural network model according to the divided training set, and continuously adjusting model parameters through a back propagation algorithm to reduce model training errors and verification errors.
It should be noted that, according to the above calculation method, parameters of the model are continuously adjusted until the training error and the verification error are small enough to reach a certain convergence condition, so that a neural network model which can better fit the training data and has better generalization capability can be obtained.
Further, training the neural network model according to the divided training set, continuously adjusting model parameters through a back propagation algorithm, and reducing model training errors and verification errors, wherein the method comprises the following specific steps:
SS5341. Calculate output layer error:
for each training sample, the error of the output layer is calculated, using the mean square error as a loss function:
Wherein is the predicted value of the neural network to the kth output, yk is the true value of the training sample, and k is the node number of the output layer;
Starting from the output layer, propagating errors layer by layer to the hidden layer, updating the weight and bias of each layer, and outputting the layer errors:
;
Where is the derivative of the activation function,/> is the weighted input of the output layer,/> is the error of the output layer node k, is the hidden layer to output layer weight,/> is the error of the hidden layer node j;
SS5342 using the calculated errors, updating the weights and bias parameters in the network by gradient descent:
Updating output layer weights and offsets:
;/>
;
Where is the bias of the hidden layer,/> is the output of the hidden layer,/> is the bias of the output layer,/> is the weight of the input layer to the hidden layer,/> is the input variable of the input layer,/> is the activation function,/> is the learning rate for controlling the step size of the weight update.
In a preferred embodiment of the present invention, in step SS6, the performance prediction of the tool is performed according to the input data verification result, and a list of recommended cutting parameters is quickly constructed, which includes the following steps:
SS61, determining cutting parameters and cutting condition ranges to be predicted according to actual requirements;
SS62, carrying out standardized characteristic pretreatment on the input cutting parameters and cutting conditions, so that the cutting parameters and cutting conditions are suitable for inputting a mathematical prediction model;
SS63, predicting based on the input cutting parameters and conditions by using a verified mathematical prediction model to obtain corresponding performance indexes, wherein the performance indexes at least comprise cutting force, power consumption and surface roughness;
SS64, carrying out reverse normalization treatment on the prediction result to obtain an actual performance index;
SS65, constructing a recommended cutting parameter list by combining the predicted performance indexes with actual requirements.
It should be noted that, by predicting the performance of the cutter under different cutting parameters, the combination of the cutting parameters is optimized, so that the production efficiency can be improved; by recommending proper cutting parameters, the processing technology can be further optimized, and the processing quality and efficiency are improved, so that the product cost is further reduced, and the product quality is improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. An aerospace material-oriented intelligent design method for a hole machining tool is characterized by at least comprising the following steps of:
SS1, determining performance requirements of a hole machining tool to be designed, including at least cutting force, cutting temperature, cutting stability and cutting life indexes, according to physical and chemical characteristics of the aerospace material to be machined and the shape, size and surface quality requirements of a hole to be machined, selecting a tool body material and a coating material coated on the surface of the tool body, and determining the geometric shape and corresponding geometric size of the hole machining tool to be designed based on the shape and size of the hole to be machined;
The method comprises the steps of SS2, constructing a finite element model of a workpiece based on physical and chemical characteristics of an aerospace material to be processed, constructing a cutter with a finite element model by combining design data of a hole machining cutter determined in the step SS1, defining boundary conditions, initial conditions and material properties of the finite element model of the workpiece and the finite element model of the cutter respectively, simulating contact and friction between the cutter and the workpiece through finite element analysis, simulating a chip forming process, setting different cutting working parameters and different cutter design parameters, obtaining relevant data of cutting force, cutting temperature, workpiece surface quality and workpiece machining deformation rule of the cutter with different design parameters under different machining conditions, analyzing cutting performance and machining effect of the cutter, evaluating cutting stability and cutting life of the cutter, and preferentially determining the cutter design parameters according to analysis results;
SS3. Based on the design parameters determined in step SS1, including at least the tool body material, coating material, geometry, and dimensions associated therewith, completing the physical machining of the tool using the tool machining device;
SS4. For the finished product cutter processed in step SS3, checking the sharpening precision and the precision allowance thereof by using a detection device to evaluate the performance and the processing effect of the finished product cutter, then using the finished product cutter to process holes on aerospace materials and collect vibration, temperature and image information of the cutter in the hole processing process in real time, and comparing and analyzing the collected actual cutting data with the simulated cutting data obtained in step SS2 to verify the consistency of the simulated cutting and the actual cutting;
SS5, establishing a database covering common cutter body materials, coating materials, workpiece materials and physical, chemical and mechanical attribute data thereof, constructing a mathematical prediction model by adopting a neural network algorithm according to the simulated cutting data obtained in the step SS2 and the actual cutting data obtained in the step SS4, classifying, optimizing and predicting the cutter body materials, the coating materials and the workpiece materials in the database based on the mathematical prediction model on the basis of fully training and verifying the mathematical prediction model, and simultaneously reasoning and verifying other data of the database including material combination, cutter performance and/or cutting parameters based on the mathematical prediction model;
and SS6, determining cutting parameters and cutting conditions to be predicted according to actual production and processing requirements, standardizing the determined cutting parameters and cutting conditions to be predicted, inputting a mathematical prediction model established and verified in step SS5, predicting the performance of the hole processing tool according to the input data verification result, evaluating cutting force, cutting temperature, cutting stability and/or cutting life indexes of the hole processing tool under different cutting parameters, and constructing a cutting parameter list of the recommended hole processing tool.
2. The method according to claim 1, wherein in the step SS1, the material of the tool body and the coating material coated on the surface of the tool body are selected according to the performance requirement of the hole processing tool, and the geometry and the corresponding geometry of the hole processing tool to be designed are determined based on the shape and the size of the hole to be processed, and the method at least comprises:
SS11, determining the performance requirements of a hole machining tool to be designed by analyzing the specific requirements of the tool, wherein the performance requirements comprise the requirements of an aerospace material to be machined, the shape, the size and the surface quality of the hole to be machined;
SS12, selecting a proper cutter body material according to the characteristics of the aerospace material to be processed and the processing requirements of the hole to be processed;
SS13, designing the geometric shape and the corresponding geometric dimension of a cutter based on the shape and the dimension of a hole to be machined and combining the rigidity and the technological property of a cutter body material, wherein the geometric shape and the corresponding geometric dimension at least comprise a blade part structure, a cutter blade angle and a cutter core diameter;
SS14. For the processing of aerospace materials, suitable tool coating materials are selected for improving the wear resistance, heat resistance and cutting performance of the tool.
3. The intelligent design method of the hole machining tool for the aerospace material according to claim 1, wherein in the step SS2, the design data of the hole machining tool determined is combined, and the simulated chip forming process is analyzed by constructing a finite element model to obtain relevant data of cutting force, cutting temperature, workpiece surface quality and workpiece machining deformation law of the hole machining tool with different design parameters under different machining conditions, and the method at least comprises the following steps:
SS21, respectively constructing finite element models of a workpiece and a cutter according to the determined aerospace material to be processed, the determined cutter body material, the determined coating material, the determined cutter shape and the determined relative size;
And SS22, based on the constructed finite element model, setting a cutting working parameter, setting a relative motion track between a cutter and a workpiece, and boundary conditions, initial conditions and material properties of the cutter and the workpiece, performing simulated trial cutting between the cutter and the workpiece, obtaining relevant data of cutting force, cutting temperature, workpiece surface quality and workpiece processing deformation rule in the cutting process, simulating the formation, fracture, flow direction and temperature change of chips according to the temperature rise, the stress and the power change generated in the cutting process, analyzing the cutting performance and the processing effect of the cutter, evaluating the cutting stability and the cutting life of the cutter, and preferentially determining the design parameters of the cutter according to the analysis result.
4. The method of claim 1, wherein the step SS3 of completing the physical machining of the tool by using a tool machining device based on the determined tool body material, coating material, shape and size, comprises the steps of installing a vibration sensor, a non-contact temperature sensor and an industrial camera at the tool machining device for data acquisition, wherein the method comprises the following steps:
SS31, adjusting and fixing the cutter body material according to the processing requirement, starting a cutter processing device, adjusting the technological parameters and starting cutter entity processing;
SS32. Selecting a fixed point near the spindle of the tool processing device to mount the vibration sensor, and ensuring that the sensor is in close contact with the device to accurately sense the vibration signal;
selecting an infrared thermometer and installing the infrared thermometer at a proper position to ensure that the surface temperature of an object can be accurately measured;
selecting a suitable industrial camera, and installing the industrial camera at a machining device according to the requirement to acquire image data in the machining process, including a cutting process and a chip shape;
and SS33, collecting and monitoring specific data of the vibration sensor, the infrared thermometer and the industrial camera, and timely adjusting parameters of the numerical control machining program to ensure the machining precision and quality of the cutter.
5. The intelligent design method of hole machining tool for aerospace material according to claim 1, wherein in step SS5, the database of the general tool body material, coating material, workpiece material and physical, chemical and mechanical attribute data thereof is built, and meanwhile, a mathematical prediction model is built according to the simulated cutting data obtained in step SS2 and the actual cutting data obtained in step SS4, and other data of the database are verified by reasoning, comprising the following steps:
SS51, establishing physical, chemical and mechanical attribute data of the common tool materials, coating layers and workpiece materials, including basic material attribute, processing parameters, cutting force and cutting temperature;
SS52. Sorting and classifying the data to create a unified database comprising data structure design, data format definition, data dictionary;
SS53, according to actual cutting data and simulated cutting data collected, adopting a neural network algorithm to establish a mathematical prediction model, classifying, predicting and optimizing the cutter material, the coating material and the workpiece material through the mathematical prediction model:
SS54, inputting data to be verified into the established mathematical prediction model, and obtaining an output result of the mathematical prediction model;
SS55, evaluating and comparing the result of the reasoning verification according to the output result of the mathematical prediction model, and verifying the validity and reliability of the model by evaluating and comparing the result of the reasoning verification;
and SS56, comparing the difference between the reasoning result and the expected result, understanding the reason of the difference, and further adjusting the mathematical prediction model parameters according to the actual situation.
6. The aerospace material-oriented intelligent design method for hole machining tools according to claim 5, wherein the steps of establishing a mathematical prediction model by using a neural network algorithm according to the collected actual cutting data and simulated cutting data, and classifying, predicting and optimizing the tool body material, the coating material and the workpiece material by using the mathematical prediction model include the following steps:
SS531, selecting input variables and output variables of a neural network, and determining the basic structure and topology of a mathematical prediction model;
SS532, selecting an activation function and determining modeling details;
SS533 dividing the original data into a training set, a verification set and a test set, wherein the training set is used for training a model, the verification set is used for adjusting model parameters, and the test set is used for evaluating the generalization capability of the model;
and SS534, training the neural network model according to the divided training set, and continuously adjusting model parameters through a back propagation algorithm to reduce model training errors and verification errors.
7. The intelligent design method of the hole machining tool for the aerospace material according to claim 1, wherein in the step SS6, the performance of the tool is predicted by the input data verification result, and the recommended cutting parameter list is quickly constructed, comprising the following steps:
SS61, determining cutting parameters and cutting condition ranges to be predicted according to actual requirements;
SS62, carrying out standardized characteristic pretreatment on the input cutting parameters and cutting conditions, so that the cutting parameters and cutting conditions are suitable for inputting a mathematical prediction model;
SS63, predicting based on the input cutting parameters and conditions by using a verified mathematical prediction model to obtain corresponding performance indexes, wherein the performance indexes at least comprise cutting force, power consumption and surface roughness;
SS64, carrying out reverse normalization treatment on the prediction result to obtain an actual performance index;
SS65, constructing a recommended cutting parameter list by combining the predicted performance indexes with actual requirements.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410075852.0A CN117592223B (en) | 2024-01-18 | 2024-01-18 | Intelligent design method of hole machining tool for aerospace materials |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410075852.0A CN117592223B (en) | 2024-01-18 | 2024-01-18 | Intelligent design method of hole machining tool for aerospace materials |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117592223A CN117592223A (en) | 2024-02-23 |
| CN117592223B true CN117592223B (en) | 2024-04-16 |
Family
ID=89910309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410075852.0A Active CN117592223B (en) | 2024-01-18 | 2024-01-18 | Intelligent design method of hole machining tool for aerospace materials |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117592223B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2119521A2 (en) * | 2008-05-14 | 2009-11-18 | United Technologies Corporation | Broach tool design method and systems |
| CN109766638A (en) * | 2019-01-11 | 2019-05-17 | 中国科学院工程热物理研究所 | A kind of fuel nozzle and its light-weight design method |
| CN113158559A (en) * | 2021-04-02 | 2021-07-23 | 杭州电子科技大学 | Efficient intelligent design method for precise complex cutter |
| CN115329492A (en) * | 2022-08-17 | 2022-11-11 | 武汉德昇科技有限公司 | Multi-objective optimization method for stainless steel turning technological parameters based on MLP and variant PSO |
-
2024
- 2024-01-18 CN CN202410075852.0A patent/CN117592223B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2119521A2 (en) * | 2008-05-14 | 2009-11-18 | United Technologies Corporation | Broach tool design method and systems |
| CN109766638A (en) * | 2019-01-11 | 2019-05-17 | 中国科学院工程热物理研究所 | A kind of fuel nozzle and its light-weight design method |
| CN113158559A (en) * | 2021-04-02 | 2021-07-23 | 杭州电子科技大学 | Efficient intelligent design method for precise complex cutter |
| CN115329492A (en) * | 2022-08-17 | 2022-11-11 | 武汉德昇科技有限公司 | Multi-objective optimization method for stainless steel turning technological parameters based on MLP and variant PSO |
Non-Patent Citations (3)
| Title |
|---|
| PCD刀具车削超硬铝合金的切削性能研究;马殿文;沈春根;张宇;姚炀;;工具技术;20200320(第03期);全文 * |
| 回转摆线铣刀和锥形圆弧侧刃铣刀设计及其切削性能研究;王广越;CNKI-博士电子期刊;20210415;全文 * |
| 基于激光选区熔化的金属点阵结构力学性能研究;丁若晨;CNKI-博士电子期刊;20220215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117592223A (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11761930B2 (en) | Prediction method of part surface roughness and tool wear based on multi-task learning | |
| CN111366123B (en) | Part surface roughness and cutter wear prediction method based on multi-task learning | |
| Lee et al. | On-line surface roughness recognition system using artificial neural networks system in turning operations | |
| CN107627152B (en) | Numerical control machining chip control method based on BP neural network | |
| CN110647943A (en) | Cutting tool wear monitoring method based on evolutionary data cluster analysis | |
| Vinodh | Parametric optimization of fused deposition modelling process using Grey based Taguchi and TOPSIS methods for an automotive component | |
| Huang et al. | Development of a Grey online modeling surface roughness monitoring system in end milling operations | |
| CN107391890B (en) | Prediction and optimal control method for oil casing threaded joint machining chatter defect | |
| Deng et al. | Reliability analysis of chatter stability for milling process system with uncertainties based on neural network and fourth moment method | |
| CN116578832B (en) | Device for predicting surface roughness of machined part | |
| Xie et al. | A generic evolutionary ensemble learning framework for surface roughness prediction in manufacturing | |
| CN117592223B (en) | Intelligent design method of hole machining tool for aerospace materials | |
| Ji et al. | Research on wear state identification and life prediction technology of ultrasonic straight-edge knife | |
| Sharma et al. | An approach for condition monitoring of a turning tool | |
| Garg et al. | Evaluation of the performance of backpropagation and radial basis function neural networks in predicting the drill flank wear | |
| CN112966449B (en) | Manufacturing process quality defect root cause diagnosis method based on variable selection and probabilistic neural network | |
| CN112529099A (en) | Robot milling chatter identification method | |
| Abdelwahab | Surface roughness modeling and prediction based on vibration signal analysis and machining parameters in milling of aluminum by artificial neural network | |
| Zou et al. | Development of a tool wear online monitoring system for dry gear hobbing machine based on new experimental approach and DAE-BPNN-integrated mathematic structure | |
| Yerramareddy et al. | Developing empirical models from observational data using artificial neural networks | |
| Herrera-Granados et al. | An experimental study of multi-sensor tool wear monitoring and its application to predictive maintenance | |
| Xu et al. | Cutting-state identification of machine tools based on improved Dempster-Shafer evidence theory | |
| Antosz et al. | Pre-processing Signal Analysis for Cutting Tool Condition in the Milling Process | |
| El Ouafi et al. | An ANN based multi-sensor integration approach for in-process monitoring of product quality in turning operations | |
| Zhang et al. | Experimental investigation and multi-objective optimization approach for low-carbon milling operation of aluminum |
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 |