CN110428000B - Milling process energy efficiency state clustering analysis method - Google Patents

Milling process energy efficiency state clustering analysis method Download PDF

Info

Publication number
CN110428000B
CN110428000B CN201910694126.6A CN201910694126A CN110428000B CN 110428000 B CN110428000 B CN 110428000B CN 201910694126 A CN201910694126 A CN 201910694126A CN 110428000 B CN110428000 B CN 110428000B
Authority
CN
China
Prior art keywords
state
cutting
energy efficiency
milling
milling process
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
Application number
CN201910694126.6A
Other languages
Chinese (zh)
Other versions
CN110428000A (en
Inventor
蔡赟
邵华
袁键键
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.)
Shanghai Jiaotong University
Original Assignee
Shanghai Jiaotong University
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 Shanghai Jiaotong University filed Critical Shanghai Jiaotong University
Priority to CN201910694126.6A priority Critical patent/CN110428000B/en
Publication of CN110428000A publication Critical patent/CN110428000A/en
Application granted granted Critical
Publication of CN110428000B publication Critical patent/CN110428000B/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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
    • G07C3/005—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles during manufacturing process
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P80/00—Climate change mitigation technologies for sector-wide applications
    • Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Multimedia (AREA)
  • Machine Tool Sensing Apparatuses (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a milling process energy efficiency state cluster analysis method based on a temperature field heat image. The method comprises the following steps: selecting and extracting heat images under different milling conditions; establishing a corresponding relation between the milling process and the heat image, and analyzing mechanism information contained in the relation; step three: and establishing a clustering analysis method. The method can classify the energy efficiency states of the cutting process, achieves the purpose of identifying different energy efficiency states of the cutting process, and has reference value for energy-saving technology and intelligent monitoring of a manufacturing system.

Description

Milling process energy efficiency state clustering analysis method
Technical Field
The invention belongs to the field of machine manufacturing, and particularly relates to a milling process energy efficiency state clustering analysis method.
Background
The cutting machining energy efficiency assessment problem has an accelerating promotion effect on cost saving and quality improvement in the manufacturing process, has long-term positive significance on sustainable development of people and the environment, and is one of important research subjects and research hotspots in the crossing field of intelligent manufacturing and green manufacturing. From the proposition of the concept of cutting energy efficiency, the development of the concept of cutting energy efficiency is carried out for nearly 30 years so far, and the measure for improving the energy efficiency is mainly the improvement of a focusing machine tool system and a technological process, and the research is particularly carried out around the research contents of machine tool structure design, technological rule analysis or system parameter optimization and the like. Because the cutting process is a complex system engineering, the manufacturing process is very different for the total processed products of the forest, and the energy consumed in the actual cutting process is a dynamic variable superposed on the inherent energy consumption of the cutting system, the cutting energy efficiency in the actual operation process of the cutting system is also time-varying, accurate modeling and prediction are difficult to be carried out in an off-line mode in the design and process planning stages, and even if the cutting process system designed based on the high energy efficiency cannot provide quantitative real-time energy efficiency evaluation indexes on line. Even if the cutting machining system is designed to be optimized in energy efficiency, the overall energy efficiency of the machining system cannot be always kept in an expected high-energy-efficiency state due to the fact that the performance degradation of all parts (a main shaft, a feed driving system and the like) is asynchronous.
If the energy efficiency of the cutting process is regarded as a state (like a machine tool state, a cutter state, a machining quality state and the like) and the energy efficiency state of the cutting process can be monitored on line, an important reference value for solving the high-energy-efficiency cutting problem is certainly provided, however, no effective and reliable monitoring means exist at present, and a new research topic 'of judging whether a machining system in operation is in the high-energy-efficiency state' is provided for researchers.
Therefore, in the face of new challenges of intelligent manufacturing and green manufacturing, the method for monitoring the energy efficiency state of the cutting process on line needs to be mastered, and the cutting processing system can be ensured to operate in a high-energy-efficiency and high-quality state only by considering the requirements of energy, efficiency, quality and economy of the cutting system at the same time, so that the requirements of economy, environmental protection and quality are all met. Therefore, those skilled in the art have endeavored to develop a milling process energy efficient state recognition method.
Disclosure of Invention
In view of the above defects in the prior art, the technical problem to be solved by the present invention is how to apply an image processing method to classify and identify the energy efficiency state, and can locate and trace the source of the low energy efficiency problem generated by the cutting processing system, so as to provide a theoretical basis and a potential technical solution for online monitoring of the energy efficiency state of the cutting processing system, and how to judge the energy efficiency state of the milling process from the thermal image of the milling process.
In order to achieve the purpose, the invention provides a milling process energy efficiency state cluster analysis method which is characterized by comprising the following steps of:
designing a milling process energy efficiency state test, carrying out image acquisition on milling processes under different cutting conditions by using a thermal imager to obtain a plurality of groups of thermal images, selecting the thermal images according to the milling states of any one milling process at different moments, and extracting common milling states of all different cutting conditions one by one.
Step two, dividing any milling process into five identical states at different moments, namely a state I, and initially cutting the tool into the workpiece; in the second state, the transition stage from the initial cutting of the cutter into the workpiece to the full cutter head cutting of the cutter is carried out; thirdly, the cutter is full of the cutter disc to cut the workpiece; a transition stage from the state that the cutter fully cuts the workpiece by the cutter disc to the final cut-out of the workpiece; and fifthly, cutting the workpiece by the tool. Each state corresponds to a heat image, each image comprises five colors of white, red, yellow, green and blue, and the milling process mechanism and the heat image information are respectively analyzed from a machine tool spindle, a milling workpiece, a milling cutter, material chips and the environment of a milling area.
And step three, establishing a clustering analysis method based on the contents of the image color area and the milling process, and providing a milling process energy efficiency state high and low classification method based on heat image matrix characteristic value matching. Extracting each color area of the heat image respectively to obtain data matrixes of different colors, solving the process-color image matrix of all different milling conditions for norm and spectrum radius, establishing matching conditions, performing iterative operation, and finally judging different energy efficiency states of high and low.
Further, the basis for evaluating the energy efficiency state of the milling process is a milling process heat image obtained by using a thermal imager.
Further, the image matrix is defined as a matrix of five states and five colors:
Figure BDA0002148805210000021
in the formula (c) (-)iRepresenting the vector matrix of the heat map of the energy efficiency state, i representing the milling condition,
Figure BDA0002148805210000022
representing region vector, j representing image color, 1 correspondingWhite area, 2 for red area, 3 for yellow area, 4 for green area, 5 for blue area, k for milling status, 1 for status one, 2 for status two, 3 for status three, 4 for status four, 5 for status five.
Further, the clusters established from the milling state and the color region, respectively, are represented as:
from the color area the image matrix can be represented as,
from the milling state the image matrix can be represented as,
Figure BDA0002148805210000031
from the milling state the image matrix can be represented as,
Figure BDA0002148805210000032
according to the expression forms of the two types of matrixes, the image groups under different milling conditions are divided to reflect the energy efficiency states of the milling process at different moments, the energy efficiency states are embodied in the row vectors of the two matrix expression forms, and the row vectors are collectively expressed as the complete milling process under one cutting condition.
Further, the established energy efficiency state classification process may be expressed as:
step 1, solving the norm of the matrix A and the transposed matrix thereof.
The matrix a and its transpose are represented as:
Figure BDA0002148805210000033
the norm is obtained by taking the norm,
Figure BDA0002148805210000034
and step 2, solving the spectrum radius of the matrix A and the transposed matrix thereof.
Figure BDA0002148805210000041
The method comprises the steps of (1) obtaining,
Figure BDA0002148805210000042
the method comprises the steps of (1) obtaining,
Figure BDA0002148805210000043
and 3, sequencing different cutting conditions according to the norm and the spectrum radius value.
Figure BDA0002148805210000044
Figure BDA0002148805210000045
Further, the established energy efficiency state classification rule is expressed as follows:
setting classification states as 0, 1, implying high-energy-efficiency state and low-energy-efficiency state, setting matching degree,
Figure BDA0002148805210000046
setting up
Figure BDA0002148805210000047
The corresponding milling condition i is in a 0 state, and the output data is stored in the lower half area. In the same way, the method for preparing the composite material,
Figure BDA0002148805210000048
the corresponding cutting condition i is 1 state, and the output data is stored in the upper half area. Generating miscellaneous | | A | non-calculationiAnd | | | AT||iAnd (4) reordering, continuing partitioning according to the step (3), and performing iterative matching until the two types are divided into 0 and 1.
Further, the established high and low energy efficiency state judgment rule is expressed as:
the state is determined from the radius of the spectrum,
ρ(A)≤||A||
the following matching conditions are set up as follows,
if | | A | non-conducting phosphoriandρi(A) Determining the state of 0 if the element belongs to the lower half area;
if A | |T||iandρi(AT) Determining the state of 0 if the element belongs to the lower half area;
if it is
Figure BDA0002148805210000051
Then entering iterative operation;
if it is
Figure BDA0002148805210000052
Then entering iterative operation;
if | | A | non-conducting phosphoriandρi(A) Determining the state 1 if the element belongs to the upper half area;
if A | |T||iandρi(AT) Determining the state 1 if the element belongs to the upper half area;
if it is
Figure BDA0002148805210000053
Then entering iterative operation;
if it is
Figure BDA0002148805210000054
An iterative operation is entered.
Thus, the heat image state matrix can be divided into two categories, and if the corresponding parameter in category 0 is in a low energy-efficient state and the corresponding parameter in category 1 is in a high energy-efficient state, the classification is finished, and vice versa. If the mixed parameters still exist in the 0, 1 classes, the parameter group corresponding to the extreme value in the 0, 1 classes and a plurality of parameter groups adjacent to the extreme value can be obtained, so that the high-energy-efficiency state and the low-energy-efficiency state can be obtained, and the cluster analysis is finished.
Furthermore, the comparison standard of the high-energy efficiency state and the low-energy efficiency state in the milling process takes an empirical formula of the specific cutting energy or the instantaneous energy efficiency as a reference basis,
Figure BDA0002148805210000055
Figure BDA0002148805210000056
in the formula P (t)cFor machine tool cutting power at any moment, P (t) for machine tool input power at any moment, ηcIs instantaneous energy efficiency. P is the input power of the machine tool, etasThe energy transfer efficiency of the main transmission system of the machine tool is Z, the material removal rate per unit time is Z, and the specific cutting energy is E. Wherein Z can be expressed by cutting dosage element in the cutting process, and Z is apfv
In the formula apFor the depth of cut (back bite), f is the feed rate and v is the cutting speed.
In the preferred embodiment of the present invention, not only the compression of the image is realized, but also the extraction of the color image is expanded, and the general method is to use red, yellow and blue, and the method uses 5 colors and sets 5 states, so that the matrix is a square matrix.
In another preferred embodiment of the present invention, the proposed method establishes an image square matrix, making it possible to solve the eigenvalues of the image and avoid the occurrence of singular matrices.
The method has the advantages that the energy efficiency state of the milling process is researched by applying a temperature field thermal image method, so that the research on the cutting process state based on an image processing method becomes possible.
According to the invention, a large number of temperature field thermal image samples are obtained and analyzed through a large number of tests, and the number of samples is greatly more than that of samples adopted in conventional image processing.
The invention can establish a cutting process heat image library and guide various states of the cutting process, such as the states of the cutting process, such as a machine tool load state, a cutter abrasion state, a cutting quality state and the like.
Technical effects
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 is a graph of 5 states and corresponding thermal images defined by the milling process of the present invention;
FIG. 2 is a matrix diagram of a heat image of the present invention;
FIG. 3 is a matrix diagram of a low energy state heat map raw image of the present invention;
FIG. 4 is a matrix diagram after low energy state heat map image processing of the present invention;
FIG. 5 is a diagram illustrating the decomposition of the color elements of the heat map in the low energy state;
FIG. 6 is a matrix diagram of an energy efficient state heat map raw image of the present invention;
FIG. 7 is a matrix diagram after energy efficient state heat map image processing in accordance with the present invention;
FIG. 8 is a graph of the result of the decomposition of the heat map of the energy efficient state after the extraction of the color elements;
FIG. 9 is a flow chart of a cluster analysis algorithm of the present invention;
fig. 10 is a diagram showing the classification result of different milling conditions according to the present invention.
Detailed Description
The technical contents of the preferred embodiments of the present invention will be more clearly and easily understood by referring to the drawings attached to the specification. The present invention may be embodied in many different forms of embodiments and the scope of the invention is not limited to the embodiments set forth herein.
In the drawings, structurally identical elements are represented by like reference numerals, and structurally or functionally similar elements are represented by like reference numerals throughout the several views. The size and thickness of each component shown in the drawings are arbitrarily illustrated, and the present invention is not limited to the size and thickness of each component. The thickness of the components may be exaggerated where appropriate in the figures to improve clarity.
As shown in fig. 1, the milling process of the present invention defines 5 states including: in the first state, a cutter is initially cut into a workpiece; in the second state, the transition stage from the initial cutting of the cutter into the workpiece to the full cutter head cutting of the cutter is carried out; thirdly, the cutter is full of the cutter disc to cut the workpiece; a transition stage from the state that the cutter fully cuts the workpiece by the cutter disc to the final cut-out of the workpiece; and fifthly, cutting the workpiece by the tool.
State one, spindle: initial cutting, small load of the main shaft and low temperature rise; workpiece: the workpiece is placed in the environment, the temperature is similar to the environment temperature, the cutter starts to contact the workpiece, the heat exchange between the workpiece and the environment is fast, and the temperature rise is low; cutting tool: the temperature of the cutter is approximate to the ambient temperature, the cutter starts to contact with a workpiece, part of cutting edges cut, the real cutting amount is small, the load is small, and the temperature rise of the cutter is small; cutting: the chip shape is still incomplete in this state, the chip shape shows a gradual growth process, the carried heat is not large, and the chip shape exchanges heat with the external environment in the process of flowing out at a certain speed, so that the heat loss is fast; environment: the environment temperature in the initial state is stable and has no change. In the state, due to the unstable dynamic balance characteristic of the cutter, the phenomena of cutter vibration, impact and damage are easy to occur, the system stability fluctuates, the energy efficiency is judged by specific energy, the material removal volume in unit time is small, the load is low, vibration and noise of different degrees exist, and the energy efficiency is low.
State two, main shaft: the temperature rise is not changed greatly, and the heat map is slightly characterized by a light green state; workpiece: the cutting process is cutting according to real cutting quantity, the temperature of a workpiece at a cutting position is high, the heat dissipation speed is low, white, red, yellow and green are presented around the cutting position, and the part of the workpiece far away from the cutting position presents blue, which is the embodiment of a heat transfer rule; cutting tool: the temperature shows a gradual rising trend; cutting: the chip carrying heat is increased when the chip is obviously different from the first state, but most of the heat is subjected to rapid heat exchange with the outside along with the high-speed movement of the chip, and the color of the chip is yellow and green; environment: the temperature field of the environment does not change greatly; in the state, the load of a cutter is increased, the cutting tends to be in the process of gradual stabilization, the highest temperature is at the cutting position, most heat is taken away by chips, the heat dissipation of the cutting position is slower than that of the chips, and chip accumulation and cutter abrasion phenomena are easily generated at the cutting position, so that the real cutting amount is changed, the actual removal volume of the material in unit time is different from the theoretical removal volume, and the material removal volume is also changed continuously, so that the energy efficiency is influenced to be in a time-varying state, the energy efficiency is judged by specific energy, the state is higher than the energy efficiency in the initial state, and the reason is that the material removal volume in unit time is increased under the condition that the load change is not large.
State three, main shaft: the temperature change is not large, and the color degree is slightly lighter compared with the previous state; workpiece: the change of the temperature field heat map is most obvious, most of the workpieces are red, yellow and green, and the proportion of red is more, which indicates that a large amount of heat is transferred to the workpieces at the cutting positions, the heat dissipation capacity of the workpieces is inferior to that of chips and cutters, and the main reason is that the workpieces are in a fixed clamping state; cutting tool: because the state is full cutter head cutting, the cutter is completely positioned in the range of the workpiece processing surface area, the heat transferred to the cutter in the cutting process has poorer heat dissipation effect than the prior state in the state, because the state that the cutter is exposed to the environment in time and space is changed in a fundamental mode compared with the prior state, the possibility of cutter abrasion and built-up edge generation is greatly increased, and the material removal volume per unit time is time-varying; cutting: the second state is different from the second state, the dynamic characteristics of the chips in the second state are changed along with the advancing of the cutting process, the acting force on the chips in the first state and the second state mainly comes from the cutting and the friction of the cutter and has the friction with the workpiece, and the friction force between the chips and the workpiece is obviously increased when the chips in the third state are reached, so that the moving direction and the carried heat of the chips are influenced, the chips attached to the workpiece and the cutter are increased, and the temperature field of a cutting area is influenced; environment: the color degree of the blue part of the cutting area becomes light, and the environmental temperature changes; in the state, the cutter reaches a stable cutting state, a large amount of workpiece materials are removed rapidly, and the whole cutting temperature of the system is in an accelerated rising stage, wherein the state is the most important stage considering the elements of the cutting system (the load and the stability of a machine tool spindle, the cutting performance of the cutter, the cutting performance of the workpiece, inherent properties of the materials and the reasonability of cutting parameters). The energy efficiency is judged according to the specific energy, and the state is a stage with high energy efficiency.
State four, main shaft: the temperature rise can be obviously changed compared with the first state, the second state and the third state, the main shaft rotates kinetic energy to work within a period of time, a large amount of heat is generated due to the loss of functional parts, and the energy transfer efficiency of the main transmission system is changed; workpiece: it can be seen that the characteristics of the heat map of the workpiece in the state four are similar to those of the state two, but the temperature of each part region is higher than that of the state two from the view point of the overall temperature state of the workpiece, because the accumulated heat of the workpiece is more and more increased along with the progress of the cutting process, the external environment temperature is also increased, the heat dissipation capacity is weakened, more importantly, the heat diffusion region of the cutting position is shown to be in a fan-shaped outline in the state two, the temperature boundary is obvious and clear, while the characteristics of the part are obviously different from that of the state four, the boundaries of yellow, green and red regions are fuzzy, red parts are also mixed in the yellow and green regions, which are caused by two reasons, firstly, the heat transfer process of the workpiece region and the surrounding environment is different, secondly, the partially splashed chips are scattered on the machined surface of the workpiece, the surface to be machined and other surfaces of the workpiece, so that the whole temperature field of the workpiece shows the phenomenon; cutting tool: in the state, the temperature of the cutter starts to be reduced, and because the cutter is far away from a cutting workpiece at a certain moment and is in direct contact with the environment in the rotation process of the cutter disc, the heat is dissipated more quickly than when the cutter disc is full of heat for cutting; cutting: the outflow state of the chips is more scattered than the three-state chip, because the friction with the workpiece and the dynamic characteristic of the cutter are more unstable, the heat carried by the chips is not fixed, and the abrasion state of the cutter, the cutting tool mark and the deformation of the workpiece all affect the heat of the chips at any time; environment: the temperature field environment of the state is not greatly different from that of the state III; the stress characteristic of the cutter in the state is similar to that in the second state, the material removal volume in unit time is gradually reduced because the cutter is used for cutting a workpiece incompletely, the energy efficiency is judged according to the specific energy, the energy efficiency in the second state is lower than that in the second state because the temperature rise of the system is intensified, and the heat generation and loss are increased;
state five, main shaft: through the cutting, the temperature rise and the heat generation of a machine tool spindle system reach a peak value, and the main transmission system in the final state is changed from the previous blue state to the green state from a heat map; workpiece: comparing the state with the state I, the obvious difference is found, the temperature characteristics of the workpiece from the cutting initial end to the cutting terminal end show an increasing rule in the complete cutting process, and the workpiece stores heat which is determined by the heat dissipation time of the workpiece; cutting tool: the temperature of the cutter in the state is lower than that in the previous state; cutting: in the state, the chip shape becomes thin and small, the outflow direction is unstable, and the carried heat is obviously reduced compared with the previous state until no chip flows out after the final cutting is finished; environment: the environmental temperature changes remarkably, heat generated by hardware components of the cutting system exchanges heat with the environment of the cutting area through the complete cutting process, and the temperature near the cutting area diffuses to the environment far away from the cutting area; the cutting process in the state I is similar to that in the state I, and the energy efficiency is lower than that in the state I, because of the reasons of system temperature rise, the performance decline of a main shaft, the abrasion of a cutter and the elastic deformation of a workpiece.
As shown in FIG. 2, the invention establishes a milling process heat image matrix, wherein the square blocks in the matrix represent the matrix, and the row elements in the matrix are 5 defined states in sequence.
As shown in FIG. 3, the invention extracts the original heat image in the low energy efficiency state through the experiment, and the square blocks in the image represent the matrix.
As shown in FIG. 4, the original heat image is subjected to color boundary processing to obtain a form after the heat image is processed in a high energy efficiency state, a square in the figure represents a matrix, the image comprises 5 colors which are purple, red, yellow, green and blue in sequence according to the temperature, and the purple is white representing the original image for the sake of display clarity.
As shown in fig. 5, 5 colors are extracted respectively, a low energy efficiency state thermal image decomposition matrix is established, a square frame in the matrix represents the matrix, wherein row elements sequentially represent 5 milling states of a state one, a state two, a state three, a state four and a state five, column elements sequentially represent 5 temperature field color areas of purple, red, yellow, green and blue, and 0 in the matrix represents that no corresponding color area exists in the state.
As shown in FIG. 6, the original heat image in the high energy efficiency state is extracted through experiments, and the square blocks in the image represent a matrix.
As shown in fig. 7, the present invention performs color boundary processing on the original heat image in the high energy efficiency state to obtain a processed form of the heat image in the high energy efficiency state, where a square in the figure represents a matrix, and the image includes 5 colors, which are purple, red, yellow, green and blue in sequence according to the temperature, and for clarity of display, the purple is white representing the original image.
As shown in fig. 8, 5 colors are extracted respectively, a high-energy-efficiency-state thermal image decomposition matrix is established, a square frame in the matrix represents the matrix, wherein row elements sequentially represent 5 milling states of a state one, a state two, a state three, a state four and a state five, column elements sequentially represent 5 temperature field color regions of purple, red, yellow, green and blue, and 0 in the matrix represents that no corresponding color region exists in the state.
As shown in fig. 9, the invention provides a milling process energy efficiency state cluster analysis method based on a temperature field thermal image, which is characterized by comprising the following steps:
step 1, designing a milling process energy efficiency state test, carrying out image acquisition on milling processes under different cutting conditions by using a thermal imager to obtain a plurality of groups of thermal images, selecting the thermal images according to the milling states of any one milling process at different moments, and extracting common milling states of all different cutting conditions one by one.
Step 2, dividing any milling process into five identical states at different moments, namely, a state I, and initially cutting the cutter into a workpiece; in the second state, the transition stage from the initial cutting of the cutter into the workpiece to the full cutter head cutting of the cutter is carried out; thirdly, the cutter is full of the cutter disc to cut the workpiece; a transition stage from the state that the cutter is full of the cutter disc to cut the workpiece to the final cut-out of the workpiece; and fifthly, cutting the workpiece by the tool. Each state corresponds to a heat image, each image comprises five colors of white, red, yellow, green and blue, and the milling process mechanism and the heat image information are respectively analyzed from a machine tool spindle, a milling workpiece, a milling cutter, material chips and the environment of a milling area.
And 3, establishing a clustering analysis method based on the contents of the image color region and the milling process, and providing a milling process energy efficiency state high and low classification method based on heat image matrix characteristic value matching. Extracting each color area of the heat image respectively to obtain data matrixes of different colors, solving the process-color image matrix of all different milling conditions for norm and spectrum radius, establishing matching conditions, performing iterative operation, and finally judging different energy efficiency states of high and low.
The basis for evaluating the energy efficiency state of the milling process is a milling process thermal image obtained by using a thermal imager.
The image matrix is defined as a matrix of five states and five colors:
Figure BDA0002148805210000091
in the formula (c) (-)iRepresenting the vector matrix of the heat map of the energy efficiency state, i representing the milling condition,
Figure BDA0002148805210000092
the image is displayed in a mode of displaying an area vector, j represents the color of the image, 1 corresponds to a white area, 2 corresponds to a red area, 3 corresponds to a yellow area, 4 corresponds to a green area, 5 corresponds to a blue area, k represents the milling state, 1 corresponds to a state I, 2 corresponds to a state II, 3 corresponds to a state III, 4 corresponds to a state IV, and 5 corresponds to a state V.
The clusters established from the milling state and color region, respectively, are represented as: from the color region, the image matrix can be represented, from the milling state,
Figure BDA0002148805210000101
Figure BDA0002148805210000102
according to the expression forms of the two types of matrixes, the energy efficiency states of the milling process at different moments can be reflected by dividing the image group under different milling conditions, and the row vectors in the expression forms of the two types of matrixes are specifically reflected and are collectively expressed as the complete milling process under one cutting condition.
The established energy efficiency state classification process can be expressed as:
step 1, solving the norm of the matrix A and the transposed matrix thereof.
The matrix a and its transpose are represented as:
Figure BDA0002148805210000103
the norm is obtained by taking the norm,
Figure BDA0002148805210000104
and step 2, solving the spectrum radius of the matrix A and the transposed matrix thereof.
Figure BDA0002148805210000111
The method comprises the steps of (1) obtaining,
Figure BDA0002148805210000112
the method comprises the steps of (1) obtaining,
Figure BDA0002148805210000113
and 3, sequencing different cutting conditions according to the norm and the spectrum radius value.
Figure BDA0002148805210000114
Figure BDA0002148805210000115
The established energy efficiency state classification rule is expressed as follows: setting classification states as 0, 1, implying high-energy-efficiency state and low-energy-efficiency state, setting matching degree,
Figure BDA0002148805210000116
setting up
Figure BDA0002148805210000117
The corresponding milling condition i is in a 0 state, and the output data is stored in the lower half area. In the same way, the method for preparing the composite material,
Figure BDA0002148805210000118
the corresponding cutting condition i is 1 state, and the output data is stored in the upper half area. Occurrence of mixed A | non-woven phosphoriAnd | | | AT||iAnd (4) reordering, continuing partitioning according to the step (3), and performing iterative matching until the two types are divided into 0 and 1.
The established high-energy and low-energy efficiency state judgment rule is expressed as follows: the state is determined from the radius of the spectrum,
ρ(A)≤||A||
the following matching conditions are set up as follows,
if | | A | non-conducting phosphoriandρi(A) Determining the state of 0 if the element belongs to the lower half area;
if A | |T||iandρi(AT) Determining the state of 0 if the element belongs to the lower half area;
if it is
Figure BDA0002148805210000121
Then entering iterative operation;
if it is
Figure BDA0002148805210000122
Then entering iterative operation;
if | | A | non-conducting phosphoriandρi(A) Determining the state 1 when the element belongs to the upper half area;
if A | |T||iandρi(AT) Determining the state 1 if the element belongs to the upper half area;
if it is
Figure BDA0002148805210000123
Then entering iterative operation;
if it is
Figure BDA0002148805210000124
An iterative operation is entered.
Thus, the heat image state matrix can be divided into two categories, and if the corresponding parameter in category 0 is a low-energy state and the corresponding parameter in category 1 is a high-energy state, the classification is finished, and vice versa. If the mixed parameters still exist in the 0, 1 classes, the parameter group corresponding to the extreme value in the 0, 1 classes and a plurality of parameter groups adjacent to the extreme value can be obtained, so that the high-energy-efficiency state and the low-energy-efficiency state can be obtained, and the cluster analysis is finished.
The comparison standard of the high and low energy efficiency states in the milling process takes an empirical formula of the specific energy to cut or the instantaneous energy efficiency as a reference basis,
Figure BDA0002148805210000125
Figure BDA0002148805210000126
in the formula P (t)cFor machine tool cutting power at any time, P (t) is machine tool input power at any time, etacIs instantaneous energy efficiency. P is the input power of the machine tool, etasThe energy transfer efficiency of the main transmission system of the machine tool is Z, the material removal rate per unit time is Z, and the specific cutting energy is E. Wherein Z can be expressed by a cut dose element during cutting,
Z＝apfv
in the formula apFor the depth of cut (back bite), f is the feed rate and v is the cutting speed.
The method not only realizes the compression of the image, but also expands the extraction of the color image, and the general method adopts red, yellow and blue, and the method adopts 5 colors and sets 5 states to make the matrix be a square matrix. The method establishes an image square matrix, so that characteristic values of the image can be solved, and singular matrixes can be avoided. The energy efficiency state of the milling process is researched by using a temperature field thermal image method, so that the research on the cutting process state based on an image processing method becomes possible. Through a large number of tests, a large number of temperature field thermal image samples are obtained and analyzed, and the number of samples greatly exceeds that of samples adopted in conventional image processing. A cutting process heat image library can be established to guide various states of the cutting process, such as the states of the cutting process, including a machine tool load state, a cutter abrasion state, a cutting quality state and the like.
As shown in fig. 10, the present invention provides a milling process energy efficiency state classification result based on a temperature field thermal image.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.

Claims (8)

1. A milling process energy efficiency state cluster analysis method is characterized by comprising the following steps:
designing a milling process energy efficiency state test, carrying out image acquisition on milling processes under different cutting conditions by using a thermal imager to obtain a plurality of groups of thermal images, selecting the thermal images according to the milling states of any one milling process at different moments, and extracting common milling states of all different cutting conditions one by one;
step two, dividing any milling process into five identical states at different moments, namely a state I, and initially cutting the tool into the workpiece; in the second state, the transition stage from the initial cutting of the cutter into the workpiece to the full cutting of the cutter head by the cutter is realized; thirdly, the cutter is full of the cutter disc to cut the workpiece; a transition stage from the state that the cutter fully cuts the workpiece by the cutter disc to the final cut-out of the workpiece; fifthly, cutting a workpiece by a cutter; each state corresponds to a heat image, each image comprises five colors of white, red, yellow, green and blue, and the milling process mechanism and the heat image information are respectively analyzed from a machine tool spindle, a milling workpiece, a milling cutter, material chips and the environment of a milling area;
establishing a clustering analysis method based on the contents of the image color area and the milling process, and providing a milling process energy efficiency state high and low classification method based on matching of the heat image matrix characteristic values; extracting each color area of the heat image respectively to obtain data matrixes of different colors, solving norms and spectrum radiuses of the heat image matrixes of all different cutting conditions, establishing matching conditions, performing iterative operation, and finally judging different high and low energy efficiency states.
2. The milling process energy efficiency state cluster analysis method according to claim 1, wherein the milling process energy efficiency state is evaluated based on milling process heat images obtained by a thermal imager.
3. The milling process energy efficiency state cluster analysis method according to claim 1, characterized in that the image matrix is defined as five states and five color matrices as follows:
Figure FDA0003595954290000011
in the formula, thetaiRepresents a heat image matrix, i represents a cutting condition,
Figure FDA0003595954290000012
the image is displayed in a mode of displaying an area vector, j represents the color of the image, 1 corresponds to a white area, 2 corresponds to a red area, 3 corresponds to a yellow area, 4 corresponds to a green area, 5 corresponds to a blue area, k represents the milling state, 1 corresponds to a state I, 2 corresponds to a state II, 3 corresponds to a state III, 4 corresponds to a state IV, and 5 corresponds to a state V.
4. The milling process energy efficiency state cluster analysis method according to claim 3, characterized by the clusters established from the milling states and the color regions, respectively:
the matrix of images on the color area may be represented as,
Figure FDA0003595954290000021
the image matrix in the milling state can be represented as,
Figure FDA0003595954290000022
5. the milling process energy efficiency state cluster analysis method according to claim 4, characterized in that the established energy efficiency state classification process can be expressed as:
step 1, solving a matrix A and a transposition A thereofTThe number of matrices of (a);
matrix A and transpose A thereofTExpressed as:
Figure FDA0003595954290000023
the norm is obtained by taking the norm,
Figure FDA0003595954290000024
step 2, solving the matrix A and the transposition A thereofT(ii) the spectral radius of;
Figure FDA0003595954290000031
the characteristic value is obtained and the characteristic value is obtained,
Figure FDA0003595954290000032
the radius of the spectrum is obtained and,
Figure FDA0003595954290000033
step 3, sorting different cutting conditions according to norm and spectrum radius values;
Figure FDA0003595954290000034
Figure FDA0003595954290000035
in the formula, ν represents a sorting operation.
6. The milling process energy efficiency state cluster analysis method according to claim 5, characterized in that the established energy efficiency state classification rule is expressed as:
setting classification states as 0, 1, implying high-energy-efficiency state and low-energy-efficiency state, setting matching degree,
Figure FDA0003595954290000036
setting up
Figure FDA0003595954290000037
The corresponding cutting condition i is in a 0 state, and the output data is stored in the lower half area; in the same way, the method for preparing the composite material,
Figure FDA0003595954290000038
the corresponding cutting condition i is in a 1 state, and the output data is stored in the upper half area; occurrence of mixed A | non-woven phosphoriAnd | | | AT||iAnd (4) reordering, continuing partitioning according to the step (3), and performing iterative matching until the two types are divided into 0 and 1.
7. The milling process energy efficiency state cluster analysis method according to claim 6, wherein the established high and low energy efficiency state decision rule is expressed as:
the state is determined from the radius of the spectrum,
ρ(A)≤||A||
the following matching conditions are set up as follows,
if | | A | non-conducting phosphoriandρi(A) Determining the state of 0 if the element belongs to the lower half area;
if AT||iandρi(AT) Determining the state of 0 if the element belongs to the lower half area;
if it is
Figure FDA0003595954290000041
Then entering iterative operation;
if it is
Figure FDA0003595954290000042
Then entering iterative operation;
if | | A | non-conducting phosphoriandρi(A) Determining the state 1 if the element belongs to the upper half area;
if A | |T||iandρi(AT) Determining the state 1 if the element belongs to the upper half area;
if it is
Figure FDA0003595954290000043
Then entering iterative operation;
if it is
Figure FDA0003595954290000044
Then entering into iterative operation;
thus, the heat image matrix can be divided into two categories, if the corresponding parameter in the category 0 is in the low-energy-efficiency state, and the corresponding parameter in the category 1 is in the high-energy-efficiency state, the classification is finished, and vice versa; if the mixed parameters still exist in the 0, 1 classes, the parameter group corresponding to the extreme value in the 0, 1 classes and a plurality of parameter groups adjacent to the extreme value can be obtained, so that the high-energy-efficiency state and the low-energy-efficiency state can be obtained, and the cluster analysis is finished.
8. The milling process energy efficiency state cluster analysis method according to claim 7, wherein the comparison criteria of milling process high and low energy efficiency states are based on an empirical formula of specific energy to cut or instantaneous energy efficiency,
Figure FDA0003595954290000045
Figure FDA0003595954290000046
in the formula P (t)cFor machine tool cutting power at any time, Pt) is the input power of the machine tool at any moment, etacInstantaneous energy efficiency; p is the input power of the machine tool, etasThe energy transfer efficiency of a main transmission system of the machine tool is shown, Z is the material removal rate in unit time, and W is the specific energy of cutting; wherein Z can be expressed by a cut dose element during cutting,
Z＝apfv
in the formula apThe depth of cut is the amount of back bite, f is the feed rate, and v is the cutting speed.
CN201910694126.6A 2019-07-30 2019-07-30 Milling process energy efficiency state clustering analysis method Active CN110428000B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910694126.6A CN110428000B (en) 2019-07-30 2019-07-30 Milling process energy efficiency state clustering analysis method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910694126.6A CN110428000B (en) 2019-07-30 2019-07-30 Milling process energy efficiency state clustering analysis method

Publications (2)

Publication Number Publication Date
CN110428000A CN110428000A (en) 2019-11-08
CN110428000B true CN110428000B (en) 2022-07-08

Family

ID=68413140

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910694126.6A Active CN110428000B (en) 2019-07-30 2019-07-30 Milling process energy efficiency state clustering analysis method

Country Status (1)

Country Link
CN (1) CN110428000B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111158313B (en) * 2020-01-14 2022-11-29 上海交通大学 Method for modeling energy consumption and optimizing machining process of numerical control machine tool
CN112270282B (en) * 2020-11-03 2021-12-10 华北电力大学 Power signal filtering method and system by utilizing matrix spectral mode

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5463470A (en) * 1991-10-09 1995-10-31 Fuji Photo Film Co., Ltd. Methods of collecting photometric image data and determining light exposure by extracting feature image data from an original image
CN104615077A (en) * 2015-01-07 2015-05-13 重庆大学 Efficient energy-saving optimizing method for numerical control milling processing process parameters based on Taguchi method
CN105631481A (en) * 2016-01-07 2016-06-01 西安交通大学 Ferrograph abrasive particle composite characteristic construction method based on heredity programming
CN107341503A (en) * 2017-06-02 2017-11-10 上海交通大学 The recognition methods of multi-source energy efficiency state is directed in a kind of working angles
CN107507194A (en) * 2017-08-07 2017-12-22 广东电网有限责任公司珠海供电局 A kind of insulator chain fault detection method based on infrared image temperature distributing rule and BP neural network

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5463470A (en) * 1991-10-09 1995-10-31 Fuji Photo Film Co., Ltd. Methods of collecting photometric image data and determining light exposure by extracting feature image data from an original image
CN104615077A (en) * 2015-01-07 2015-05-13 重庆大学 Efficient energy-saving optimizing method for numerical control milling processing process parameters based on Taguchi method
CN105631481A (en) * 2016-01-07 2016-06-01 西安交通大学 Ferrograph abrasive particle composite characteristic construction method based on heredity programming
CN107341503A (en) * 2017-06-02 2017-11-10 上海交通大学 The recognition methods of multi-source energy efficiency state is directed in a kind of working angles
CN107507194A (en) * 2017-08-07 2017-12-22 广东电网有限责任公司珠海供电局 A kind of insulator chain fault detection method based on infrared image temperature distributing rule and BP neural network

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于振源识别的高速微铣削机床状态研究;孙岳，于占江，许金凯，于化东;《振动与冲击》;20150930;第34卷(第9期);全文 *
基于计算机泛视觉的刀具状态监测方法研究;计时鸣，张立彬，袁巨龙，周晓军;《中国会议》;20011101;全文 *

Also Published As

Publication number Publication date
CN110428000A (en) 2019-11-08

Similar Documents

Publication Publication Date Title
CN110428000B (en) Milling process energy efficiency state clustering analysis method
CN109514349B (en) Tool wear state monitoring method based on vibration signal and Stacking integrated model
Edalew et al. A computer-based intelligent system for automatic tool selection
US7697764B2 (en) Similar pattern searching apparatus, method of similar pattern searching, program for similar pattern searching, and fractionation apparatus
CN107065778B (en) One kind is towards the highest lathe Selection Method of the entire service stage energy efficiency of lathe
CN108345670B (en) Service hotspot discovery method for 95598 power work order
CN113189937B (en) Integrated management method, system and application of tools of automatic production line of aviation parts
CN116560327A (en) Electric tool production control method and system based on Internet of things
Sristi et al. Multi-response optimization of hard turning parameters: a comparison between different hybrid Taguchi-based MCDM methods
CN113369994A (en) Cutter state monitoring method in high-speed milling process
CN106680693B (en) Semiconductor chip batch testing method based on fault data gray images
Kodirov WAYS OF IMPROVING THE TECHNOLOGICAL PROCESSES OF SHEET STAMPING
Sing et al. Knowledge-based process layout system for axisymmetrical deep drawing using decision tables
Zheng et al. Investigation on wear-induced edge passivation of fine-blanking punch
CN111595697B (en) Method for judging shearing resistance forming capability of material during stamping
CN105598635B (en) A kind of fine structure part residual stress and machining deformation control method
CN116653346A (en) Online monitoring method and tool for forming quality of stamping workpiece
Jawahir et al. Predictive modeling of machining performance in turning operations
CN109396956A (en) A kind of chain digital control gear hobbing machine hobboing cutter state intelligent monitoring method
Bariani et al. Computer aided design of multi-stage cold forging process: Load peaks and strain distribution evaluation
CN113868860A (en) Part self-adaptive cost estimation method based on process knowledge
CN110929337A (en) Intelligent forming method for automobile panel die
Wang et al. Detection Algorithm of Friction and Wear State of Large Mechanical and Electrical Equipment in Coal Mine based on C-SVC
Ershov et al. Approach to the clustering modeling for the strong correlative control measurements for estimation of percent of the suitable integrated circuits in the semiconductor industry
Zhou et al. Tool selection method based on transfer learning for CNC machines

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