CN115179194A - Mold machining control method based on big data - Google Patents
Mold machining control method based on big data Download PDFInfo
- Publication number
- CN115179194A CN115179194A CN202210726828.XA CN202210726828A CN115179194A CN 115179194 A CN115179194 A CN 115179194A CN 202210726828 A CN202210726828 A CN 202210726828A CN 115179194 A CN115179194 A CN 115179194A
- Authority
- CN
- China
- Prior art keywords
- average gray
- concentric circle
- grinding
- degree
- gray value
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003754 machining Methods 0.000 title abstract description 4
- 238000000227 grinding Methods 0.000 claims abstract description 87
- 238000005498 polishing Methods 0.000 claims abstract description 85
- 238000009826 distribution Methods 0.000 claims abstract description 27
- 238000005070 sampling Methods 0.000 claims abstract description 25
- 239000004576 sand Substances 0.000 claims description 47
- 230000000694 effects Effects 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000002156 mixing Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000015654 memory Effects 0.000 claims description 7
- 238000002372 labelling Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 239000003381 stabilizer Substances 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 230000002950 deficient Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000007670 refining Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 4
- 239000002245 particle Substances 0.000 description 3
- OIGNJSKKLXVSLS-VWUMJDOOSA-N prednisolone Chemical compound O=C1C=C[C@]2(C)[C@H]3[C@@H](O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 OIGNJSKKLXVSLS-VWUMJDOOSA-N 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000008187 granular material Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 238000003723 Smelting Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000071 blow moulding Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000004512 die casting Methods 0.000 description 1
- 239000002305 electric material Substances 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- 238000005242 forging Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000001746 injection moulding Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B51/00—Arrangements for automatic control of a series of individual steps in grinding a workpiece
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
- B24B49/12—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation involving optical means
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Mechanical Engineering (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Constituent Portions Of Griding Lathes, Driving, Sensing And Control (AREA)
Abstract
The invention discloses a die machining control method based on big data, which comprises the following steps: the method comprises the following steps of firstly, sampling an original processed by each grinding and polishing machine, collecting a sampling image of each original sample, and acquiring a frequency distribution map corresponding to each original sample according to the sampling image; step two, making a plurality of concentric circles in each frequency distribution graph, acquiring the average gray value on the circumference of each concentric circle, and establishing an average gray set according to the average gray values on the circumferences of the plurality of concentric circles; and step three, acquiring the surface thinning degree and the smoothness degree of the corresponding original sample for the average gray level set of each frequency distribution map. Through the overall structure of the equipment, the centralized control of the grinding and polishing machines connected in series in multiple stages in the production process is realized, the feasibility of original part treatment is improved, the grinding of original parts meets the requirements of a mold technology more, the quality of mold original part processing is improved, and the defective rate is reduced.
Description
Technical Field
The invention relates to the technical field of mold processing based on big data, in particular to a mold processing control method based on big data.
Background
The mould is used for producing various moulds and tools of required products by injection molding, blow molding, extrusion, die casting or forging forming, smelting, stamping and other methods in the industrial production of moulds. In short, a mold is a tool used to make a shaped article, the tool being made up of various parts, different molds being made up of different parts. The method realizes the processing of the appearance of the article mainly by changing the physical state of the formed material, and the article is called as 'industrial mother'.
When a mold original is polished, when multiple stages of serially connected polishing machines are generally controlled in a centralized manner, the polishing effect of the polishing machines is poor due to inappropriate proportion of coarse sand and fine sand, and even the original is possibly wasted, so that a mold processing control method based on big data is provided.
Disclosure of Invention
The invention aims to provide a mould processing control method based on big data, which realizes the centralized control of a multistage series grinding and polishing machine in the production process, improves the feasibility of original processing, enables the grinding of the original to better meet the requirements of mould technology, improves the quality of mould original processing and reduces the defective rate.
The invention discloses a mould processing control method based on big data, which comprises an image acquisition unit, a data processing unit and an intelligent control unit, and comprises the following steps:
the method comprises the following steps of firstly, sampling an original processed by each grinding and polishing machine, collecting a sampling image of each original sample, and acquiring a frequency distribution map corresponding to each original sample according to the sampling image;
step two, making a plurality of concentric circles in each frequency distribution graph, acquiring the average gray value on the circumference of each concentric circle, and establishing an average gray set according to the average gray values on the circumferences of the plurality of concentric circles;
step three, acquiring the surface thinning degree and the smoothness degree of the corresponding original sample for the average gray level set of each frequency distribution map, and obtaining the polishing effect of each grinding and polishing machine according to the surface thinning degree and the smoothness degree;
step four, taking a plurality of grinding data obtained in the actual processing process of the original as grinding samples, wherein the grinding data comprises the surface refining degree, the smoothness degree and different coarse and fine sand proportions in each grinding and polishing machine, training the ANNs by using the grinding samples, obtaining the optimal coarse and fine sand mixing proportions corresponding to different grinding effects according to the trained ANNs, and setting the coarse and fine sand proportion in each grinding and polishing machine according to the optimal coarse and fine sand mixing proportions.
Preferably, the method for obtaining the surface refinement degree of the corresponding original sample according to the average gray level set of each histogram includes:
labeling is carried out according to the radius of the concentric circles, and the surface thinning degree of the original sample obtained according to the label of each concentric circle and the average gray level set is as follows:
where A represents the degree of grain (surface) refinement, max (c) represents the maximum mean gray value in the mean gray set, min (c) represents the minimum mean gray value in the mean gray set, c b The mean gray value corresponding to the b-th concentric circle is shown, and K/2 represents the number of concentric circles.
As a preferred scheme, the perimeter of each concentric circle and the sum of gray values corresponding to all pixel points on the circumference of the concentric circle are obtained, and the ratio of the sum of gray values to the perimeter is an average gray value, then the average gray value is calculated as:
wherein c represents the mean gray value, D m And expressing the gray value of the mth pixel point on the circumference of the concentric circle, M expressing the number of the pixel points on the circumference of the concentric circle, R expressing the radius of the concentric circle, and pi expressing the circumference ratio.
As a preferred scheme, the average gray level sets are constructed by sorting and labeling from small to large according to the radius of each concentric circle as follows:
c＝{c 1 ,c 2 ,…,c K/2 }
wherein, c 1 The average gray value of the pixel points on the circumference of the 1 st concentric circle, that is, the average gray value of the pixel points on the circumference of the concentric circle with the smallest radius，c 2 Represents the average gray value of the pixel points on the circumference of the 2 nd concentric circle, c K/2 And expressing the average gray value of the pixel points on the circumference of the K/2 th concentric circle.
As a preferable scheme, the specific method for obtaining the uniformity degree is as follows:
step 1, normalizing the average gray level set obtained in the data acquisition unit, so that the value range of all the average gray levels in the average gray level set is [0,1].
Step 2, selecting the concentric circle corresponding to the maximum average gray value after normalization in the average gray set, and marking the label corresponding to the position of the concentric circle as e max Then the smoothness is calculated as:
wherein F represents the degree of uniformity, i represents the ith concentric circle index, e max Representing the concentric circle label corresponding to the maximum average gray value in the average gray set, K/2 representing the number of concentric circles, j i Indicating the calculation state of the average gray value corresponding to the ith concentric circle.
As a preferred scheme, the coarse sand and the fine sand proportion are parameters of a grinding polisher and are adjusted manually, and the coarse sand and the fine sand proportion are calculated by the following steps:
N＝M c /M x
wherein N represents the proportion of coarse sand and the coarse sand in the grinding and polishing machine; m c Represents the mass of the grit; m x Indicating the quality of the fine sand.
Preferably, the mold processing control method based on big data is stored in an application program of a computer framework, is driven to run by a burning program, and further comprises a bus framework, a storage and a bus interface, wherein the bus framework can comprise any number of interconnected buses and bridges, the bus framework links various circuits including one or more processors represented by a processor and a memory represented by a memory, the bus framework can also connect various other circuits such as peripheral devices, voltage regulators, power management circuits and the like, the bus interface provides an interface between the bus framework and a receiver and a transmitter, and the receiver and the transmitter can be the same element, namely a transceiver, which provides a unit for communicating with various other systems on a transmission medium.
The mould processing control method based on big data disclosed by the invention has the beneficial effects that:
through the overall structure of equipment, obtain the surface refining degree based on degree of depth ANNs, the relation between the coarse and fine sand ratio in smoothness degree and the grinding and polishing machine, thereby obtain the optimum coarse and fine sand mixing ratio under the prerequisite of known effect of polishing, carry out intelligent control to every grinding and polishing machine through optimum coarse and fine sand mixing ratio, the centralized control to the multistage series connection's of production in-process grinding and polishing machine has been realized, and the feasibility that the original paper was handled has been improved, make the requirement that the mould technique was accorded with more in the polishing of original paper, the quality of mould original paper processing has been improved, the defective percentage has been reduced, unnecessary waste has been avoided.
Drawings
Fig. 1 is a schematic step diagram of an embodiment of a method for detecting movement of electric materials according to the present invention.
Detailed Description
The invention will be further elucidated and described with reference to the embodiments and drawings of the specification:
referring to fig. 1, the present invention: a mould processing control method based on big data comprises the following steps:
the method comprises the following steps of firstly, sampling an original processed by each grinding and polishing machine, collecting a sampling image of each original sample, and acquiring a frequency distribution map corresponding to each original sample according to the sampling image;
in mould original paper production process, need polish the mould spare, utilize grinding and polishing machine to polish promptly, the size of a dimension and the smoothness degree of back original paper of polishing have very big influence to the quality of mould, consequently need detect the effect of polishing after the grinding and polishing machine is polished.
Sampling an original before each grinding and polishing machine is processed to obtain an original sample, and defaulting that the weights of the original samples sampled five times are equal to ensure the accuracy of subsequent comparative analysis; original paper samples obtained through sampling are placed on a sampling platform, the sampling platform vibrates so that the original paper samples are uniformly distributed, and then corresponding sampling images are obtained through high-definition cameras corresponding to the sampling platforms.
Because be covered with the granule of polishing of mixture in the sampling image, the size and the size of the granule of polishing can make the proportion of high frequency information and low frequency information in the sampling image change, consequently the change through the frequency distribution graph carries out the analysis to the effect of polishing, and this scheme utilizes two-dimensional discrete Fourier transform algorithm to obtain the frequency distribution graph that the sampling image of every original paper sample corresponds, carries out follow-up analysis based on the frequency distribution graph that every original paper sample corresponds.
Step two, making a plurality of concentric circles in each frequency distribution graph, acquiring the average gray value on the circumference of each concentric circle, and establishing an average gray set according to the average gray values on the circumferences of the plurality of concentric circles;
obtaining a histogram corresponding to each original sample from an image acquisition unit, taking a central point of each histogram as a dot, making a plurality of concentric circles in the histogram based on the dot, namely taking the histogram corresponding to any original sample as an example, obtaining the central point of the histogram, taking the central point as the dot, making a plurality of concentric circles in the histogram, wherein the number of the concentric circles in the histogram is determined by the transverse dimension of the histogram, and if the transverse dimension of the histogram is K, the number of the concentric circles in the histogram is K/2
Step three, acquiring the surface thinning degree and the smoothness degree of the corresponding original sample for the average gray level set of each frequency distribution map, and obtaining the polishing effect of each grinding and polishing machine according to the surface thinning degree and the smoothness degree;
the low-frequency information in the histogram represents a flat area, the high-frequency information represents an edge area, and when the size of the grinding particles in the collected sampling image is smaller, the number of the grinding particles is larger and the number of the edge pixels is larger under the same quality, so that the high-frequency component value represented in the histogram is higher.
Step four, taking a plurality of grinding data obtained in the actual processing process of the original as grinding samples, wherein the grinding data comprises the surface refining degree, the smoothness degree and different coarse and fine sand proportions in each grinding and polishing machine, training the ANNs by using the grinding samples, obtaining the optimal coarse and fine sand mixing proportions corresponding to different grinding effects according to the trained ANNs, and setting the coarse and fine sand proportion in each grinding and polishing machine according to the optimal coarse and fine sand mixing proportions.
The data processing unit can obtain the grinding effect of each grinding and polishing machine in the processing process of the die original part; when raw materials with different surface fineness degrees and smoothness degrees pass through the grinding and polishing machine with the same coarse sand ratio, the obtained ground surface fineness degrees and the obtained ground smoothness degrees are different, in order to accurately obtain the relationship among the surface fineness degrees, the surface smoothness degrees and the coarse sand ratio, the scheme adopts a depth ANNs technology to realize digital twinning of the grinding and polishing machine, the depth ANNs adopt a full-connection network structure, the number of neurons in an input layer is 4, and the number of neurons in an output layer is 3; the training data set is the grinding data obtained in the actual grinding process before and after grinding of the grinding and polishing machine, the grinding data specifically comprises the surface refining degree and the smoothness degree before and after grinding of the grinding and polishing machine and the actual coarse and fine sand proportion in each grinding and polishing machine, and the specific training process is as follows:
(1) Inputting the depth ANNs into the surface refining degree of the original, the smoothness degree of the original and the coarse-fine sand ratio;
(2) The output of the depth ANNs is the surface thinning degree and the smoothness degree after the grinding and polishing machine grinds the surfaces;
(3) The loss function is a mean square error loss function.
The method for acquiring the surface refinement degree of the corresponding original sample according to the average gray level set of each frequency distribution map comprises the following steps:
labeling is carried out according to the radius of the concentric circles, and the surface thinning degree of the original sample obtained according to the label of each concentric circle and the average gray level set is as follows:
wherein A represents the grain (surface) refinement degree, max (c) represents the maximum mean gray value in the mean gray set, min (c) represents the minimum mean gray value in the mean gray set, c b The mean gray value corresponding to the b-th concentric circle is shown, and K/2 represents the number of concentric circles.
The perimeter of each concentric circle and the sum of gray values corresponding to all pixel points on the circumference of the concentric circle are obtained, and the ratio of the sum of gray values to the perimeter is an average gray value, then the average gray value is calculated as follows:
wherein c represents the mean gray value, D m And expressing the gray value of the mth pixel point on the circumference of the concentric circle, M expressing the number of the pixel points on the circumference of the concentric circle, R expressing the radius of the concentric circle, and pi expressing the circumference ratio.
The method comprises the following steps of sorting and labeling according to the radius of each concentric circle from small to large, and establishing an average gray level set as follows:
c＝{c 1 ,c 2 ,…,c K/2 }
wherein, c 1 Representing the average gray value of the pixel points on the circumference of the 1 st concentric circle, i.e. the average gray value of the pixel points on the circumference of the concentric circle with the smallest radius, c 2 Representing the average gray value of the pixel points on the circumference of the 2 nd concentric circle, c K/2 And expressing the average gray value of the pixel points on the circumference of the K/2 th concentric circle.
The specific method for obtaining the uniformity degree is as follows:
step 1, normalizing the average gray level set obtained in the data acquisition unit to enable the value range of all average gray levels in the average gray level set to be [0,1].
Step 2, selecting the concentric circle corresponding to the maximum average gray value after normalization in the average gray set, and marking the mark corresponding to the position of the concentric circle as e max Then the smoothness is calculated as:
wherein F represents the degree of uniformity, i represents the ith concentric circle index, e max Representing the number of concentric circles corresponding to the maximum mean gray value in the mean gray set, K/2 representing the number of concentric circles, j i Indicating the calculation state of the average gray value corresponding to the ith concentric circle.
Acquiring the label of the concentric circle corresponding to the maximum average gray value in the average gray set, obtaining the uniformity degree according to the label corresponding to the maximum average gray value and the number of all concentric circles, wherein the smoothness degree is related to the calculation state of each concentric circle, the calculation state of each concentric circle is obtained by the difference value between the average gray value of the concentric circle and the maximum average gray value, when the difference value is greater than a preset threshold value, the calculation state of the concentric circle is 0, and when the difference value is less than the preset threshold value, the calculation state of the concentric circle is 1.
The method for determining the calculation state of the average gray value corresponding to each concentric circle comprises the following steps:
wherein j is i Representing the calculation state of the average gray value corresponding to the ith concentric circle; g max Representing the maximum average gray value in the normalized average gray set; g i Expressing the ith average gray value in the normalized average gray set; k is a preset threshold.
The scheme takes an empirical value k =0.4.
Based on the method for obtaining the same surface refinement degree and smoothness degree of the original sample corresponding to one frequency distribution map, the surface refinement degree and the smoothness degree corresponding to the original sample before and after grinding by each grinding and polishing machine are respectively obtained, and the variation of the surface refinement degree and the smoothness degree before and after grinding by the grinding and polishing machine is the grinding effect. Specifically, the surface refinement degree and the smoothness degree of the original sample corresponding to the frequency distribution maps before and after each grinding and polishing machine are obtained, the change of the original sample before and after being polished is obtained according to the two frequency distribution maps before and after the grinding and polishing machine, and the surface fineness degree change is as follows:
ΔA＝A h -A q
wherein Δ a represents the degree of surface fineness variation; a. The h Representing the degree of particle fineness corresponding to the previous frequency distribution map of the current grinding and polishing machine; a. The q And representing the degree of surface fineness corresponding to the next frequency distribution diagram of the current grinding and polishing machine.
Further, the degree of smoothness varies as:
ΔF＝F h -F q
wherein Δ F represents the degree of smoothness change; f h Representing the smoothness degree corresponding to the previous frequency distribution diagram of the current grinding and polishing machine; f q Indicating the smoothness degree corresponding to the frequency distribution graph after the current grinding and polishing machine.
The grinding effect of each grinding and polishing machine is [ delta A, delta F ] obtained by the change of the surface fineness degree and the change of the smoothness degree.
The coarse and fine sand proportion is a parameter of the grinding and polishing machine and is manually adjusted, and the coarse and fine sand proportion is calculated by the following method:
N＝M c /M x
wherein N represents the proportion of coarse sand and the coarse sand in the grinding and polishing machine; m c Represents the mass of the grit; m is a group of x Indicating the quality of the fine sand.
And subsequently, corresponding surface thinning degree and smoothness degree can be obtained according to the sampling image of the raw material sample, and the surface thinning degree and smoothness degree after grinding of the grinding and polishing machine under different coarse-fine sand ratios are obtained through ergodic reasoning by the depth ANNs through continuously changing the coarse-fine sand ratio in the grinding and polishing machine.
During grinding and polishing machine's intelligent control in to die machining production process, at first acquire the target surface that polishes to the original paper and refine degree and target smooth degree, then calculate the surface of current original paper and refine degree and smooth degree, refine degree, target smooth degree and current surface and refine degree, current smooth degree and do the difference respectively and obtain the target sanding effect of whole multistage series connection grinding and polishing unit and do:
[ΔA,ΔF]
wherein, delta A represents the surface thinning degree change corresponding to the multistage serial grinding and polishing unit; and deltaF represents the corresponding smoothness change of the multistage grinding and polishing unit.
Further, because this scheme multistage series connection grinding and polishing unit includes four grinding and polishing machine devices, consequently obtain every grinding and polishing machine's average grinding effect according to whole multistage series connection grinding and polishing unit's target sanding effect and be:
[ΔA z /4,ΔF z /4]
wherein, delta A z Representing the surface thinning degree change corresponding to the multistage serial grinding and polishing unit; Δ F z Representing the corresponding smoothness change of the multi-stage grinding and polishing unit.
And (4) obtaining the optimal coarse and fine sand mixing proportion of each grinding and polishing machine when the corresponding polishing effect is required to be achieved according to the ergodic calculation of the trained depth ANNs, and adjusting the coarse and fine sand proportion of the grinding and polishing machine according to the obtained optimal coarse and fine sand mixing proportion to finally realize the intelligent control of each grinding and polishing machine.
A mould processing control method based on big data is stored in an application program of a computer framework and comprises an image acquisition unit, a data processing unit and an intelligent control unit, wherein the image acquisition unit, the data processing unit and the intelligent control unit are electrically connected with one another in sequence, the image acquisition unit samples an original before being processed by each grinding and polishing machine, acquires a sampling image of each original sample, acquires a frequency distribution diagram corresponding to each original sample according to the sampling image, the data acquisition unit makes a plurality of concentric circles in each frequency distribution diagram, acquires an average gray value on the circumference of each concentric circle, establishes an average gray value set according to the average gray value on the circumference of the plurality of concentric circles, and the data processing unit acquires the surface thinning degree and the smoothness degree of the corresponding original sample from the average gray value set of each frequency distribution diagram, the method comprises the steps of obtaining the polishing effect of each grinding and polishing machine according to the surface thinning degree and the smoothness degree, using the polishing samples to train ANNs by the intelligent control unit to obtain a plurality of polishing data in the actual processing process of an original as polishing samples, wherein the polishing data comprises the surface thinning degree, the smoothness degree and different coarse and fine sand proportions in each grinding and polishing machine, obtaining the optimal coarse and fine sand mixing proportion corresponding to different polishing effects according to the trained ANNs, setting the coarse and fine sand proportion in each grinding and polishing machine according to the optimal coarse and fine sand mixing proportion, performing driving operation through a burning program, and further comprising a bus architecture, a storage and a bus interface, wherein the bus architecture can comprise any number of interconnected buses and bridges, and the bus architecture links various circuits comprising one or more processors represented by the processors and a storage represented by the storage together, the bus architecture may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, together with the bus interface providing an interface between the bus architecture and a receiver and transmitter, which may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (7)
1. A mould processing control method based on big data comprises the following steps:
the method comprises the following steps of firstly, sampling an original processed by each grinding and polishing machine, collecting a sampling image of each original sample, and acquiring a frequency distribution map corresponding to each original sample according to the sampling image;
step two, making a plurality of concentric circles in each frequency distribution map, acquiring an average gray value on the circumference of each concentric circle, and establishing an average gray set according to the average gray values on the circumferences of the plurality of concentric circles;
step three, acquiring the surface refinement degree and the smoothness degree of the corresponding original sample for the average gray level set of each frequency distribution map, and obtaining the grinding effect of each grinding and polishing machine according to the surface refinement degree and the smoothness degree;
and step four, taking a plurality of polishing data obtained in the actual processing process of the original as polishing samples, wherein the polishing data comprises the surface thinning degree, the smoothness degree and different coarse and fine sand proportions in each polishing machine, training the ANNs by using the polishing samples, obtaining the optimal coarse and fine sand mixing proportions corresponding to different polishing effects according to the trained ANNs, and setting the coarse and fine sand proportion in each polishing machine according to the optimal coarse and fine sand mixing proportions.
2. The mold processing control method based on big data according to claim 1, wherein: the method for acquiring the surface refinement degree of the corresponding original sample according to the average gray level set of each frequency distribution map comprises the following steps:
labeling is carried out according to the radius of the concentric circles, and the surface thinning degree of the original sample obtained according to the label of each concentric circle and the average gray level set is as follows:
where A represents the degree of grain (surface) refinement, max (c) represents the maximum mean gray value in the mean gray set, min (c) represents the minimum mean gray value in the mean gray set, c b Represents the average gray value corresponding to the b-th concentric circleAnd K/2 represents the number of concentric circles.
3. The mold processing control method based on big data according to claim 2, wherein: the perimeter of each concentric circle and the sum of the gray values corresponding to all the pixel points on the circumference of the concentric circle are obtained, and the ratio of the sum of the gray values to the perimeter is an average gray value, then the average gray value is calculated as follows:
wherein c represents the mean gray value, D m Expressing the gray value of the mth pixel point on the circumference of the concentric circle, M expressing the number of the pixel points on the circumference of the concentric circle, R expressing the radius of the concentric circle, and pi expressing the circumference ratio.
4. The mold processing control method based on big data according to claim 3, wherein: the average gray level sets are constructed by sorting and labeling from small to large according to the radius of each concentric circle as follows:
c＝{c 1 ,c 2 ,…,c K/2 }
wherein, c 1 Representing the average gray value of the pixel points on the circumference of the 1 st concentric circle, i.e. the average gray value of the pixel points on the circumference of the concentric circle with the smallest radius, c 2 Represents the average gray value of the pixel points on the circumference of the 2 nd concentric circle, c K/2 And expressing the average gray value of the pixel points on the circumference of the K/2 th concentric circle.
5. The mold processing control method based on big data according to claim 4, wherein: the specific method for obtaining the uniformity degree is as follows:
step 1, normalizing the average gray level set obtained in the data acquisition unit to enable the value range of all average gray levels in the average gray level set to be [0,1];
step 2, selecting the averageMarking the mark number corresponding to the position of the concentric circle as e max Then the smoothness is calculated as:
wherein F represents the degree of uniformity, i represents the ith concentric circle index, e max Representing the concentric circle label corresponding to the maximum average gray value in the average gray set, K/2 representing the number of concentric circles, j i Indicating the calculation state of the average gray value corresponding to the ith concentric circle.
6. The mold processing control method based on big data according to claim 5, wherein: the coarse and fine sand proportion is a parameter of the grinding and polishing machine and is manually adjusted, and the coarse and fine sand proportion is calculated by the following method:
N＝M c /M x
wherein N represents the proportion of coarse sand and the coarse sand in the grinding and polishing machine; m is a group of c Represents the mass of the grit; m is a group of x Indicating the quality of the fine sand.
7. The big data based mold processing control method according to claim 1, wherein; a mould processing control method based on big data is stored in the application program of computer frame, driven by the burning program, and it also includes bus frame, memory and bus interface, the bus frame can include any number of interconnected buses and bridges, the bus frame links various circuits including one or more processors represented by processors and memories represented by memories, the bus frame can also connect various other circuits such as peripheral devices, voltage stabilizer and power management circuit, the bus interface provides interface between the bus frame and receiver and transmitter, the receiver and transmitter can be the same element, i.e. transceiver, providing a unit for communicating with various other systems on the transmission medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210726828.XA CN115179194A (en) | 2022-06-23 | 2022-06-23 | Mold machining control method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210726828.XA CN115179194A (en) | 2022-06-23 | 2022-06-23 | Mold machining control method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115179194A true CN115179194A (en) | 2022-10-14 |
Family
ID=83516015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210726828.XA Pending CN115179194A (en) | 2022-06-23 | 2022-06-23 | Mold machining control method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115179194A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117584153A (en) * | 2024-01-16 | 2024-02-23 | 季华实验室 | Stamping die trial grinding control method and device, electronic equipment and storage medium |
-
2022
- 2022-06-23 CN CN202210726828.XA patent/CN115179194A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117584153A (en) * | 2024-01-16 | 2024-02-23 | 季华实验室 | Stamping die trial grinding control method and device, electronic equipment and storage medium |
| CN117584153B (en) * | 2024-01-16 | 2024-04-05 | 季华实验室 | Stamping die trial grinding control method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115179194A (en) | Mold machining control method based on big data | |
| CN109815859B (en) | Automatic extraction and change analysis method for low-grade roads | |
| CN110298394B (en) | Image recognition method and related device | |
| CN113837193B (en) | Zinc flotation froth image segmentation method based on improved U-Net network | |
| CN115171097B (en) | Processing control method and system based on three-dimensional point cloud and related equipment | |
| CN114216911B (en) | Powder paving quality monitoring and controlling method in metal selective laser melting forming | |
| WO2022037499A1 (en) | Control system and control method for pelletizing machine | |
| US20160250570A1 (en) | Feed conditioning automation | |
| CN108919752B (en) | Data analysis processing system and method for tread product extrusion production line | |
| CN113569737A (en) | Notebook screen defect detection method and medium based on autonomous learning network model | |
| CN114462543B (en) | Screening method for producing recycled asphalt concrete | |
| CN114648494B (en) | Pesticide suspending agent production control system based on factory digitization | |
| CN110595959A (en) | Massecuite particle size analysis system and analysis method | |
| CN112355713B (en) | Method, device and equipment for predicting cutting force based on image | |
| CN112633393B (en) | Automatic classification method and device for ceramic tile textures | |
| CN111294588B (en) | Device and method for analyzing white pixel distribution in CMOS image sensor | |
| CN112651174A (en) | Method and device for improving efficiency of screening natural colored sand | |
| CN116555559A (en) | Intelligent control method and device for granulating sintering mixture and computer control system | |
| CN117137374B (en) | Sweeping robot recharging method based on computer vision | |
| CN111797730A (en) | Automatic analysis method for lithofacies of cement clinker | |
| CN117806387B (en) | Processing temperature regulation and control method based on data processing | |
| CN114851040B (en) | Ceramic plate polishing control system | |
| CN114723748B (en) | Detection method, device and equipment of motor controller and storage medium | |
| CN112836722B (en) | Road feel simulation method based on data driving | |
| CN112561922B (en) | Distortion three-dimensional point cloud segmentation method based on neural network |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20221014 |
|
| WD01 | Invention patent application deemed withdrawn after publication |