CN113591246B - Automatic die casting process optimization method based on DQN - Google Patents
Automatic die casting process optimization method based on DQN Download PDFInfo
- Publication number
- CN113591246B CN113591246B CN202110906279.XA CN202110906279A CN113591246B CN 113591246 B CN113591246 B CN 113591246B CN 202110906279 A CN202110906279 A CN 202110906279A CN 113591246 B CN113591246 B CN 113591246B
- Authority
- CN
- China
- Prior art keywords
- valve
- die casting
- dqn
- product
- length
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- 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
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Molds, Cores, And Manufacturing Methods Thereof (AREA)
Abstract
The invention discloses an automatic die casting process optimization method based on DQN, which comprises the following steps: (1) The water valves in the cooling system of the die casting machine are marked as water valve No. 1-water valve No. N respectively; the open and closed state of the water valve is represented by a vector with the length of 2N; wherein, the valve is in the state of the valve at the next moment with large value; (2) Acquiring a thermal image of a cooling system in the working process of the die casting machine; (3) Taking the thermal image in the step (2) as input and taking a vector with the length of 2N as output to establish an DQN model; (4) Training the DQN model established in the step (3) through big data generated by multiple trial production; (5) And (3) using the model trained in the step (4) in die casting work, and performing logic control on a valve switch of a cooling system to realize automatic optimization of a product production process. The invention realizes production optimization of the die casting process based on DQN, ensures that different positions of the die can be uniformly cooled, has high product qualification rate and prolongs the service life of the die.
Description
Technical Field
The invention relates to the field of die casting processes, in particular to an automatic optimizing method of a die casting process based on DQN.
Background
The die casting process is a precision casting method in which a metal melt is forced to be pressed into a metal mold with a complex shape by high pressure in a process of unifying pressure, speed and time by using three major elements such as a machine, a mold, an alloy and the like.
The die casting has the characteristics of high production precision, high material utilization rate and high production efficiency, and can manufacture metal parts with complex shapes, clear outlines and thin-wall deep cavities, so that the die casting is more and more widely applied.
After the die casting is performed, the temperature of the die is increased at the same time, and then the die is solidified to form a product, and the temperature of the die is also fallen back. In the process, the shape of the die cavity is complex, the temperature difference between different positions of the die is large, at the moment, the die is easy to generate microscopic deformation, microcracks are initiated, and the die is invalid and the product is disqualified. Although the existing mold is generally provided with a cooling system consisting of a plurality of cooling paths so as to ensure that different positions of the mold can be uniformly cooled, the phenomena of low product qualification rate, short service life of the mold and the like still exist due to lack of effective control.
Disclosure of Invention
The invention aims to provide an automatic die casting process optimization method based on DQN, which can solve one or more of the technical problems.
In order to achieve the above purpose, the technical scheme provided by the invention is as follows:
an automatic optimizing method of a die casting process based on DQN comprises the following steps:
(1) The water valves in the cooling system of the die casting machine are marked as water valve No. 1-water valve No. N respectively; the open and closed state of the water valve is represented by a vector with the length of 2N; wherein, the valve is in the state of the valve at the next moment with large value;
(2) Acquiring a thermal image of a cooling system in the working process of the die casting machine;
(3) Taking the thermal image in the step (2) as input and taking a vector with the length of 2N as output to establish an DQN model;
(4) Training the DQN model established in the step (3) through big data generated by a plurality of trial productions;
(5) And (3) using the model trained in the step (4) in die casting work, and performing logic control on a valve switch of a cooling system to realize automatic optimization of a product production process.
Preferably, the specific process in step (3) is as follows: initializing a structural body D; randomly generated matrix Q M×2N The method comprises the steps of carrying out a first treatment on the surface of the Wherein M refers to the times of heat patterns shot in the production process of a single die-casting product, and N refers to the number of water valves in a cooling system; initializing M deep learning networks net m 。
Preferably, the specific process in step (4) is as follows:
(41) Entering into trial production stage, setting production of ith product, taking picture for mth time, and preprocessing generated thermal image to form
Is a two-dimensional vector of 300 x 300;
(42) Randomly generating a vector s of length 2N m As an initial state for controlling the N valves;
(43) Generating a label for an mth heat map photograph of an ith product
Wherein λ is the attenuation parameter, recommended +.>
Q i-1 (m, n) is the element value of the mth row and n-th column in the Q matrix before updating,
is the quality evaluation result after the production of the ith product is completed,
wherein delta i Is the mark of the ith internal defect or not, delta when the ith product has internal defect i =0, otherwise δ i =1; j is the total number of standard sizes in the standard product; />
For the j-th dimension in standard product, < >>
Represents the j-th dimension in product i;
(44) For the ith product respectively
For input, in +.>
Updating net for labels m The method comprises the steps of carrying out a first treatment on the surface of the Respectively using net for the ith product m Update the mth row of the matrix,/>
Finally get->
(45) After the trial production is finished, Q and net are not updated any more m Obtaining Q I ，
Preferably, the deep learning network in the step (3) adopts a convolutional neural network consisting of 4 convolutional layers and 2 fully connected layers: the convolution Layer in Layer1 has 5 convolution kernels with the size of 37, the input is a two-dimensional vector with the length of 300 x 300 (the size after the pretreatment of a thermal image), and the size and the step length of the kernels in the maximum pooling Layer are 2; the convolution Layer in Layer2 has 5 convolution kernels with the size of 31, and the size and the step length of the kernels in the largest pooling Layer are 2; the convolution Layer in Layer3 has 5 convolution kernels with the size of 29, and the size and the step length of the kernels in the largest pooling Layer are 2; the convolution Layer in Layer4 has 5 convolution kernels with the size of 29, and the size and the step length of the kernels in the largest pooling Layer are 2; layer5-layer6 is a full connection layer, and the number of neurons of an output layer of layer5 is 45; the excitation function is a linear activation function; the number of output neurons of layer6 is 2N, and the activation function is a sigmoid activation function.
Preferably, the training algorithm may be: random gradient descent algorithm, adam algorithm, RMSProp algorithm, adagard algorithm, adadelta algorithm, adamax algorithm.
The invention has the technical effects that:
the invention is based on DQN, takes the image of the cooling system as input, takes the switch of the valve as output, realizes the production optimization of the die casting process, ensures that different positions of the die can be uniformly cooled, has high product qualification rate, and prolongs the service life of the die.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
In the drawings:
fig. 1 is a schematic diagram of the working logic of the present invention.
Fig. 2 is a schematic of the workflow of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the drawings and the specific embodiments thereof, wherein the exemplary embodiments and the description are for the purpose of illustrating the invention only and are not to be construed as unduly limiting the invention.
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be capable of being practiced otherwise than as specifically illustrated and described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Spatially relative terms, such as "above … …," "above … …," "upper surface at … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial location relative to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "above" or "over" other devices or structures would then be oriented "below" or "beneath" the other devices or structures. Thus, the exemplary term "above … …" may include both orientations of "above … …" and "below … …". The device may also be positioned in other different ways (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
As shown in fig. 1 and 2, an automatic optimizing method for a die casting process based on DQN includes the following steps:
(1) The water valves in the cooling system of the die casting machine are marked as water valve No. 1-water valve No. N respectively; the open and closed state of the water valve is represented by a vector with the length of 2N; wherein, the valve is in the state of the valve at the next moment with large value;
(2) Acquiring a thermal image of a cooling system in the working process of the die casting machine; preprocessing the image to generate a 300 x 300 two-dimensional vector
(3) Taking the thermal image graph (vector after preprocessing) in the step (2) as an input and taking a vector with the length of 2N as an output to establish an DQN model;
preferably, the specific process in step (3) is as follows: initializing a structural body D; randomly generated matrix Q M×2N The method comprises the steps of carrying out a first treatment on the surface of the Wherein M refers to the times of heat patterns shot in the production process of a single die-casting product, and N refers to the number of water valves in a cooling system; initializing M deep learning networks net m 。
(4) Training the DQN model established in the step (3) through big data generated by a plurality of trial productions, wherein the DQN model is correspondingly trained once after each trial production;
preferably, the specific process in step (4) is as follows:
(41) Entering into trial production stage, settingThe production of the ith product is determined, the m-th photographing is carried out by adopting a thermal imager, and the generated thermal image is preprocessed to form
Is a two-dimensional vector of 300 x 300.
(42) Randomly generating a length-2N vector S m As an initial state for controlling the N valves.
Each valve is provided with two control positions which respectively represent the opening and closing of the valve, and the value in the switch control position is large and is the state of the valve at the next moment.
For example S m ＝[1,3,2,1]Can control 2 valves S m The 1 st and 2 nd control the first valve, the 3 rd and 4 th control the second valve (other vectors and the like); the number on the front bit indicates the valve open state and the number on the rear bit indicates the valve closed state; and comparing the numbers at the front position and the rear position, wherein the current state of the valve is the number.
Above S m For example, at position 1 of the first valve (S m The 1 st bit of (2) is 1, the 2 nd bit (S) m 2 nd bit of (2)<3, thus indicating that the first valve is in the closed state;
position 1 of the second valve (S m The 3 rd bit of (2) is 2, the 2 nd bit (S) m 4 th bit of (2) is 1, since 2>1 indicates that the second valve is in an open state.
(43) Generating a label for an mth heat map photograph of an ith product
Wherein λ is the attenuation parameter, recommended +.>
Q i-1 (m, n) is the element value of the mth row and n-th column in the Q matrix before updating,
is the quality of the i-th product after the production is finishedAs a result of the evaluation, the results,
wherein delta i Is the mark of the ith internal defect or not, delta when the ith product has internal defect i =0, otherwise δ i =1; j is the total number of standard sizes in the standard product; i.e. standard product comprising J standard sizes, +.>
For the j-th dimension in standard product, < >>
Represents the j-th dimension in product i; j E [1, J]；
(44) For the ith product respectively
For input, in +.>
Updating net for labels m The method comprises the steps of carrying out a first treatment on the surface of the Respectively using net for the ith product m Update the mth row of the matrix,/>
Finally get->
(45) After the trial production is finished, Q and net are not updated any more m Obtaining Q I ，
(5) Training the model (Q) in the step (4) I ，
) In the die casting work, the valve switch of the cooling system is logically controlled to realize the automatic optimization of the product production processAnd (5) melting.
Namely: in the die casting process of each product in production, the heat map shooting is carried out in the same way, and the heat map data is input for the mth shooting
Calculating to obtain a vector with length of 2N +.>
The opening and closing of the valve is controlled according to the same logic as step (42).
Preferably, the deep learning network in the step (3) adopts a convolutional neural network consisting of 4 convolutional layers and 2 fully connected layers: the convolution Layer in Layer1 has 5 convolution kernels with the size of 37, the input is a two-dimensional vector with the length of 300 x 300 (the size after the pretreatment of a thermal image), and the size and the step length of the kernels in the maximum pooling Layer are 2; the convolution Layer in Layer2 has 5 convolution kernels with the size of 31, and the size and the step length of the kernels in the largest pooling Layer are 2; the convolution Layer in Layer3 has 5 convolution kernels with the size of 29, and the size and the step length of the kernels in the largest pooling Layer are 2; the convolution Layer in Layer4 has 5 convolution kernels with the size of 29, and the size and the step length of the kernels in the largest pooling Layer are 2; layer5-layer6 is a full connection layer, and the number of neurons of an output layer of layer5 is 45; the excitation function is a linear activation function; the number of output neurons of layer6 is 2N, and the activation function is a sigmoid activation function.
Preferably, the training algorithm may be: random gradient descent algorithm, adam algorithm, RMSProp algorithm, adagard algorithm, adadelta algorithm, adamax algorithm.
According to the automatic optimizing method of the die casting process based on the DQN, the large data corresponding to the thermal image and the valve state are established through trial production, and the DQN application network learning model is trained; and the reasonable state of the cooling system in the die casting processing process is given out through the trained model, so that the automatic adjustment and the quick response of the cooling system are realized, the processing technology of die casting is optimized, the quality of die casting products is improved, and the service life of the die is prolonged.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. The automatic die casting process optimizing method based on DQN is characterized by comprising the following steps:
(1) The water valves in the cooling system of the die casting machine are marked as water valve No. 1-water valve No. N respectively; the open and closed state of the water valve is represented by a vector with the length of 2N; wherein, the valve is in the state of the valve at the next moment with large value;
(2) Acquiring a thermal image of a cooling system in the working process of the die casting machine;
(3) Taking the thermal image in the step (2) as input and taking a vector with the length of 2N as output to establish an DQN model;
(4) Training the DQN model established in the step (3) through big data generated by a plurality of trial productions;
(5) The trained model in the step (4) is used in die casting work, and the valve switch of a cooling system is logically controlled to realize automatic optimization of the production process of the product;
the step (4) specifically comprises the following steps:
(41) Entering into trial production stage, setting production of ith product, taking picture for mth time, and preprocessing generated thermal image to form
Is a two-dimensional vector of 300 x 300;
(42) Randomly generating a length-2N vector S m As an initial state for controlling the N valves;
(43) Mth heat map photograph for ith productGenerating a label
Wherein lambda is the attenuation parameter, taking +.>
Q i-1 (m, n) is the element value of the mth row and nth column in the Q matrix before update, r i Is the quality evaluation result after the production of the ith product,/->
Wherein delta i Is the mark of the ith internal defect or not, delta when the ith product has internal defect i =0, otherwise δ i =1; j is the total number of standard sizes in the standard product; />
For the j-th dimension in standard product, < >>
Represents the j-th dimension in product i;
(44) For the ith product respectively
For input, in +.>
Updating net for labels m The method comprises the steps of carrying out a first treatment on the surface of the Respectively using net for the ith product m Update the mth row of the matrix,/>
Finally get->
(45) After the test production is finished, do notRe-updating Q and net m Obtaining Q I ，
The valve state in the step (1) with a large value is the state of the valve at the next moment, specifically S m Is a vector with the length of 2N, wherein S m The 2N-1 th bit of the valve, the 2N-1 th bit of the valve controls the N-th valve, n=1, 2, … N, the 2N-1 th bit of the valve represents the valve N open state, and the 2N bit of the valve represents the valve N closed state; comparing the number of the 2n-1 bit with the number of the 2n bit, if the number of the 2n-1 bit is large, the current state of the valve n is an open state, and if the number of the 2n bit is large, the current state of the valve n is a closed state.
2. The automatic optimizing method of die casting process based on DQN according to claim 1, wherein the specific process in step (3) is as follows: initializing a structural body D; randomly generated matrix Q M×2N The method comprises the steps of carrying out a first treatment on the surface of the Wherein M refers to the times of heat patterns shot in the production process of a single die-casting product, and N refers to the number of water valves in a cooling system; initializing M deep learning networks net m 。
3. The automatic optimizing method of die casting process based on DQN according to claim 1, wherein the deep learning network in step (3) adopts a convolutional neural network composed of 4 convolutional layers+2 fully connected layers: the convolution Layer in Layer1 has 5 convolution kernels with the size of 37, the input is a two-dimensional vector with the length of 300 x 300, and the size and the step length of the kernels in the largest pooling Layer are 2; the convolution Layer in Layer2 has 5 convolution kernels with the size of 31, and the size and the step length of the kernels in the largest pooling Layer are 2; the convolution Layer in Layer3 has 5 convolution kernels with the size of 29, and the size and the step length of the kernels in the largest pooling Layer are 2; the convolution Layer in Layer4 has 5 convolution kernels with the size of 29, and the size and the step length of the kernels in the largest pooling Layer are 2; layer5-layer6 is a full connection layer, and the number of neurons of an output layer of layer5 is 45; the excitation function is a linear activation function; the number of output neurons of layer6 is 2N, and the activation function is a sigmoid activation function.
4. A method for automatically optimizing a DQN-based die casting process according to claim 3, wherein the training algorithm is: random gradient descent algorithm, adam algorithm, RMSProp algorithm, adagard algorithm, adadelta algorithm, adamax algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110906279.XA CN113591246B (en) | 2021-08-09 | 2021-08-09 | Automatic die casting process optimization method based on DQN |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110906279.XA CN113591246B (en) | 2021-08-09 | 2021-08-09 | Automatic die casting process optimization method based on DQN |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113591246A CN113591246A (en) | 2021-11-02 |
| CN113591246B true CN113591246B (en) | 2023-06-23 |
Family
ID=78256182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110906279.XA Active CN113591246B (en) | 2021-08-09 | 2021-08-09 | Automatic die casting process optimization method based on DQN |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113591246B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115625317B (en) * | 2022-12-21 | 2023-05-16 | 昆山市恒达精密机械工业有限公司 | Surface water wave optimization processing method and system for die casting regulation and control |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105911095A (en) * | 2016-05-04 | 2016-08-31 | 东北电力大学 | Visual recognition method of continuous casting billet surface longitudinal cracks |
| CN108332858A (en) * | 2018-01-10 | 2018-07-27 | 云南电网有限责任公司电力科学研究院 | A kind of valve cooling system monitoring method and system |
| CN109675933A (en) * | 2018-12-29 | 2019-04-26 | 北京勤泽鸿翔冶金科技有限公司 | A kind of bar water cooling closed-loop control process and control system |
| CN111882535A (en) * | 2020-07-21 | 2020-11-03 | 中国计量大学 | Resistance welding shear strength identification method based on improved Unet network |
-
2021
- 2021-08-09 CN CN202110906279.XA patent/CN113591246B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105911095A (en) * | 2016-05-04 | 2016-08-31 | 东北电力大学 | Visual recognition method of continuous casting billet surface longitudinal cracks |
| CN108332858A (en) * | 2018-01-10 | 2018-07-27 | 云南电网有限责任公司电力科学研究院 | A kind of valve cooling system monitoring method and system |
| CN109675933A (en) * | 2018-12-29 | 2019-04-26 | 北京勤泽鸿翔冶金科技有限公司 | A kind of bar water cooling closed-loop control process and control system |
| CN111882535A (en) * | 2020-07-21 | 2020-11-03 | 中国计量大学 | Resistance welding shear strength identification method based on improved Unet network |
Non-Patent Citations (1)
| Title |
|---|
| 宝钢高炉冷却系统的改造与优化;居勤章;;炼铁(S1);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113591246A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113591246B (en) | Automatic die casting process optimization method based on DQN | |
| EP0787547B1 (en) | A method of investment casting and a method of making an investment casting mould | |
| CN100383796C (en) | Copper-alloy pipe-material casting-milling technology parameter designing and optimizing method | |
| US20180036928A1 (en) | Data management system | |
| CA2565927A1 (en) | Methods of and apparatus for forming hollow metal articles | |
| ATE129952T1 (en) | DEVICE AND METHOD FOR PRODUCING MOLDED SKINS AND BODIES FROM PLASTIC. | |
| D’Addona et al. | Tool wear control through cognitive paradigms | |
| CN108255059A (en) | A kind of robot control method based on simulator training | |
| KR102390019B1 (en) | Device for Multi forming | |
| KR20230019153A (en) | Method for determining at least one manufacturing parameter | |
| Rajkumar et al. | Influence of parameters on the smart productivity of modern metal casting process: an overview | |
| CN113887133A (en) | Deep learning-based automatic cooling method for die casting system | |
| FR2823321A1 (en) | Improved control system for glass shaping machine controlled by programmable sequencer which allows determination of data fixing event times in machine | |
| Venkata Rao et al. | Single-and multi-objective optimization of casting processes using Jaya algorithm and its variants | |
| CN114986855A (en) | Self-adaptive bottle blowing control method and system for bottle blowing machine | |
| JP7493045B2 (en) | Method for adapting a component description of a workpiece to be manufactured having amorphous properties - Patents.com | |
| FR2823324A1 (en) | Control device used for an individual section glass molding machine comprises a computerized model of a mathematical representation of a network-dependent diagram of an open bottle molding process, and a computer analysis unit | |
| Rutkauskas et al. | Knowledge-based method for gate and cold runner definition in injection mold design | |
| Wang et al. | Experimental and numerical investigation of 3D printed elastomeric composite with integrated SMA actuator | |
| JPWO2019177981A5 (en) | ||
| CZ2005666A3 (en) | Control of line automatic machine | |
| JPS6153020A (en) | Memory for setting molding condition and setting method that uses the same | |
| Meibodi et al. | Bespoke cast facade | |
| US3150218A (en) | Device for and method of making a series of inanimate objects having portions in relatively different postures | |
| CN116823831B (en) | Embryo image fragment removing system based on cyclic feature reasoning |
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 |