CN110955147A - Sizing process parameter optimization method - Google Patents
Sizing process parameter optimization method Download PDFInfo
- Publication number
- CN110955147A CN110955147A CN201911295564.1A CN201911295564A CN110955147A CN 110955147 A CN110955147 A CN 110955147A CN 201911295564 A CN201911295564 A CN 201911295564A CN 110955147 A CN110955147 A CN 110955147A
- Authority
- CN
- China
- Prior art keywords
- parameters
- spraying
- process parameters
- neural network
- network model
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Application Of Or Painting With Fluid Materials (AREA)
Abstract
The invention relates to a sizing technology on a shoemaking production line, in particular to a sizing technological parameter optimization method. The method comprises the following steps of S1, spraying under different process parameters, and collecting corresponding spraying quality parameters under different process parameters; s2, training a neural network model by adopting the information obtained in the step S1, taking the process parameters as an input layer of the neural network model, and taking the spraying quality parameters as an output layer of the neural network model; and step S3, obtaining expected values of the spraying quality parameters through experiments, searching in a given process parameter range based on a particle swarm search algorithm, and searching for target process parameters, wherein the difference between the spraying quality parameters of the target process parameters calculated through a neural network model and the expected values of the spraying quality parameters is smaller than a threshold value. The method obtains the technological parameters according to the expected values of the glue spraying quality parameters, and ensures that the quality of the shoes obtained by spraying the spraying equipment based on the technological parameters is optimal.
Description
Technical Field
The invention relates to a sizing technology on a shoemaking production line, in particular to a sizing technological parameter optimization method.
Background
The shoe industry in China has a long history. With the development of manufacturing industry, China has once become the biggest shoe industry production center and the sale center all over the world, forms a very perfect industrial chain and an industrial development platform, and basically occupies the middle-low-end shoe product market all over the world.
The shoe making industry in China is a labor-intensive industry, the process is complicated, the technical content is relatively low, the shoe making industry in China occupies middle and low-end markets for a long time, and the high-end shoe making industry is mainly concentrated in Italy, Spain, portugal and the like. At present, the manufacturing industry of China is in a critical point of transformation and upgrading, the shoe making industry of China faces the transformation from a middle-low end to a high-end industry, and in the transformation process, the automatic shoe making production line gradually replaces the traditional manual shoe making mode.
Most of the existing automatic shoe production lines adopt six-joint robots, people are liberated from severe environments, and production precision and efficiency are greatly improved. The RFID technology is introduced into the shoe tree to interact with the robot, and the robot applies glue according to different glue applying tracks according to shoe information in the RFID, so that the production efficiency is improved, and the quality is guaranteed. Meanwhile, with the development of cameras, the deep fusion of the 3D vision technology and the industrial robot becomes the basis for solving the complicated and changeable shoemaking industry, and the progress of the technology gradually becomes the automatic development for promoting the shoemaking industry.
Footwear is typically manufactured through molding, cutting, and assembly processes. One of the most important is the assembly process, i.e., the process of combining the upper, sole and other components together. The existing shoe making and forming method mainly comprises various process methods such as a glue combination process, a sewing process and the like, wherein the glue process is widely applied to the shoe making and forming process due to the advantages of simple process, low manufacturing cost, high production efficiency and the like. Cold-stick shoes are a typical example of shoes formed by the gluing process. The cold-bonding shoe vamp and sole are separately treated, the surfaces of the cold-bonding shoe vamp and the sole are softened by spraying a treating agent before the cold-bonding shoe vamp and the sole are attached, and then the cold-bonding shoe vamp and the sole are baked in an oven, glue is sprayed at a gluing station, and the cold-bonding shoe vamp and the sole are baked again. The process of spraying the treating agent is to soften the surface to facilitate the adhesion of the glue.
The manufacturing process of the cold-bonded shoe is complex, wherein the gluing link is crucial to the quality of the finished product. The existing automatic shoemaking production line uses a large number of six-joint robots to finish the gluing work of vamps. This change, while being very labor-saving, still relies on the experience of the operator to adjust the process parameters. In the process of adjusting technological parameters, the gluing station of the robot is required to stop working, and the yield of a production line and the working beat of the shoe upper and the shoe sole are seriously influenced.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a gluing process parameter optimization method, which obtains process parameters according to expected values of glue spraying quality parameters and ensures that the quality of shoes sprayed by spraying equipment based on the process parameters is optimal. The problem of prior art, automatic shoemaking production line when certain parameter changes among them, readjust other technological parameter so as to guarantee that the stability of spraying quality is not influenced by great.
The invention adopts the following technical scheme:
a method for optimizing parameters of a sizing process comprises the following steps,
s1, spraying under different process parameters, and collecting corresponding spraying quality parameters under different process parameters;
s2, training a neural network model by adopting the information obtained in the step S1, taking the process parameters as an input layer of the neural network model, and taking the spraying quality parameters as an output layer of the neural network model;
and step S3, obtaining expected values of the spraying quality parameters through experiments, searching in a given process parameter range based on a particle swarm search algorithm, and searching for target process parameters, wherein the difference between the spraying quality parameters of the target process parameters calculated through a neural network model and the expected values of the spraying quality parameters is smaller than a threshold value.
According to the technical scheme, the technological parameters are further optimized, technological parameters influencing the spraying quality are selected, and the spraying quality parameters are used for measuring the spraying quality.
According to the further optimization of the technical scheme, the technological parameters comprise one or more of the moving speed of the robot, the distance between the upper and the tail end of the spray gun, the atomizing pressure, the feeding pressure and the viscosity of glue according to the characteristics of the spraying system of the shoemaking production line.
According to the technical scheme, the spraying quality parameters comprise the glue spraying width and/or the glue spraying thickness.
In a further optimization of the technical scheme, step S1 further includes discretizing the process parameters, randomly combining a plurality of discretized process parameters to obtain a limited set of process parameter sets, and obtaining the spraying quality parameters corresponding to each process parameter set of the robot spraying system through experiments.
The technical scheme is further optimized, and discretization is equal-step discretization.
In the further optimization of the technical scheme, the neural network model in the step S2 is used for fitting a complex nonlinear relation between the process parameters and the spraying quality parameters as follows:
wherein the content of the first and second substances,andthe parameters of the quality of the spray coating are shown,the set of process parameters is indicated. A neural network model is selected for fitting a complex non-linear relationship between process parameters and spray quality. The specific method is that all collected parameter sets are divided into a training set, a verification set and a test set according to the proportion. Inputting the training set into a neural network model to train the neural network model; obtaining an optimal model from the trained models through a verification set, namely adjusting various parameters of the neural network model; the performance of the model is measured by the test set.
Compared with the prior art, the invention has the following beneficial effects:
1. the method is based on an automatic robot spraying system, a process parameter model is established through a neural network, and optimal parameters are searched through a particle swarm optimization algorithm, so that the method for intelligently controlling the glue applying process parameters is obtained.
2. The spraying system based on the method can correct the deviation of spraying quality brought by the change of the process parameters in real time, and automatically adjust and calibrate various process parameters on the production line without human participation so as to ensure that the spraying work is stably and efficiently carried out.
Drawings
FIG. 1 is a schematic view of an automated production line for cold-bonded shoes;
FIG. 2 is a block diagram of a spray system for an automated shoe manufacturing line;
FIG. 3 is a flow chart of a method of sizing process parameter optimization;
FIG. 4 is a flow chart of an embodiment for on-line optimization of process parameters.
Detailed Description
To further illustrate the various embodiments, the invention provides the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments. Those skilled in the art will appreciate still other possible embodiments and advantages of the present invention with reference to these figures. Elements in the figures are not drawn to scale and like reference numerals are generally used to indicate like elements.
The invention will now be further described with reference to the accompanying drawings and detailed description.
Referring to fig. 1, a schematic view of an automatic production line for cold-bonded shoes is shown. This automatic shoemaking production line specifically includes: the device comprises a conveyor belt and a driving mechanism 1 thereof, a climbing upper baking mechanism 2, a heat setting mechanism 3, a visual scanning mechanism 4, a vamp marking mechanism 5, a primary gluing mechanism 6, a primary baking mechanism 7, a secondary gluing mechanism 8, a secondary baking mechanism 9, a bottom pressing and attaching mechanism 10 and a cooling and setting mechanism 11. The mechanisms 2-11 are all stations of the automatic production line of the cold-bonded shoes and are distributed on the conveyor belt 1. The conveying belt 1 moves at a constant speed, the shoe uppers are sleeved on the shoe trees and are arranged on the accompanying fixture to move along with the conveying belt 1 in the direction of an arrow shown in the figure, and the shoe uppers reach another station from one station. The shoe upper is subjected to steaming, shoe finishing and shoe lasting at the initial position of the conveyor belt. The vamp reaches the upper climbing baking mechanism 2 along with the transmission belt, and the shoe tree is baked at the station; after the shoe upper is baked, the production line personnel manually climb the shoe upper; then the vamp is brought to a heat setting mechanism 3 along with the transmission belt to complete the heat setting of the vamp; the vamp reaches the vision scanning mechanism 4 along with the transmission belt, the main working unit of the mechanism is a six-joint robot, the tail end of the robot is provided with a line scanning camera, the vamp is scanned according to a preset track, a vamp gluing track is obtained according to a certain algorithm, and gluing track information is sent to the vamp scribing mechanism 5, the primary gluing mechanism 6 and the secondary gluing mechanism 8; after the visual scanning of the vamp is finished, the vamp enters a vamp scribing mechanism 5, in the station, the six-joint robot finishes the scribing operation on the vamp according to the gluing track, and the scribing is to finish the attaching operation of the vamp and the sole conveniently and manually; after the vamp is scribed, the vamp enters a one-time gluing mechanism 6, and the treating agent is sprayed on the peripheral part of the vamp in the process so that the glue can be well adhered to the surface of the vamp; after the first gluing is finished, the shoe enters a first baking mechanism 7, and through baking, the treating agent plays a role to soften the vamp and facilitate the adhesion of glue; after the primary baking is finished, the shoe enters a secondary gluing mechanism 8, a spray gun is installed at the tail end of the robot, and glue is sprayed on the shoe upper; after the secondary gluing is finished, the shoe enters a secondary baking mechanism 9, and in the process, the glue is activated, so that the vamp and the sole are more favorably and closely attached; the vamp which is baked for the second time enters a bottom pressing and jointing mechanism 10, and the vamp and the sole coated with glue are jointed and pressed by using an instrument manually; the shoes after being attached enter a cooling and shaping mechanism 11, glue is solidified in the mechanism, and finished shoes are formed.
The glue applying is a key process for forming cold-bonded shoes, and the main part of a glue applying mechanism is a spraying system. Referring to fig. 2, it is a structural diagram of a spraying system of an automatic shoe making production line, the spraying system uses a six-joint robot as a main working unit, and uses an electric proportional valve or other elements to control the spraying atomization pressure and the feeding pressure, the spraying gun uses a gas-liquid two-phase spraying gun, and the glue is atomized by high-pressure gas and coated on the vamp.
The spraying system obtains high-pressure gas from the pressure pump, and the gas passes through the filter and is divided into 3 branches. The first branch is connected with the glue barrel through an electric proportional valve A, the electric proportional valve A ensures the constancy of the feeding pressure, the pressure conveys the aqueous glue in the glue barrel to the feeding end of the spray gun to finish the spraying operation, and whether the glue at the outlet of the spray nozzle can flow out from the spray nozzle is controlled by the air passage of the control end of the spray gun; the second branch is connected with the atomizing end of the spray gun through an electric proportional valve B, the electric proportional valve B ensures the constant atomizing pressure, atomizing gas is used for atomizing and blowing the glue and spraying the glue on the vamp, and the opening and closing of an atomizing gas path are controlled by a robot control system through an electromagnetic valve B; the third branch is connected to the control end of the spray gun, the air path controls the opening and closing of the glue outlet at the spray nozzle part of the spray gun, and the control air path is controlled by the robot control system through the electromagnetic valve A.
Before spraying, the air source works, and the air pump provides a stable pressure of 0.6MPa for the spraying system. The electric proportional valves of the two branches are opened, and the electric proportional valve A of the feeding loop provides stable pressure of about 0.23MPa for conveying the glue in the glue barrel to the spray gun; and an electric proportional valve B of the atomization gas circuit ensures the constancy of the atomization pressure, and opens an electromagnetic valve B of the atomization gas circuit to continuously provide high-speed high-pressure gas for the spray gun. After the pallet carrying the shoe tree reaches the designated position, the robot obtains the information of the shoe upper by scanning the RFID. At the moment, the robot is in place, the robot moves to a spraying starting point, the electromagnetic valve A of the control gas circuit is opened, the ejector pin at the tail end of the spray gun is opened, the glue flows out from the feeding circuit, and at the moment, atomized gas of the spray gun flows out at a high speed to generate negative pressure so as to bring the glue out. The gas-liquid two-phase speed difference is large, the glue is split into extremely fine fog drops, and the glue is atomized. The atomized glue is jetted to the vamp along with the high-speed gas and is attached to the vamp. When the robot finishes the processing process according to the preset track, the electromagnetic valves of the control gas circuit and the atomization gas circuit are closed, and one glue spraying period is immediately finished.
In the spraying process, the robot moves according to a preset track, a spray gun arranged at the tail end of the robot sprays an approximately conical atomization spray torch, and the moving speed, the spraying distance and the glue viscosity of the robot influence the width and the thickness of a vamp glue coating.
Referring to fig. 3, a flow chart of a method for optimizing sizing process parameters is shown. The sizing technological parameter optimization method comprises the following steps,
and step S1, selecting process parameters influencing the spraying quality and spraying quality parameters for measuring the spraying quality. According to the characteristics of the spraying system of the shoemaking production line, 5 indexes of the moving speed of the robot, the distance (spraying distance) of the vamp at the tail end of the spray gun, the atomizing pressure, the feeding pressure and the glue viscosity are the most critical factors influencing the spraying quality of the vamp. The spraying quality of the shoe can be measured by two indexes of glue spraying width and glue spraying thickness.
And step S2, carrying out experiments under different process parameters, and collecting spraying quality parameters under different process parameters. In a reasonable range of 5 process parameters, discretizing according to a specific step length, randomly combining a plurality of discretized process parameters to obtain a limited set of process parameter sets, and recording the glue spraying width and the glue spraying thickness of the robot spraying system under each process parameter set.
And S3, putting the collected process parameters into a neural network model for training, adjusting various parameters of the neural network, and fitting the optimal neural network model with the nonlinear relation between the process parameters and the spraying quality. The specific method is to divide all the parameter sets acquired in step S2 into a training set, a verification set and a test set according to a proportion. Inputting the training set into a neural network model to train the neural network model; obtaining an optimal model from the trained models through a verification set, namely adjusting various parameters of the neural network model; the performance of the model is measured by the test set.
The neural network is a widely parallel network composed of simple units with adaptability, and is an abstract mathematical model reflecting the structure and function of the human brain. The basic unit of the neural network model is a single neuron, the single neuron comprises a plurality of input signals, and the input signals are weighted and summed and processed by using an activation function to obtain an output. Different organization forms of the neurons form different kinds of networks and can be used for different application scenes. Deep learning technology formed on the basis of a neural network model is widely applied to the fields of pattern recognition, image processing, intelligent control and the like. Theoretically, any nonlinear relation model can be fitted as long as the number of neurons in the neural network is enough and the layers are deep enough. For the engineering field of spraying, due to the complex process and many factors, a set of complete and general theory cannot be formed in a modeling mode, and different models can be established only aiming at different spraying equipment. Based on this, fitting a complex nonlinear relationship between the parameters of the spraying process and the spraying quality by using an artificial neural network model is an effective method.
And establishing a process parameter optimization model, and fitting by adopting a neural network in order to establish a model between spraying process parameters and glue width and glue thickness. Before the process, a plurality of groups of process parameters need to be collected, and a neural network model is used for establishing a nonlinear relation model between 5 process parameters and the glue spraying width and the glue spraying thickness. Wherein, 5 groups of technological parameters are used as input layers of the artificial neural network, the glue applying width and the glue applying thickness are used as output layers, and the error is minimized through parameter adjustment, so that a complex nonlinear relation model among the glue applying technological parameters, the glue applying width and the glue applying thickness is obtained.
Wherein the content of the first and second substances,the width of the applied glue is indicated,the thickness of the applied glue is expressed,5 technological parameters of the moving speed of the robot, the spraying distance, the atomizing pressure, the feeding pressure and the viscosity of the glue are respectively represented.
After the model is built, each set of process parameters always yields a set of sizing width and sizing thickness results, but the actual process requires that an optimal set of process parameter combinations be obtained based on this model and the desired sizing width and sizing thickness.
And step S4, obtaining the expected spraying quality index, namely the expected value of the spraying quality through experiments. The expected value of the spraying quality needs to be determined, wherein the width of the sprayed glue is limited by the width of the side surface of the vamp and the attaching part of the sole, and the thickness of the sprayed glue can be determined only by a tension test. And placing the experimental shoe sprayed with different glue thicknesses on a tensile machine for tensile test, drawing a tensile curve of the glue thickness and the sole and vamp tension, and taking the glue thickness corresponding to the maximum tensile force required by the sole and vamp tension as the expected glue spraying thickness.
Step S5, searching from a given process parameter range based on a particle swarm search algorithm, and searching for a target process parameter, wherein the difference between the spraying quality parameter calculated by the target process parameter through a neural network model and the expected value of the spraying quality parameter is smaller than a threshold value.
And searching a group of optimal values from the given technological parameters by using a particle swarm search algorithm, so that the quality of the vamp sprayed under the group of technological parameters is closest to the expected spraying quality. The process parameters need to calculate a set of process parameter sets with the expected process parameters as targets, which is equivalent to solving an inverse function of a neural network nonlinear relation model, and the inverse process cannot be realized in a mathematical mode. A particle swarm optimization algorithm may be used to search within the global process parameters to achieve the closest approximation of spray quality to the desired spray quality.
Referring to fig. 4, a flow chart of the embodiment for optimizing the process parameters on line, which is a working process of optimizing the process parameters in the actual production process, is shown. And compiling the trained model and the particle swarm algorithm into computer software, and placing the computer software into upper computer software of the spraying system. When the spraying system starts to work, the upper computer obtains glue viscosity information in the current environment, obtains expected glue spraying width and glue spraying thickness parameters according to vamp materials, takes the expected glue spraying width and glue spraying thickness parameters as optimization targets, takes the current glue viscosity as constraint conditions, calculates a group of process parameters, and sets the process parameters as process parameters of the robot or the spraying system element so as to carry out spraying production. In the production process, when the spraying system detects that a certain parameter changes, namely the changed parameter is taken as a constraint condition, a group of optimal parameters are calculated on line again, and the stability requirement of the change of the spraying quality is met by changing other parameters.
In conclusion, the invention establishes a complex nonlinear relation between the spraying process parameters and the spraying quality through a neural network model, and calculates the optimal process parameters on line through a particle swarm algorithm. In a production environment, the change of various process parameters needs to be detected continuously, and once the change occurs, a new set of process parameters needs to be recalculated to make up for the influence of the spraying quality caused by the changed process parameters.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. A sizing technological parameter optimization method is characterized in that: comprises the following steps of (a) carrying out,
s1, spraying under different process parameters, and collecting corresponding spraying quality parameters under different process parameters;
s2, training a neural network model by adopting the information obtained in the step S1, taking the process parameters as an input layer of the neural network model, and taking the spraying quality parameters as an output layer of the neural network model;
and step S3, searching from a given process parameter range based on a particle swarm search algorithm, and searching for a target process parameter, wherein the difference between the spraying quality parameter calculated by the target process parameter through a neural network model and the expected value of the spraying quality parameter is smaller than a threshold value.
2. The method for optimizing sizing process parameters according to claim 1, characterized in that: and selecting the technological parameters influencing the spraying quality, wherein the spraying quality parameters are used for measuring the spraying quality.
3. The method for optimizing sizing process parameters according to claim 1, characterized in that: the process parameters include one or more of robot travel speed, distance of the spray gun tip vamp, atomization pressure, feed pressure, and glue viscosity.
4. The method for optimizing sizing process parameters according to claim 1, characterized in that: the spraying quality parameters comprise spraying width and/or spraying thickness.
5. The method for optimizing sizing process parameters according to claim 1, characterized in that: the step S1 further includes discretizing the process parameters, randomly combining the discretized process parameters to obtain a limited set of process parameter sets, and obtaining the spraying quality parameters corresponding to each process parameter set through experiments.
6. The method for optimizing sizing process parameters according to claim 5, characterized in that: the discretization is equal-step discretization.
7. The method for optimizing sizing process parameters according to claim 1, characterized in that: the neural network model of step S2 is used to fit a complex nonlinear relationship between process parameters and spray quality parameters as follows:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911295564.1A CN110955147A (en) | 2019-12-16 | 2019-12-16 | Sizing process parameter optimization method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911295564.1A CN110955147A (en) | 2019-12-16 | 2019-12-16 | Sizing process parameter optimization method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110955147A true CN110955147A (en) | 2020-04-03 |
Family
ID=69981934
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911295564.1A Pending CN110955147A (en) | 2019-12-16 | 2019-12-16 | Sizing process parameter optimization method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110955147A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113919601A (en) * | 2021-12-09 | 2022-01-11 | 山东捷瑞数字科技股份有限公司 | Resin process prediction method and device based on product performance and process data model |
CN114214869A (en) * | 2021-12-17 | 2022-03-22 | 浙江华章科技有限公司 | Sizing optimization method and system of film transfer sizing machine |
CN115587545A (en) * | 2022-11-23 | 2023-01-10 | 广州粤芯半导体技术有限公司 | Parameter optimization method, device and equipment for photoresist and storage medium |
CN117970818A (en) * | 2024-04-01 | 2024-05-03 | 深圳桥通物联科技有限公司 | Industrial equipment regulation and control method based on Internet of things |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104361393A (en) * | 2014-09-06 | 2015-02-18 | 华北电力大学 | Method for using improved neural network model based on particle swarm optimization for data prediction |
CN109472397A (en) * | 2018-10-19 | 2019-03-15 | 东华大学 | Polymerization technique parameter adjusting method based on viscosity change |
CN110377948A (en) * | 2019-06-12 | 2019-10-25 | 江苏师范大学 | A kind of injection parameters Multipurpose Optimal Method |
-
2019
- 2019-12-16 CN CN201911295564.1A patent/CN110955147A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104361393A (en) * | 2014-09-06 | 2015-02-18 | 华北电力大学 | Method for using improved neural network model based on particle swarm optimization for data prediction |
CN109472397A (en) * | 2018-10-19 | 2019-03-15 | 东华大学 | Polymerization technique parameter adjusting method based on viscosity change |
CN110377948A (en) * | 2019-06-12 | 2019-10-25 | 江苏师范大学 | A kind of injection parameters Multipurpose Optimal Method |
Non-Patent Citations (2)
Title |
---|
倪立斌等: "基于神经网络和粒子群算法的激光熔覆工艺优化", 《中国激光》 * |
沈飞: "制鞋涂胶设备设计及关键工位研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅰ辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113919601A (en) * | 2021-12-09 | 2022-01-11 | 山东捷瑞数字科技股份有限公司 | Resin process prediction method and device based on product performance and process data model |
CN114214869A (en) * | 2021-12-17 | 2022-03-22 | 浙江华章科技有限公司 | Sizing optimization method and system of film transfer sizing machine |
CN114214869B (en) * | 2021-12-17 | 2023-08-15 | 浙江华章科技有限公司 | Sizing optimization method of film transfer sizing machine |
CN115587545A (en) * | 2022-11-23 | 2023-01-10 | 广州粤芯半导体技术有限公司 | Parameter optimization method, device and equipment for photoresist and storage medium |
CN115587545B (en) * | 2022-11-23 | 2023-04-07 | 广州粤芯半导体技术有限公司 | Parameter optimization method, device and equipment for photoresist and storage medium |
CN117970818A (en) * | 2024-04-01 | 2024-05-03 | 深圳桥通物联科技有限公司 | Industrial equipment regulation and control method based on Internet of things |
CN117970818B (en) * | 2024-04-01 | 2024-05-31 | 深圳桥通物联科技有限公司 | Industrial equipment regulation and control method based on Internet of things |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110955147A (en) | Sizing process parameter optimization method | |
Montagne et al. | Movement reversals in ball catching | |
US6528109B1 (en) | Integrated paint quality control system | |
CN109695944B (en) | Control method for coating fresh air conditioner based on multi-model deep learning | |
CN105045098A (en) | Control method of robot spraying track automatic generation system | |
CN109967292A (en) | A kind of automatic spraying system and its method based on the reconstruct of workpiece profile information three-dimensional | |
DE102011011542A1 (en) | Method for automated programming and optimization of robotic workflows | |
CN110198801A (en) | Soldering system, control device, control method and program | |
CN110508463A (en) | A kind of coating method being precisely controlled coated shape thickness | |
US20220266506A1 (en) | Additive manufacturing using polymer materials | |
CN115945324B (en) | Toy model surface spraying system and method | |
KR102218863B1 (en) | Real-time variable rate application system and real-time variable rate application method using drones | |
WO2017031802A1 (en) | Device for integrating product fingerprint assignation, identifier code assignation and visual inspection | |
CN105962408A (en) | Multi-strategy composite control method for moisture of tobacco at outlet of tobacco redryer | |
CN102540997B (en) | Tire vulcanization production control system and operative plan execution method | |
CN203789285U (en) | Automatic gluing system for soles and vamps | |
CN106392251A (en) | K-shaped groove cutting device of flame groove robot | |
CN116128672A (en) | Model-data combined driving intelligent greenhouse fertilizer preparation method and system | |
CN111280151B (en) | Variable pesticide application control method based on cotton growth period recognition | |
CN114789450A (en) | Robot motion trajectory digital twinning method based on machine vision | |
CN114036447A (en) | Sole gluing track offset method and storage equipment | |
CN110181517A (en) | A kind of double remote operating training method based on virtual clamp | |
CN105093923A (en) | Football robot bottom control method based on fuzzy control | |
CN107159521A (en) | A kind of industrial Glue Spreading Robot control system of optimum selecting gluing parameter | |
EP3359371B1 (en) | Additive manufacturing using polymer materials |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200403 |