CN117507289A - Self-adaptive injection molding product production method - Google Patents
Self-adaptive injection molding product production method Download PDFInfo
- Publication number
- CN117507289A CN117507289A CN202311785229.6A CN202311785229A CN117507289A CN 117507289 A CN117507289 A CN 117507289A CN 202311785229 A CN202311785229 A CN 202311785229A CN 117507289 A CN117507289 A CN 117507289A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- injection molding
- reinforcement learning
- parameters
- 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
- 238000001746 injection moulding Methods 0.000 title claims abstract description 47
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 22
- 230000002787 reinforcement Effects 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 31
- 230000008569 process Effects 0.000 claims abstract description 27
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 238000002347 injection Methods 0.000 claims description 10
- 239000007924 injection Substances 0.000 claims description 10
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 239000002994 raw material Substances 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims 3
- 238000013528 artificial neural network Methods 0.000 abstract description 2
- 238000010801 machine learning Methods 0.000 abstract description 2
- 229920003023 plastic Polymers 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000843 powder Substances 0.000 description 2
- 229920000426 Microplastic Polymers 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C45/00—Injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould; Apparatus therefor
- B29C45/17—Component parts, details or accessories; Auxiliary operations
- B29C45/76—Measuring, controlling or regulating
- B29C45/766—Measuring, controlling or regulating the setting or resetting of moulding conditions, e.g. before starting a cycle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C2945/00—Indexing scheme relating to injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould
- B29C2945/76—Measuring, controlling or regulating
- B29C2945/76822—Phase or stage of control
- B29C2945/76913—Parameter setting
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C2945/00—Indexing scheme relating to injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould
- B29C2945/76—Measuring, controlling or regulating
- B29C2945/76929—Controlling method
- B29C2945/76979—Using a neural network
Abstract
The self-adaptive injection molding product production method comprises a data acquisition module, wherein the data acquisition module acquires influence factors from an injection molding machine and the environment in advance; the reinforcement learning module inputs the influence factors and outputs the technological parameters; the process parameters output by the reinforcement learning module are transmitted to a decision module, and the decision module adjusts the process parameters in real time; the decision module sends data to the execution module, and the execution module regulates and controls the technological parameters of the injection molding machine in real time; the monitoring module monitors the technological parameters in real time, and the monitoring module feeds back data to the reinforcement learning module to form closed-loop control. The invention has simple whole flow, combines machine learning to realize intelligent process parameter adjustment, and through the neural network module and the decision module, the system can intelligently output process parameters according to input influence factors and automatically adjust the parameters so as to realize more accurate production control.
Description
Technical Field
The invention relates to the field of injection molding production algorithms, in particular to a self-adaptive injection molding product production method.
Background
An injection molding machine is a machine apparatus for manufacturing plastic articles. The desired plastic article is formed by heating plastic particles or powder to a molten state, then injecting the molten plastic into a mold, and cooling. Injection molding machines are widely used in industrial applications for manufacturing plastic articles of various sizes and shapes, with plastic pellets or powder being fed into a hopper of the injection molding machine by a feed system. These materials are then heated by a heating system and gradually melted into a liquid plastic. Once the plastic melts, the molten plastic is injected into the cavity of the mold.
In the traditional injection molding product production process by using an injection molding machine, the quality of the product produced by the traditional injection molding machine is unstable and is difficult to meet the requirement of high-quality products due to the influence of environmental influence factors and the stationarity of technological parameters, the technological parameters cannot be adjusted according to real-time conditions, and the technological parameters are required to be continuously manually interfered and adjusted, so that the efficiency is low and human errors are easy to occur.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a self-adaptive injection molding product production method, which comprises the following specific technical scheme:
a self-adaptive injection molding product production method is characterized in that:
the system comprises a data acquisition module, a control module and a control module, wherein the data acquisition module acquires influence factors from an injection molding machine and the environment in advance;
the reinforcement learning module inputs the influence factors and outputs the technological parameters;
the process parameters output by the reinforcement learning module are transmitted to a decision module, and the decision module adjusts the process parameters in real time;
the decision module sends data to the execution module, and the execution module regulates and controls the technological parameters of the injection molding machine in real time;
the monitoring module monitors the technological parameters in real time, and the monitoring module feeds back data to the reinforcement learning module to form closed-loop control;
the method comprises the following steps:
s1: the data acquisition module acquires influence factors, wherein the influence factors comprise temperature, pressure, speed, rotating speed, injection speed, ambient temperature, ambient humidity and raw material characteristics of the injection molding machine;
s2: the data preprocessing module cleans and standardizes the collected influence factors;
s3: the preprocessed data is used as input characteristics to be input into a reinforcement learning module, and the reinforcement learning module outputs corresponding technological parameters;
s4: the process parameters output by the reinforcement learning module are transmitted to a decision module, and the decision module dynamically adjusts the process parameters;
s5: the decision module sends data to the execution module, and the execution module regulates and controls various parameters of the injection molding machine to realize dynamic production;
s6: the monitoring module collects parameters of the injection molding machine in real time, and feeds back monitoring data to the reinforcement learning algorithm module to dynamically adjust the parameters.
To better implement the invention, it is possible to further: the reinforcement learning module uses a neural network model.
Further: the monitoring module comprises a data aggregation unit, a data processing unit and a feedback unit, wherein the data aggregation unit receives data from various sensors;
the data processing unit is used for processing the original data from the sensor;
the feedback unit feeds back the monitored data to the reinforcement learning algorithm module for dynamically optimizing the process parameters;
the sensor data comprises an injection molding machine temperature sensor, an injection molding machine pressure sensor, an injection molding machine rotating shaft speed sensor, an injection speed sensor and a vibration sensor.
Further: the reinforcement learning module comprises an input layer, a hidden layer and an output layer, wherein the dimension a of an input characteristic is determined according to the vector dimension of an influence factor, the dimension b of output is determined according to label data, sigmoid is selected as an activation function in each hidden layer and output layer, influence factor historical data with labels is collected to be used as a training set, the training set comprises the input influence factor and corresponding output process labels, a neural network model is trained, and the mean square error between predicted output and actual output is minimized by continuously adjusting internal weights and deviations.
The beneficial effects of the invention are as follows:
the invention has simple whole flow, combines machine learning to realize intelligent process parameter adjustment, and through the neural network module and the decision module, the system can intelligently output process parameters according to input influence factors and automatically adjust the parameters so as to realize more accurate production control.
The parameters of the injection molding machine are regulated and controlled through the execution module, so that the whole production process is automatically controlled, human intervention is reduced, and the production efficiency is improved.
The process parameters are monitored in real time through the monitoring module, and the monitored data are fed back to the reinforcement learning algorithm module to form closed-loop control. The real-time monitoring and feedback mechanism is beneficial to the automatic adjustment of the system and the adaptation of the system to the production change, so that the process parameters are in the optimal state, and the consistency and the quality stability of the product are ensured.
Drawings
Fig. 1 is a flow chart of the operation of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1:
the self-adaptive injection molding product production method comprises a data acquisition module, wherein the data acquisition module acquires influence factors from an injection molding machine and the environment in advance;
the reinforcement learning module inputs the influence factors and outputs the technological parameters;
the process parameters output by the reinforcement learning module are transmitted to a decision module, and the decision module adjusts the process parameters in real time;
the decision module sends data to the execution module, and the execution module regulates and controls the technological parameters of the injection molding machine in real time;
the monitoring module monitors the technological parameters in real time, and the monitoring module feeds back data to the reinforcement learning module to form closed-loop control;
the method comprises the following steps:
s1: the data acquisition module acquires influence factors, wherein the influence factors comprise temperature, pressure, speed, rotating speed, injection speed, ambient temperature, ambient humidity and raw material characteristics of the injection molding machine;
s2: the data preprocessing module cleans and standardizes the collected influence factors;
s3: the preprocessed data is used as input characteristics to be input into a reinforcement learning module, and the reinforcement learning module outputs corresponding technological parameters;
specifically, the reinforcement learning module uses a neural network model. The reinforcement learning module comprises an input layer, a hidden layer and an output layer, wherein the dimension a of an input characteristic is determined according to the vector dimension of an influence factor, the dimension b of output is determined according to label data, sigmoid is selected as an activation function in each hidden layer and output layer, influence factor historical data with labels is collected to be used as a training set, the training set comprises the input influence factor and corresponding output process labels, a neural network model is trained, and the mean square error between predicted output and actual output is minimized by continuously adjusting internal weights and deviations.
S4: the process parameters output by the reinforcement learning module are transmitted to a decision module, and the decision module dynamically adjusts the process parameters based on the real-time state;
s5: the decision module sends data to the execution module, and the execution module regulates and controls various parameters of the injection molding machine to realize dynamic production;
s6: the monitoring module collects parameters of the injection molding machine in real time, and feeds back monitoring data to the reinforcement learning algorithm module to dynamically adjust the parameters.
Specifically, the monitoring module comprises a data aggregation unit, a data processing unit and a feedback unit, wherein the data aggregation unit receives data from various sensors;
the data processing unit is used for processing the original data from the sensor;
the feedback unit feeds back the monitored data to the reinforcement learning algorithm module for dynamically optimizing the process parameters;
the sensor data comprises an injection molding machine temperature sensor, an injection molding machine pressure sensor, an injection molding machine rotating shaft speed sensor, an injection speed sensor and a vibration sensor.
The invention works in such a way that the environmental temperature is different in different seasons, and the melting characteristics or flowability of raw materials are different due to the environmental characteristics and the characteristics of raw materials in different batches. Meanwhile, the screw and the die of the injection molding machine can be gradually worn along with the time in the processing process, so that the product molding can be influenced on the product. Thus, the influencing factors include injection molding machine temperature, pressure, speed, rotational speed, injection speed, ambient temperature. By adopting the reinforcement learning module, the decision module and the monitoring module and combining with the self-adaptive adjustment of injection speed, pressure and temperature, the injection device adapts to the characteristics of materials in different batches and ensures the stable quality of formed parts. The reinforcement learning module adjusts the technological parameters of the injection molding machine in real time according to the real-time data and the environmental change,
it will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (4)
1. A self-adaptive injection molding product production method is characterized in that:
the system comprises a data acquisition module, a control module and a control module, wherein the data acquisition module acquires influence factors from an injection molding machine and the environment in advance;
the reinforcement learning module inputs the influence factors and outputs the technological parameters;
the process parameters output by the reinforcement learning module are transmitted to a decision module, and the decision module adjusts the process parameters in real time;
the decision module sends data to the execution module, and the execution module regulates and controls the technological parameters of the injection molding machine in real time;
the monitoring module monitors the technological parameters in real time, and the monitoring module feeds back data to the reinforcement learning module to form closed-loop control;
the method comprises the following steps:
s1: the data acquisition module acquires influence factors, wherein the influence factors comprise temperature, pressure, speed, rotating speed, injection speed, ambient temperature, ambient humidity and raw material characteristics of the injection molding machine;
s2: the data preprocessing module cleans and standardizes the collected influence factors;
s3: the preprocessed data is used as input characteristics to be input into a reinforcement learning module, and the reinforcement learning module outputs corresponding technological parameters;
s4: the process parameters output by the reinforcement learning module are transmitted to a decision module, and the decision module dynamically adjusts the process parameters;
s5: the decision module sends data to the execution module, and the execution module regulates and controls various parameters of the injection molding machine to realize dynamic production;
s6: the monitoring module collects parameters of the injection molding machine in real time, and feeds back monitoring data to the reinforcement learning algorithm module to dynamically adjust the parameters.
2. The method for producing an adaptive injection molding product according to claim 1, wherein:
the reinforcement learning module uses a neural network model.
3. The method for producing an adaptive injection molding product according to claim 2, wherein:
the monitoring module comprises a data aggregation unit, a data processing unit and a feedback unit, wherein the data aggregation unit receives data from various sensors;
the data processing unit is used for processing the original data from the sensor;
the feedback unit feeds back the monitored data to the reinforcement learning algorithm module for dynamically optimizing the process parameters;
the sensor data comprises an injection molding machine temperature sensor, an injection molding machine pressure sensor, an injection molding machine rotating shaft speed sensor, an injection speed sensor and a vibration sensor.
4. A method of producing an adaptive injection molded product according to claim 3, wherein:
the reinforcement learning module comprises an input layer, a hidden layer and an output layer, wherein the dimension a of an input characteristic is determined according to the vector dimension of an influence factor, the dimension b of output is determined according to label data, sigmoid is selected as an activation function in each hidden layer and output layer, influence factor historical data with labels is collected to be used as a training set, the training set comprises the input influence factor and corresponding output process labels, a neural network model is trained, and the mean square error between predicted output and actual output is minimized by continuously adjusting internal weights and deviations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311785229.6A CN117507289A (en) | 2023-12-22 | 2023-12-22 | Self-adaptive injection molding product production method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311785229.6A CN117507289A (en) | 2023-12-22 | 2023-12-22 | Self-adaptive injection molding product production method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117507289A true CN117507289A (en) | 2024-02-06 |
Family
ID=89753348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311785229.6A Pending CN117507289A (en) | 2023-12-22 | 2023-12-22 | Self-adaptive injection molding product production method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117507289A (en) |
-
2023
- 2023-12-22 CN CN202311785229.6A patent/CN117507289A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111065506B (en) | System and method for standardized PID control across injection molding machines | |
| US20220305729A1 (en) | Methods and apparatus for processing and dispensing material during additive manufacturing | |
| WO2008003618A3 (en) | Apparatus and method for user-specific production monitoring and regulation | |
| US20090057938A1 (en) | Closed Loop Control for an Injection Unit | |
| CN104669623A (en) | Wire feeding speed control system and method of FDM rapid molding machine | |
| WO2008019469A1 (en) | Control schema of molding-system process, amongst other things | |
| US4944903A (en) | Method for regulating the working and the output of plastic material in extrusion moulding | |
| CN117507289A (en) | Self-adaptive injection molding product production method | |
| CN104527009A (en) | Injection moulding process parameter optimization regulation and control method based on Gaussian prediction | |
| JP2021070302A (en) | Resin pellet manufacturing device and method | |
| CN203391288U (en) | Conical twin-screw extruder | |
| CN107618166A (en) | A kind of injection molding intelligent adjusting method based on temperature gap analysis | |
| CN117698079B (en) | Injection molding process control system for PET plastic packaging box | |
| CN113059775B (en) | Control method for changing injection pressure to pressure maintaining | |
| CA3143986C (en) | Methods and apparatus for processing and dispensing material during additive manufacturing | |
| Cirak et al. | Barrel temperature control for quality of thermoplastic polymers in the extrusion process | |
| CN107399065A (en) | A kind of injection molding intelligent regulating system based on temperature detection | |
| WO2022144142A1 (en) | Adjustable height cooling die for high moisture extrusion food processing including an automatic dynamic feedback loop | |
| JPH02120023A (en) | Speed control method of gear pump in extrusion molding device | |
| CN107379460A (en) | A kind of injection Intelligentized control method based on temperature analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |