CN115032946B - Blow molding control method and system of blow molding machine - Google Patents
Blow molding control method and system of blow molding machine Download PDFInfo
- Publication number
- CN115032946B CN115032946B CN202210708653.XA CN202210708653A CN115032946B CN 115032946 B CN115032946 B CN 115032946B CN 202210708653 A CN202210708653 A CN 202210708653A CN 115032946 B CN115032946 B CN 115032946B
- Authority
- CN
- China
- Prior art keywords
- blow molding
- characteristic diagram
- classification
- motor
- preset time
- 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/408—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by data handling or data format, e.g. reading, buffering or conversion of data
- G05B19/4086—Coordinate conversions; Other special calculations
-
- 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
- B29C55/00—Shaping by stretching, e.g. drawing through a die; Apparatus therefor
- B29C55/28—Shaping by stretching, e.g. drawing through a die; Apparatus therefor of blown tubular films, e.g. by inflation
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/35—Nc in input of data, input till input file format
- G05B2219/35356—Data handling
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Blow-Moulding Or Thermoforming Of Plastics Or The Like (AREA)
Abstract
The application relates to the field of intelligent control of a blow molding machine, and particularly discloses a blow molding control method and a blow molding control system of the blow molding machine, wherein dynamic change characteristics of the thickness change of a blown film on a time dimension and high-dimensional implicit associated characteristic information of the working state data of each motor in an automatic air ring system are respectively extracted from a blown film monitoring video in a preset time period and the working state data of each motor through a deep neural network model of an artificial intelligence technology, and in the characteristic fusion process, class condition boundary constraint correction is performed on a classification characteristic diagram after fusion so as to perform rule-based structural understanding on characteristic values and class conditions to which the characteristic values belong, so that the boundary constraint of characteristics is performed on the whole characteristic distribution of the characteristic diagram, and then the convergence capability of a classification result is improved, and the rationality of a control mode of an automatic air ring in the preset time period is accurately judged.
Description
Technical Field
The present invention relates to the field of intelligent control of blow molding machines, and more particularly, to a blow molding control method and system for a blow molding machine.
Background
The blow molding machine blows the liquid plastic to a mold cavity of a certain shape by using the wind force blown out by the machine, thereby forming a product. The plastic is melted in a screw extruder and extruded quantitatively, then is shaped by a mouth film and is cooled by air blowing of an air ring.
In the blown film production process, the film thickness uniformity is a very critical index, in order to improve the film transverse thickness uniformity, an automatic transverse thickness control system needs to be introduced, and a common control method is an automatic air ring.
The automatic wind ring is an on-line real-time control system, and the controlled objects of the system are a plurality of motors distributed on the wind ring. The cooling air flow sent by the fan is distributed to each air channel after being subjected to constant pressure by the air ring air chamber, and the motor drives the valve to perform opening and closing movement so as to adjust the size of the air opening and the air quantity, so that the cooling effect of the film blank at the discharging position of the die head is changed, and the thickness of the film is controlled.
However, in the actual control process, no clear relationship can be found between the thickness change of the film and the motor control quantity, the thickness change of the films with different thicknesses and different positions of the valve and the control quantity are in nonlinear irregular change, the influence on adjacent points is large when each valve is adjusted, and the adjustment has hysteresis, so that different moments are correlated with each other.
Therefore, an optimized blow control scheme for blow molding machines is desired.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides a blow molding control method and a blow molding control system of a blow molding machine, wherein dynamic change characteristics of the thickness change of a blown film on a time dimension and high-dimensional implicit associated characteristic information of working state data of each motor in a blowing monitoring video and an automatic air ring system of the blown film in a preset time period are respectively extracted from the working state data of each motor through a deep neural network model of an artificial intelligence technology, class condition boundary constraint correction is carried out on a fused classification characteristic diagram in the characteristic fusion process, so that the structural understanding based on rules is carried out on characteristic values and class conditions of the characteristic values, the boundary constraint of the characteristics is carried out on the whole characteristic distribution of the characteristic diagram, the convergence capacity of a classification result is further improved, and the rationality of a control mode of an automatic air ring in the preset time period is accurately judged.
According to one aspect of the present application, there is provided a blow molding control method of a blow molding machine, including:
acquiring a blowing monitoring video of the blown film in a preset time period, which is acquired from the cross section direction of the blown film by a camera;
acquiring working state data of each motor in the automatic air ring system at a plurality of preset time points in the preset time period;
arranging the working state data of each motor in the automatic air ring system at the preset time points into a working state input matrix according to the motor sample dimension and the time dimension;
enabling the working state input matrix to pass through a first convolutional neural network to obtain a state characteristic diagram;
enabling the blow molding monitoring video to pass through a second convolution neural network using a three-dimensional convolution kernel to obtain a film thickness change characteristic diagram;
fusing the state characteristic diagram and the film thickness change characteristic diagram to obtain a classification characteristic diagram;
correcting the classification characteristic diagram to obtain a corrected classification characteristic diagram; and
and passing the corrected classification characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the control mode of the automatic wind ring in a preset time period is reasonable or not.
In the blow molding control method of the blow molding machine, arranging the working state data of each motor in the automatic air ring system at the plurality of predetermined time points into a working state input matrix according to the motor sample dimension and the time dimension, the method includes: if the working state of the motor at the preset time point is in an on state, the working state data of the motor at the preset time point is the power value of the motor at the preset time point; and if the working state of the motor at the preset time point is in a closed state, the working state data of the motor at the preset time point is zero.
In the blow molding control method of the blow molding machine, arranging the working state data of each motor in the automatic air ring system at the plurality of predetermined time points into a working state input matrix according to the motor sample dimension and the time dimension, the method includes: respectively arranging the working state data of each motor in the automatic air ring systems at the preset time points into row vectors according to the time dimension to obtain a plurality of row vectors; and arranging the plurality of row vectors into the working state input matrix according to the dimension of the motor sample.
In the blow molding control method of the blow molding machine, the step of passing the working state input matrix through a first convolutional neural network to obtain a state characteristic diagram includes: and each layer of the first convolutional neural network performs convolution processing, pooling processing and activation processing on input data in forward transmission of the layer to generate the state characteristic diagram from the last layer of the first convolutional neural network, wherein the input of the first layer of the first convolutional neural network is the working state input matrix.
In the blow molding control method of the blow molding machine, the passing the blow molding monitoring video through a second convolution neural network using a three-dimensional convolution kernel to obtain a film thickness variation characteristic map includes: the second convolutional neural network using the three-dimensional convolutional kernel performs, in forward transfer of layers, respectively: performing three-dimensional convolution processing on the input data based on the three-dimensional convolution kernel to obtain a convolution characteristic diagram; performing pooling-based processing on the convolution feature map to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activated feature map; wherein the output of the last layer of the second convolutional neural network is the film thickness variation characteristic diagram, and the input of the first layer of the second convolutional neural network is the blow molding monitoring video.
In the blow molding control method of the blow molding machine, fusing the state feature map and the film thickness variation feature map to obtain a classification feature map includes: linearly transforming the state characteristic diagram to enable each characteristic matrix of the state characteristic diagram and the characteristic matrix of the film thickness change characteristic diagram to have the same size so as to obtain a size-corrected state characteristic diagram; and calculating a position-weighted sum of the size-corrected state feature map and the film thickness variation feature map to obtain the classification feature map.
In the blow molding control method for a blow molding machine, the method of correcting the classification feature map to obtain a corrected classification feature map includes: calculating a first difference between a natural exponent function value raised by the feature value of each position in the classification feature map and the reciprocal of the feature value of the position in the classification feature map, and calculating a second difference between the first difference and one; and calculating a logarithmic function value of the second difference value as a feature value of each position in the corrected classification feature map to obtain the corrected classification feature map.
In the blow molding control method for a blow molding machine, the step of obtaining a classification result by passing the corrected classification feature map through a classifier includes: performing full-join encoding on the corrected classification feature map by using a plurality of full-join layers of the classifier to reduce the dimension of the corrected classification feature map into a classification feature vector; and passing the classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
According to another aspect of the present application, there is provided a blow molding control system of a blow molding machine, comprising:
the monitoring video acquisition unit is used for acquiring a blow molding monitoring video of the blown film in a preset time period, which is acquired by a camera from the cross section direction of the blown film;
the working state data acquisition unit is used for acquiring the working state data of each motor in the automatic air ring system at a plurality of preset time points in the preset time period;
the input matrix arrangement unit is used for arranging the working state data of each motor in the automatic air ring system at the plurality of preset time points into a working state input matrix according to the motor sample dimension and the time dimension;
the first convolution unit is used for enabling the working state input matrix to pass through a first convolution neural network so as to obtain a state characteristic diagram;
the second convolution unit is used for enabling the blow molding monitoring video to pass through a second convolution neural network using a three-dimensional convolution kernel so as to obtain a film thickness change characteristic diagram;
the characteristic fusion unit is used for fusing the state characteristic diagram and the film thickness change characteristic diagram to obtain a classification characteristic diagram;
the correction unit is used for correcting the classification characteristic diagram to obtain a corrected classification characteristic diagram; and
and the classification unit is used for enabling the corrected classification characteristic diagram to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the control mode of the automatic air ring in a preset time period is reasonable or not.
In the blow molding control system of the blow molding machine, the input matrix arrangement unit is further configured to: if the working state of the motor at the preset time point is in an on state, the working state data of the motor at the preset time point is the power value of the motor at the preset time point; and if the working state of the motor at the preset time point is in a closed state, the working state data of the motor at the preset time point is zero.
In the blow molding control system of the blow molding machine, the input matrix arrangement unit includes: the time dimension arrangement subunit is used for respectively arranging the working state data of each motor in the automatic wind ring system at the plurality of preset time points into row vectors according to the time dimension to obtain a plurality of row vectors; and the sample dimension arrangement subunit is used for arranging the plurality of row vectors into the working state input matrix according to the motor sample dimension.
In the blow molding control system of the blow molding machine, the first winding unit is further configured to: and each layer of the first convolutional neural network performs convolution processing, pooling processing and activation processing on input data in forward transmission of the layer to generate the state characteristic diagram from the last layer of the first convolutional neural network, wherein the input of the first layer of the first convolutional neural network is the working state input matrix.
In the blow molding control system of the blow molding machine, the second convolution unit is further configured to: the second convolutional neural network using the three-dimensional convolutional kernel performs, in forward transfer of layers, respectively: performing three-dimensional convolution processing on the input data based on the three-dimensional convolution kernel to obtain a convolution characteristic diagram; performing pooling-based processing on the convolution feature map to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activated feature map; wherein the output of the last layer of the second convolutional neural network is the film thickness variation characteristic diagram, and the input of the first layer of the second convolutional neural network is the blow molding monitoring video.
In the blow molding control system of the blow molding machine, the feature fusion unit includes: the scale transformation subunit is used for carrying out linear transformation on the state characteristic diagram so that each characteristic matrix of the state characteristic diagram has the same size as that of the characteristic matrix of the film thickness change characteristic diagram to obtain a size-corrected state characteristic diagram; and the weighted sum calculating subunit is used for calculating the weighted sum of the state characteristic diagram after size correction and the film thickness change characteristic diagram according to positions so as to obtain the classification characteristic diagram.
In the blow molding control system of the blow molding machine, the correction unit includes: a difference calculation subunit, configured to calculate a first difference between a natural exponent function value raised by a power of a feature value at each position in the classification feature map and a reciprocal of the feature value at the position in the classification feature map, and calculate a second difference between the first difference and one; and a logarithmic function value operator unit, configured to calculate a logarithmic function value of the second difference as a feature value of each position in the corrected classification feature map to obtain the corrected classification feature map.
In the blow molding control system of the blow molding machine, the sorting unit is further configured to: performing full-join encoding on the corrected classification feature map by using a plurality of full-join layers of the classifier to reduce the dimension of the corrected classification feature map into a classification feature vector; and passing the classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
Compared with the prior art, the blow molding control method and the system thereof of the blow molding machine respectively extract the dynamic change characteristics of the thickness change of the blow molding film in the time dimension and the high-dimensional implicit associated characteristic information of the working state data of each motor in the blow molding monitoring video of the blow molding film in the preset time period and the automatic air ring system through the deep neural network model of the artificial intelligence technology, and carry out class condition boundary constraint correction on the fused classification characteristic diagram in the characteristic fusion process so as to carry out rule-based structural understanding on the characteristic value and the class condition to which the characteristic value belongs, thereby carrying out characteristic boundary constraint on the whole characteristic distribution of the characteristic diagram, further improving the convergence capability of the classification result and accurately judging the rationality of the control mode of the automatic air ring in the preset time period.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
Fig. 1 is a view of an application scenario of a blow molding control method of a blow molding machine according to an embodiment of the application;
FIG. 2 is a flow chart of a blow control method of a blow molding machine according to an embodiment of the present application;
fig. 3 is a schematic system architecture diagram of a blow molding control method of a blow molding machine according to an embodiment of the present application;
fig. 4 is a flowchart of modifying the classification feature map to obtain a modified classification feature map in a blow molding control method of a blow molding machine according to an embodiment of the present application;
FIG. 5 is a block diagram of a blow molding control system of a blow molding machine according to an embodiment of the present application;
FIG. 6 is a block diagram of a correction unit in a blow molding control system of a blow molding machine according to an embodiment of the present application;
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.
Overview of a scene
As described above, the blow molding machine ejects the liquid plastic, and then blows the molded body to the cavity having a predetermined shape by the wind force blown by the machine, thereby forming a product. The plastic is melted in a screw extruder and extruded quantitatively, then is shaped by a mouth film and is cooled by air blowing of an air ring.
In the blown film production process, the film thickness uniformity is a very critical index, in order to improve the film transverse thickness uniformity, an automatic transverse thickness control system needs to be introduced, and a common control method is an automatic air ring.
The automatic wind ring is an on-line real-time control system, and the controlled objects of the system are a plurality of motors distributed on the wind ring. The cooling air flow sent by the fan is distributed to each air channel after being subjected to constant pressure by the air ring air chamber, and the motor drives the valve to perform opening and closing movement so as to adjust the size of the air opening and the air quantity, so that the cooling effect of the film blank at the discharging position of the die head is changed, and the thickness of the film is controlled.
However, in the actual control process, no clear relationship can be found between the thickness variation of the film and the control quantity of the motor, the thickness variation of the films with different thicknesses and different positions of the valve and the control quantity are in nonlinear irregular variation, the influence on adjacent points is large when each valve is adjusted, and the adjustment has hysteresis, so that different times are correlated with each other. Therefore, an optimized blow control scheme for blow molding machines is desired.
Based on this, the blow molding machine of the invention aims at producing 20L pesticide packaging barrel, namely a large-capacity barrel, the pesticide packaging barrel has a 4-layer multilayer structure, and the blow molding process is as follows: unloading, blank (cold sword seals, hot sword is cut), blow molding, remove overlap, manipulator clamp get the pesticide pail pack, put into the conveyer belt, 4 layers of materials are by outer to interior respectively: PE, DEPE (PE reclaimed materials), TIE and ECOH, and because the fluidity of EVOH is better than that of PE, a spiral groove is arranged in the blowing needle and evenly shunted through a herringbone groove, so that the uniformity of the middle barrier layer is required to be controlled within 2 filaments. In addition, the material feeding device is multi-layer, if central feeding is adopted, supporting points are arranged among the ring rings, the material blanks can be scratched, and the produced barrel is provided with hidden lines.
Accordingly, in the technical solution of the present application, it is considered that the thickness variation characteristic of the blown film can be embodied by the image frames of the monitoring video captured by the camera at each time point, and the control quantity characteristic of the motor can be expressed by the working state data of each motor in the automatic wind ring system at the plurality of time points. Therefore, in the technical scheme of the application, firstly, a blowing monitoring video of the blown film in a preset time period is acquired from the cross section direction of the blown film through a camera, and working state data of each motor in the automatic air ring system at a plurality of preset time points in the preset time period is acquired.
Then, a convolutional neural network model with excellent performance in the aspect of image implicit feature extraction is used for feature extraction of each image frame in the surveillance video, and considering that the features of each image frame in the surveillance video are feature performances of different time points in a preset time period, in the technical scheme of the application, a second convolutional neural network with a three-dimensional convolution kernel is selected to be used for processing the blow-molding surveillance video so as to extract local high-dimensional implicit associated features of the image frames of each time point in the surveillance video, and therefore a film thickness variation feature map is obtained. The obtained film thickness variation characteristic diagram can embody dynamic variation characteristic information of the thickness of the film in a time dimension.
And arranging the working state data of each motor in the automatic wind ring system at the preset time points into a working state input matrix according to the motor sample dimension and the time dimension. Specifically, if the working state of the motor at the predetermined time point is an on state, the working state data of the motor at the predetermined time point is a power value of the motor at the predetermined time point; and if the working state of the motor at the preset time point is in a closed state, the working state data of the motor at the preset time point is zero. In the embodiment of the application, firstly, the working state data of each motor in the automatic wind ring system at the plurality of preset time points are respectively arranged into row vectors according to the time dimension to obtain a plurality of row vectors; and then arranging the plurality of row vectors into the working state input matrix according to the motor sample dimension. Therefore, the obtained working state input matrix can be further processed through the first convolutional neural network to extract high-dimensional implicit association characteristics of the working state data of each motor in the automatic wind loop system at the plurality of preset time points, and a state characteristic diagram is obtained.
Further, a classification characteristic diagram for classification can be obtained by fusing the state characteristic diagram and the film thickness change characteristic diagram, and specifically, the state characteristic diagram is subjected to linear transformation so that each characteristic matrix of the state characteristic diagram and the characteristic matrix of the film thickness change characteristic diagram have the same size to obtain a size-corrected state characteristic diagram; and calculating the position-weighted sum of the state characteristic diagram after size correction and the film thickness variation characteristic diagram to obtain the classification characteristic diagram. And finally, the classification characteristic graph can be used for obtaining a classification result for indicating whether the control mode of the automatic wind ring in a preset time period is reasonable or not through a classifier.
However, it is considered that, when the state feature map and the thickness variation feature map are fused, only scale alignment is performed at each position of the feature map, and dimension alignment is not performed, and the state feature map and the thickness variation feature map are from data sources of different dimensions, and therefore dimension alignment cannot be performed. Therefore, during fusion, an out-of-distribution (out-of-distribution) characteristic of the feature value set of the feature map may be caused, and therefore, class condition boundary constraint correction needs to be performed on the fused classification feature map, specifically:
wherein f is the feature value of each position of the classification feature map, and f' is the feature value of each position of the modified classification feature map.
In this way, by performing class condition boundary constraint correction on the classification feature map, it is possible to perform rule-based structured understanding on the feature values and the class conditions to which the feature values belong, and perform feature boundary constraint on the overall feature distribution of the feature map. Therefore, excessive fragmentation of the decision region of the characteristic map in the classification target domain caused by the characteristic outside the distribution of the characteristic value set can be avoided to a certain extent, the robustness of the conditioned class boundary is obtained, and the convergence capability of the classification result is improved. Furthermore, the rationality judgment of the control mode of the automatic air ring in the preset time period is more accurate.
Based on this, the present application proposes a blow molding control method of a blow molding machine, which includes: acquiring a blowing monitoring video of the blown film in a preset time period, which is acquired from the cross section direction of the blown film by a camera; acquiring working state data of each motor in the automatic air ring system at a plurality of preset time points in the preset time period; arranging the working state data of each motor in the automatic air ring systems at the preset time points into a working state input matrix according to the dimension and the time dimension of a motor sample; enabling the working state input matrix to pass through a first convolutional neural network to obtain a state characteristic diagram; passing the blow molding monitoring video through a second convolution neural network using a three-dimensional convolution kernel to obtain a film thickness variation characteristic diagram; fusing the state characteristic diagram and the film thickness change characteristic diagram to obtain a classification characteristic diagram; correcting the classification characteristic diagram to obtain a corrected classification characteristic diagram; and the corrected classification characteristic diagram is processed by a classifier to obtain a classification result, and the classification result is used for indicating whether the control mode of the automatic wind ring in a preset time period is reasonable or not.
Fig. 1 illustrates an application scenario of a blow molding control method of a blow molding machine according to an embodiment of the present application. As shown in fig. 1, in this application scenario, first, a cross-sectional direction of a blown film (e.g., T as illustrated in fig. 1) is captured by a camera (e.g., a camera C as illustrated in fig. 1) to obtain a blowing monitoring video of the blown film for a predetermined period of time, and working status data of each motor in the automatic wind ring system at a plurality of predetermined time points within the predetermined period of time is obtained. Then, the obtained blowing monitoring video of the blown film in the predetermined time period and the working state data of the motors are input into a server (for example, S as illustrated in fig. 1) deployed with a blowing control algorithm of the blowing machine, wherein the server can process the blowing monitoring video of the blown film in the predetermined time period and the working state data of the motors by the blowing control algorithm of the blowing machine to generate a classification result indicating whether the control mode of the automatic air ring in the predetermined time period is reasonable or not.
Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary method
Fig. 2 illustrates a flow chart of a blow control method of the blow molding machine. As shown in fig. 2, a blow molding control method of a blow molding machine according to an embodiment of the present application includes: s110, acquiring a blown film monitoring video of the blown film in a preset time period, which is acquired from the cross section direction of the blown film by a camera; s120, acquiring working state data of each motor in the automatic air ring system at a plurality of preset time points in the preset time period; s130, arranging the working state data of each motor in the automatic wind ring system at the preset time points into a working state input matrix according to the motor sample dimension and the time dimension; s140, enabling the working state input matrix to pass through a first convolutional neural network to obtain a state characteristic diagram; s150, enabling the blow molding monitoring video to pass through a second convolution neural network using a three-dimensional convolution kernel to obtain a film thickness variation characteristic diagram; s160, fusing the state characteristic diagram and the film thickness change characteristic diagram to obtain a classification characteristic diagram; s170, correcting the classification characteristic diagram to obtain a corrected classification characteristic diagram; and S180, passing the corrected classification characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the control mode of the automatic wind ring in a preset time period is reasonable or not.
Fig. 3 illustrates an architecture diagram of a blow molding control method of a blow molding machine according to an embodiment of the present application. As shown in fig. 3, in the network architecture of the blow molding control method of the blow molding machine, firstly, the obtained operating state data (for example, P1 as illustrated in fig. 3) of each motor in the automatic air ring system at the plurality of predetermined time points are arranged into an operating state input matrix (for example, M as illustrated in fig. 3) according to a motor sample dimension and a time dimension; then, passing the working state input matrix through a first convolutional neural network (e.g., CNN1 as illustrated in fig. 3) to obtain a state feature map (e.g., F1 as illustrated in fig. 3); then, passing the obtained blow molding monitoring video (e.g., P2 as illustrated in fig. 3) through a second convolutional neural network (e.g., CNN2 as illustrated in fig. 3) using a three-dimensional convolutional kernel to obtain a film thickness variation profile (e.g., F2 as illustrated in fig. 3); then, fusing the state feature map and the film thickness variation feature map to obtain a classification feature map (e.g., F as illustrated in fig. 3); then, modifying the classification feature map to obtain a modified classification feature map (e.g., FC as illustrated in fig. 3); and finally, passing the corrected classification feature map through a classifier (such as the classifier illustrated in fig. 3) to obtain a classification result, wherein the classification result is used for indicating whether the control mode of the automatic wind ring in a preset time period is reasonable or not.
In the steps S110 and S120, acquiring a blowing monitoring video of the blown film in a preset time period, wherein the blowing monitoring video is acquired by a camera from the cross section direction of the blown film; and acquiring the working state data of each motor in the automatic air ring system at a plurality of preset time points in the preset time period. As mentioned above, in the actual control process, no clear relationship can be found between the thickness variation of the film and the motor control quantity, the thickness variation of the films with different thicknesses and different positions of the valve and the control quantity are in nonlinear irregular variation, the influence on adjacent points is large when each valve is adjusted, and the adjustment has hysteresis, so that different times are correlated with each other. Therefore, in the technical solution of the present application, in order to accurately control the blowing process of the blow molding machine, it is necessary to accurately judge the rationality of the control mode of the automatic air ring.
That is, in particular, in the technical solution of the present application, it is considered that the thickness variation characteristic of the blown film can be embodied by the image frames of each time point in the surveillance video captured by the camera, and the control quantity characteristic of the motor can be expressed by the operating state data of each motor in the automatic wind ring system at the plurality of time points. Therefore, in the technical scheme of the application, firstly, a blowing monitoring video of the blown film in a preset time period is acquired from the cross section direction of the blown film through a camera, and working state data of each motor in the automatic air ring system at a plurality of preset time points in the preset time period is acquired.
In step S130 and step S140, arranging the operating state data of each motor in the automatic wind ring system at the plurality of predetermined time points into an operating state input matrix according to the motor sample dimension and the time dimension, and passing the operating state input matrix through a first convolutional neural network to obtain a state feature map. That is, in the technical solution of the present application, the operating state data of each motor in the automatic wind ring system at the plurality of predetermined time points is further arranged as an operating state input matrix according to the motor sample dimension and the time dimension. Accordingly, in a specific example, if the operating state of the motor at the predetermined time point is an on state, the operating state data of the motor at the predetermined time point is a power value of the motor at the predetermined time point; and if the working state of the motor at the preset time point is in a closed state, the working state data of the motor at the preset time point is zero. Therefore, the obtained working state input matrix can be further processed in the first convolutional neural network to extract high-dimensional implicit association characteristics of the working state data of each motor in the automatic wind ring system at the plurality of preset time points, and a state characteristic diagram is obtained. In a specific example, each layer of the first convolutional neural network performs convolution processing, pooling processing and activation processing on input data in forward transfer of layers to generate the state feature map from the last layer of the first convolutional neural network, wherein the input of the first layer of the first convolutional neural network is the working state input matrix.
Specifically, in this embodiment of the present application, the process of arranging the operating state data of each motor in the automatic wind ring system at the plurality of predetermined time points into an operating state input matrix according to the motor sample dimension and the time dimension includes: firstly, respectively arranging the working state data of each motor in the automatic wind ring system at a plurality of preset time points into row vectors according to the time dimension to obtain a plurality of row vectors. Then, the plurality of row vectors are arranged into the working state input matrix according to the motor sample dimension.
In step S150, the blow molding monitoring video is passed through a second convolutional neural network using a three-dimensional convolutional kernel to obtain a film thickness variation characteristic map. That is, in the technical solution of the present application, a convolutional neural network model having an excellent performance in terms of image implicit feature extraction is further used to perform feature extraction on each image frame in the surveillance video. It should be understood that, in consideration that each image frame feature in the surveillance video is a feature representation at different time points in a predetermined time period, in the technical solution of the present application, a second convolutional neural network with a three-dimensional convolutional kernel is selected to be used for processing the blow-molding surveillance video to extract a local high-dimensional implicit associated feature of the image frame at each time point in the surveillance video, so as to obtain a film thickness variation feature map. The obtained film thickness variation characteristic diagram can embody dynamic variation characteristic information of the thickness of the film in a time dimension.
Specifically, in this embodiment of the present application, the process of passing the blow-molding monitoring video through a second convolutional neural network using a three-dimensional convolutional kernel to obtain a film thickness variation characteristic map includes: the second convolutional neural network using the three-dimensional convolutional kernel performs, in forward transfer of layers, respectively: performing three-dimensional convolution processing on the input data based on the three-dimensional convolution kernel to obtain a convolution characteristic diagram; performing pooling-based processing on the convolution feature map to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activated feature map; and the output of the last layer of the second convolutional neural network is the film thickness change characteristic diagram, and the input of the first layer of the second convolutional neural network is the blow molding monitoring video.
In step S160, the state feature map and the film thickness variation feature map are fused to obtain a classification feature map. That is, further, a classification feature map for classification can be obtained by fusing the state feature map and the film thickness variation feature map. Specifically, in a specific example, the state feature map may be linearly transformed such that each feature matrix of the state feature map and the feature matrix of the film thickness variation feature map have the same size to obtain a size-corrected state feature map; and further calculating the position-weighted sum of the state characteristic diagram after size correction and the film thickness variation characteristic diagram to obtain the classification characteristic diagram.
In step S170, the classification feature map is modified to obtain a modified classification feature map. It should be understood that, further, the classification feature map is passed through a classifier to obtain a classification result indicating whether the control mode of the automatic wind ring is reasonable within a predetermined time period. However, it is considered that, when the state feature map and the thickness variation feature map are fused, only scale alignment is performed at each position of the feature map, and dimension alignment is not performed, and the state feature map and the thickness variation feature map are from data sources of different dimensions, and therefore dimension alignment cannot be performed. Therefore, during the fusion, an out-of-distribution (out-of-distribution) characteristic of the feature value set of the feature map may be caused, and therefore, in the technical solution of the present application, it is necessary to further perform class-conditional boundary constraint correction on the fused classification feature map.
Specifically, in this embodiment of the present application, the process of modifying the classification feature map to obtain a modified classification feature map includes: first, a first difference between a natural exponent function value raised by a feature value of each position in the classification feature map and a reciprocal of the feature value of the position in the classification feature map is calculated, and a second difference between the first difference and unity is calculated. And then, calculating a logarithmic function value of the second difference value as a characteristic value of each position in the corrected classification characteristic map to obtain the corrected classification characteristic map. That is, in a specific example, the formula for modifying the classification feature map to obtain the modified classification feature map is:
wherein f is the feature value of each position of the classification feature map, and f' is the feature value of each position of the modified classification feature map. It should be understood that, by performing class condition boundary constraint modification on the classification feature map, a rule-based structural understanding can be performed on the feature values and the class conditions to which the feature values belong, so that feature boundary constraint is performed on the overall feature distribution of the feature map. Therefore, excessive fragmentation of the decision region of the characteristic map in the classification target domain caused by the characteristic outside the distribution of the characteristic value set can be avoided to a certain extent, the robustness of the conditioned class boundary is obtained, and the convergence capability of the classification result is improved. Furthermore, the rationality judgment of the control mode of the automatic air ring in the preset time period is more accurate.
Fig. 4 is a flowchart illustrating a method for controlling blow molding of a blow molding machine according to an embodiment of the present application, in which the classification feature map is corrected to obtain a corrected classification feature map. As shown in fig. 4, in the embodiment of the present application, modifying the classification feature map to obtain a modified classification feature map includes: s210, calculating a first difference value between a natural exponent function value taking the feature value of each position in the classification feature map as power and the reciprocal of the feature value of the position in the classification feature map, and calculating a second difference value between the first difference value and one; and S220, calculating the logarithm function value of the second difference value as the characteristic value of each position in the corrected classification characteristic diagram to obtain the corrected classification characteristic diagram.
In step S180, the corrected classification feature map is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether the control mode of the automatic wind ring within a predetermined time period is reasonable. Accordingly, in one specific example, first, the modified classification feature map is full-connected encoded using a plurality of full-connection layers of the classifier to reduce the dimension of the modified classification feature map into a classification feature vector; then, the classification feature vector is passed through a Softmax classification function of the classifier to obtain the classification result.
Specifically, in this embodiment of the present application, the classifier processes the corrected classification feature map by using the following formula to generate a classification result, where the formula is: softmax { (W) n ,B n ):…:(W 1 ,B 1 ) L Project (F), where Project (F) represents the projection of the revised classification profile as a vector, W 1 To W n As a weight matrix for all connected layers of each layer, B 1 To B n A bias matrix representing the layers of the fully connected layer.
In summary, the blow molding control method of the blow molding machine according to the embodiment of the present application is elucidated, the dynamic change feature of the blown film thickness change in the time dimension and the high-dimensional implicit associated feature information of the working state data of each motor in the automatic wind ring system are respectively extracted from the blown film blowing monitoring video in the predetermined time period and the working state data of each motor in the automatic wind ring system through the deep neural network model of the artificial intelligence technology, and in the process of feature fusion, class condition boundary constraint modification is performed on the fused classification feature map, so that rule-based structural understanding is performed on the feature values and the class conditions to which the feature values belong, and thus feature boundary constraint is performed on the overall feature distribution of the feature map, and the convergence capability of the classification result is further improved, so that the rationality of the control mode of the automatic wind ring in the predetermined time period is accurately judged.
Exemplary System
Fig. 5 illustrates a block diagram of a blow molding control system of a blow molding machine according to an embodiment of the present application. As shown in fig. 5, a blow molding control system 500 of a blow molding machine according to an embodiment of the present application includes: a monitoring video obtaining unit 510, configured to obtain a blowing monitoring video of the blown film acquired by a camera from a cross-sectional direction of the blown film in a predetermined time period; a working state data acquiring unit 520, configured to acquire working state data of each motor in the automatic wind ring system at multiple predetermined time points within the predetermined time period; an input matrix arrangement unit 530, configured to arrange the working state data of each motor in the automatic wind ring system at the multiple predetermined time points into a working state input matrix according to a motor sample dimension and a time dimension; a first convolution unit 540, configured to pass the working state input matrix through a first convolution neural network to obtain a state feature map; a second convolution unit 550, configured to pass the blow-molding monitoring video through a second convolution neural network using a three-dimensional convolution kernel to obtain a film thickness variation characteristic map; a feature fusion unit 560, configured to fuse the state feature map and the film thickness variation feature map to obtain a classification feature map; a correcting unit 570, configured to correct the classification feature map to obtain a corrected classification feature map; and a classification unit 580, configured to pass the corrected classification feature map through a classifier to obtain a classification result, where the classification result is used to indicate whether a control mode of the automatic wind ring within a predetermined time period is reasonable.
In an example, in the blow molding control system 500 of the blow molding machine, the input matrix arrangement unit 530 is further configured to: if the working state of the motor at the preset time point is in an on state, the working state data of the motor at the preset time point is the power value of the motor at the preset time point; and if the working state of the motor at the preset time point is in a closed state, the working state data of the motor at the preset time point is zero.
In an example, in the blow molding control system 500 of the blow molding machine, the input matrix arrangement unit 530 includes: the time dimension arrangement subunit is used for respectively arranging the working state data of each motor in the automatic wind ring system at the plurality of preset time points into row vectors according to the time dimension to obtain a plurality of row vectors; and the sample dimension arrangement subunit is used for arranging the plurality of row vectors into the working state input matrix according to the motor sample dimension.
In one example, in the blow molding control system 500 of the blow molding machine, the first volume unit 540 is further configured to: and each layer of the first convolutional neural network performs convolution processing, pooling processing and activation processing on input data in forward transmission of the layer to generate the state characteristic diagram from the last layer of the first convolutional neural network, wherein the input of the first layer of the first convolutional neural network is the working state input matrix.
In one example, in the blow molding control system 500 of the blow molding machine, the second convolution unit 550 is further configured to: the second convolutional neural network using the three-dimensional convolutional kernel performs, in forward transfer of layers, respectively: performing three-dimensional convolution processing on the input data based on the three-dimensional convolution kernel to obtain a convolution characteristic diagram; performing pooling-based processing on the convolution feature map to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activated feature map; wherein the output of the last layer of the second convolutional neural network is the film thickness variation characteristic diagram, and the input of the first layer of the second convolutional neural network is the blow molding monitoring video.
In one example, in the blow molding control system 500 of the blow molding machine, the feature fusion unit 560 includes: the scale transformation subunit is used for carrying out linear transformation on the state characteristic diagram so that each characteristic matrix of the state characteristic diagram has the same size as that of the characteristic matrix of the film thickness change characteristic diagram to obtain a size-corrected state characteristic diagram; and the weighted sum calculating subunit is used for calculating the weighted sum of the state characteristic diagram after size correction and the film thickness change characteristic diagram according to positions so as to obtain the classification characteristic diagram.
In an example, in the blow molding control system 500 of the blow molding machine, as shown in fig. 6, the correction unit 570 includes: a difference operator unit 571, configured to calculate a first difference between a natural exponent function value raised by a feature value at each position in the classification feature map and a reciprocal of the feature value at the position in the classification feature map, and calculate a second difference between the first difference and one; and a logarithmic function value operator unit 572 configured to calculate a logarithmic function value of the second difference as a feature value of each position in the modified classification feature map to obtain the modified classification feature map.
In an example, in the blow molding control system 500 of the blow molding machine, the sorting unit 580 is further configured to: performing full-join encoding on the corrected classification feature map by using a plurality of full-join layers of the classifier to reduce the dimension of the corrected classification feature map into a classification feature vector; and passing the classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
Here, it can be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the blow molding control system 500 of the above-described blow molding machine have been described in detail in the above description of the blow molding control method of the blow molding machine with reference to fig. 1 to 4, and thus, a repetitive description thereof will be omitted.
As described above, the blow molding control system 500 of the blow molding machine according to the embodiment of the present application may be implemented in various terminal devices, such as a server of a blow molding control algorithm of the blow molding machine. In one example, the blow molding control system 500 of the blow molding machine according to embodiments of the present application may be integrated into the terminal device as a software module and/or a hardware module. For example, the blow molding control system 500 of the blow molding machine may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the blow control system 500 of the blow molding machine may also be one of many hardware modules of the terminal equipment.
Alternatively, in another example, the blow molding control system 500 of the blow molding machine and the terminal device may be separate devices, and the blow molding control system 500 of the blow molding machine may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information according to the agreed data format.
The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the foregoing disclosure is not intended to be exhaustive or to limit the disclosure to the precise details disclosed.
The block diagrams of devices, apparatuses, systems referred to in this application are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that in the devices, apparatuses, and methods of the present application, the components or steps may be decomposed and/or recombined. These decompositions and/or recombinations are to be considered as equivalents of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (10)
1. A blow molding control method for a blow molding machine, comprising:
acquiring a blowing monitoring video of the blown film in a preset time period, which is acquired from the cross section direction of the blown film by a camera;
acquiring working state data of each motor in the automatic air ring system at a plurality of preset time points in the preset time period;
arranging the working state data of each motor in the automatic air ring system at the preset time points into a working state input matrix according to the motor sample dimension and the time dimension;
enabling the working state input matrix to pass through a first convolutional neural network to obtain a state characteristic diagram;
passing the blow molding monitoring video through a second convolution neural network using a three-dimensional convolution kernel to obtain a film thickness variation characteristic diagram;
fusing the state characteristic diagram and the film thickness change characteristic diagram to obtain a classification characteristic diagram;
correcting the classification characteristic diagram to obtain a corrected classification characteristic diagram; and
and passing the corrected classification characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the control mode of the automatic wind ring in a preset time period is reasonable or not.
2. The blow molding control method of the blow molding machine according to claim 1, wherein arranging the operation state data of the motors in the automatic air ring system of the plurality of predetermined time points into an operation state input matrix according to a motor sample dimension and a time dimension comprises:
if the working state of the motor at the preset time point is in an on state, the working state data of the motor at the preset time point is the power value of the motor at the preset time point; and
and if the working state of the motor at the preset time point is in a closed state, the working state data of the motor at the preset time point is zero.
3. The blow molding control method of the blow molding machine according to claim 2, wherein arranging the operation state data of the motors in the automatic air ring system of the plurality of predetermined time points into an operation state input matrix according to a motor sample dimension and a time dimension comprises:
respectively arranging the working state data of each motor in the automatic air ring systems at the preset time points into row vectors according to the time dimension to obtain a plurality of row vectors; and
and arranging the plurality of row vectors into the working state input matrix according to the dimension of the motor sample.
4. The blow molding control method of the blow molding machine according to claim 3, wherein passing the operation state input matrix through a first convolutional neural network to obtain a state feature map comprises: and each layer of the first convolutional neural network performs convolution processing, pooling processing and activation processing on input data in forward transmission of the layer to generate the state characteristic diagram from the last layer of the first convolutional neural network, wherein the input of the first layer of the first convolutional neural network is the working state input matrix.
5. The blow molding control method of the blow molding machine according to claim 4, wherein the passing of the blow molding monitoring video through a second convolutional neural network using a three-dimensional convolutional kernel to obtain a film thickness variation characteristic map comprises:
the second convolutional neural network using the three-dimensional convolutional kernel performs, in forward transfer of layers, respectively:
performing three-dimensional convolution processing on the input data based on the three-dimensional convolution kernel to obtain a convolution characteristic diagram;
performing pooling-based processing on the convolution feature map to obtain a pooled feature map; and
performing nonlinear activation on the pooled feature map to obtain an activated feature map;
and the output of the last layer of the second convolutional neural network is the film thickness change characteristic diagram, and the input of the first layer of the second convolutional neural network is the blow molding monitoring video.
6. The blow molding control method of the blow molding machine according to claim 5, wherein fusing the state characteristic map and the film thickness variation characteristic map to obtain a classification characteristic map comprises:
linearly transforming the state characteristic diagram to enable each characteristic matrix of the state characteristic diagram and the characteristic matrix of the film thickness change characteristic diagram to have the same size so as to obtain a size-corrected state characteristic diagram; and
and calculating the position-weighted sum of the state characteristic diagram after size correction and the film thickness variation characteristic diagram to obtain the classification characteristic diagram.
7. The blow molding control method of a blow molding machine according to claim 6, wherein the modifying the classification feature map to obtain a modified classification feature map comprises:
calculating a first difference between a natural exponent function value raised by the feature value of each position in the classification feature map and the reciprocal of the feature value of the position in the classification feature map, and calculating a second difference between the first difference and one; and
and calculating a logarithmic function value of the absolute value of the second difference value as a characteristic value of each position in the corrected classification characteristic diagram to obtain the corrected classification characteristic diagram.
8. The blow molding control method of the blow molding machine according to claim 7, wherein the step of passing the corrected classification feature map through a classifier to obtain a classification result comprises:
performing full-join encoding on the corrected classification feature map by using a plurality of full-join layers of the classifier to reduce the dimension of the corrected classification feature map into a classification feature vector; and
and passing the classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
9. A blow molding control system for a blow molding machine, comprising:
the monitoring video acquisition unit is used for acquiring a blow molding monitoring video of the blown film in a preset time period, which is acquired by a camera from the cross section direction of the blown film;
the working state data acquisition unit is used for acquiring the working state data of each motor in the automatic air ring system at a plurality of preset time points in the preset time period;
the input matrix arrangement unit is used for arranging the working state data of each motor in the automatic air ring system at the plurality of preset time points into a working state input matrix according to the motor sample dimension and the time dimension;
the first convolution unit is used for enabling the working state input matrix to pass through a first convolution neural network so as to obtain a state characteristic diagram;
the second convolution unit is used for enabling the blow molding monitoring video to pass through a second convolution neural network using a three-dimensional convolution kernel so as to obtain a film thickness variation characteristic diagram;
the characteristic fusion unit is used for fusing the state characteristic diagram and the film thickness change characteristic diagram to obtain a classification characteristic diagram;
the correction unit is used for correcting the classification characteristic diagram to obtain a corrected classification characteristic diagram; and
and the classification unit is used for enabling the corrected classification characteristic diagram to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the control mode of the automatic air ring in a preset time period is reasonable or not.
10. The blow molding control system of the blow molding machine of claim 9, wherein the input matrix arrangement unit is further configured to: if the working state of the motor at the preset time point is in an on state, the working state data of the motor at the preset time point is the power value of the motor at the preset time point; and if the working state of the motor at the preset time point is in a closed state, the working state data of the motor at the preset time point is zero.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210708653.XA CN115032946B (en) | 2022-06-21 | 2022-06-21 | Blow molding control method and system of blow molding machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210708653.XA CN115032946B (en) | 2022-06-21 | 2022-06-21 | Blow molding control method and system of blow molding machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115032946A CN115032946A (en) | 2022-09-09 |
| CN115032946B true CN115032946B (en) | 2022-12-06 |
Family
ID=83126710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210708653.XA Active CN115032946B (en) | 2022-06-21 | 2022-06-21 | Blow molding control method and system of blow molding machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115032946B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115393779B (en) * | 2022-10-31 | 2023-03-24 | 济宁九德半导体科技有限公司 | Control system and control method for laser cladding metal ball manufacturing |
| CN115471216B (en) * | 2022-11-03 | 2023-03-24 | 深圳市顺源科技有限公司 | Data management method of intelligent laboratory management platform |
| CN117163355B (en) * | 2023-11-02 | 2024-01-02 | 济群医药科技(启东)有限公司 | Automatic generation method and system for drug package bubble caps |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001162675A (en) * | 1999-12-14 | 2001-06-19 | Taisei Kako Co Ltd | Method for producing multi-layer extruded molding, direct blow molding method, and multi-layer extrusion molding apparatus |
| CN203752484U (en) * | 2014-01-16 | 2014-08-06 | 玉环同发塑机有限公司 | Wall thickness control system |
| CN103978669A (en) * | 2014-05-15 | 2014-08-13 | 西安交通大学 | Automatic thickness control system and method of blown film |
| CN105059506A (en) * | 2015-07-24 | 2015-11-18 | 王琳 | Intelligent underwater robot based on laser imaging detection |
| CN105904703A (en) * | 2016-06-08 | 2016-08-31 | 西安交通大学 | Air ring cooling system controller and control method based on field programmable gate array (FPGA) |
| EP3248752A1 (en) * | 2016-05-27 | 2017-11-29 | Ashley Stone | Manufacturing process control systems and methods |
| CN208452284U (en) * | 2018-06-07 | 2019-02-01 | 汕头市众鑫隆机械制造有限公司 | A kind of double air duct film blowing device cooling air rings of regulating flow quantity |
| CN109311211A (en) * | 2016-07-01 | 2019-02-05 | 布鲁克纳机械有限责任两合公司 | For manufacture and/or handle plastic film control device and affiliated method |
| WO2020004547A1 (en) * | 2018-06-27 | 2020-01-02 | 株式会社Ｓｃｒｅｅｎホールディングス | Correction method, substrate-processing device, and substrate-processing system |
| CN111553415A (en) * | 2020-04-28 | 2020-08-18 | 哈尔滨理工大学 | Memristor-based ESN neural network image classification processing method |
| JP2020163768A (en) * | 2019-03-29 | 2020-10-08 | 住友重機械工業株式会社 | Film molding apparatus |
| CN112036435A (en) * | 2020-07-22 | 2020-12-04 | 温州大学 | Brushless direct current motor sensor fault detection method based on convolutional neural network |
| CN213500828U (en) * | 2020-09-09 | 2021-06-22 | 武汉新中德塑机股份有限公司 | Automatic wind ring of wind warm type |
| CN214820848U (en) * | 2021-06-18 | 2021-11-23 | 河北正茂塑料机械科技有限公司 | Air ring structure of degradable film blowing machine |
| CN114502351A (en) * | 2019-10-10 | 2022-05-13 | 3M创新有限公司 | Method and system for blown film thickness measurement |
| CN114600750A (en) * | 2022-03-02 | 2022-06-10 | 上海继睿机械工程有限公司 | Intelligent water-saving irrigation system and operation method thereof |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104985800A (en) * | 2015-08-10 | 2015-10-21 | 武汉新中德塑机股份有限公司 | Cooling air ring for film blowing equipment |
| CN106738751A (en) * | 2017-03-07 | 2017-05-31 | 中国科学技术大学 | A kind of blown film apparatus and its experimental technique that structure detection in situ is carried out with X-ray scattering combination |
| CN206703343U (en) * | 2017-05-20 | 2017-12-05 | 玉环同发塑机有限公司 | Blow moulding machine cooling blower device |
| CN212736747U (en) * | 2020-06-03 | 2021-03-19 | 天津市富郡农业科技有限公司 | Greenhouse film production device |
-
2022
- 2022-06-21 CN CN202210708653.XA patent/CN115032946B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001162675A (en) * | 1999-12-14 | 2001-06-19 | Taisei Kako Co Ltd | Method for producing multi-layer extruded molding, direct blow molding method, and multi-layer extrusion molding apparatus |
| CN203752484U (en) * | 2014-01-16 | 2014-08-06 | 玉环同发塑机有限公司 | Wall thickness control system |
| CN103978669A (en) * | 2014-05-15 | 2014-08-13 | 西安交通大学 | Automatic thickness control system and method of blown film |
| CN105059506A (en) * | 2015-07-24 | 2015-11-18 | 王琳 | Intelligent underwater robot based on laser imaging detection |
| EP3248752A1 (en) * | 2016-05-27 | 2017-11-29 | Ashley Stone | Manufacturing process control systems and methods |
| CN105904703A (en) * | 2016-06-08 | 2016-08-31 | 西安交通大学 | Air ring cooling system controller and control method based on field programmable gate array (FPGA) |
| CN109311211A (en) * | 2016-07-01 | 2019-02-05 | 布鲁克纳机械有限责任两合公司 | For manufacture and/or handle plastic film control device and affiliated method |
| CN208452284U (en) * | 2018-06-07 | 2019-02-01 | 汕头市众鑫隆机械制造有限公司 | A kind of double air duct film blowing device cooling air rings of regulating flow quantity |
| WO2020004547A1 (en) * | 2018-06-27 | 2020-01-02 | 株式会社Ｓｃｒｅｅｎホールディングス | Correction method, substrate-processing device, and substrate-processing system |
| JP2020163768A (en) * | 2019-03-29 | 2020-10-08 | 住友重機械工業株式会社 | Film molding apparatus |
| CN114502351A (en) * | 2019-10-10 | 2022-05-13 | 3M创新有限公司 | Method and system for blown film thickness measurement |
| CN111553415A (en) * | 2020-04-28 | 2020-08-18 | 哈尔滨理工大学 | Memristor-based ESN neural network image classification processing method |
| CN112036435A (en) * | 2020-07-22 | 2020-12-04 | 温州大学 | Brushless direct current motor sensor fault detection method based on convolutional neural network |
| CN213500828U (en) * | 2020-09-09 | 2021-06-22 | 武汉新中德塑机股份有限公司 | Automatic wind ring of wind warm type |
| CN214820848U (en) * | 2021-06-18 | 2021-11-23 | 河北正茂塑料机械科技有限公司 | Air ring structure of degradable film blowing machine |
| CN114600750A (en) * | 2022-03-02 | 2022-06-10 | 上海继睿机械工程有限公司 | Intelligent water-saving irrigation system and operation method thereof |
Non-Patent Citations (6)
| Title |
|---|
| Investigations of film thickness variations in blown film extrusion when using air guiding systems;Kraus, L;《JOURNAL OF PLASTIC FILM & SHEETING》;20200707;第37卷(第1期);第33-52页 * |
| ONLINE WALL THICKNESS CONTROL FOR BLOW MOLDED PART USING HYBRID OPTIMIZATION METHOD AND FUZZY ITERATIVE LEARNING CONTROL ALGORITHM;Huang, Geng-Qun;《ASME International Mechanical Engineering Congress and Exposition》;20090101;第445-451页 * |
| Parison dimension prediction in extrusion blow molding using neural network approach: A new strategy;Huang, Han-Xiong;《PROCEEDINGS OF THE ASME INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION 2007》;20080101(第8期);第1953-1958页 * |
| 基于遗传算法的改进BP神经网络在中空成型机型坯壁厚控制系统中的应用;程凤芹;《塑料科技》;20200731;第48卷(第7期);第114-117页 * |
| 自动风环技术在薄膜厚度控制上的应用;沈志红;《石油化工技术与经济》;20111231;第27卷(第6期);第32-34页 * |
| 薄膜拉伸加工物理在线研究装备;孟令蒲;《中国优秀博士学位论文全文数据库工程科技Ⅰ辑》;20160915;第51-65页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115032946A (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115032946B (en) | Blow molding control method and system of blow molding machine | |
| US20170057160A1 (en) | Large scale room temperature polymer advanced manufacturing | |
| JP5674787B2 (en) | Method and apparatus for blow molding containers | |
| KR102264066B1 (en) | System of smart controller for Injection molding machine by image analysis with AI and operating method thereof | |
| CN115284580B (en) | Injection blow molding intelligent manufacturing system based on remote monitoring | |
| US5648026A (en) | Multiple utilization of blow-mold air | |
| EP1777056A1 (en) | Blow moulding apparatus and method | |
| CN111542426B (en) | Method and device for processing plastic containers with a speed-controlled blow molding machine | |
| KR101897503B1 (en) | Apparatus for manufacturing of zipper bag | |
| EP0477527B1 (en) | Method and apparatus for controlling molding machine | |
| CN105911909A (en) | Integrated type carbon fiber automatically laying apparatus controlling system and the controlling method | |
| US20080191394A1 (en) | Blow moulding apparatus and method | |
| US4126658A (en) | Method of blow molding | |
| CN115091725A (en) | Intelligent blow molding machine for producing pesticide packaging barrel and control method thereof | |
| CN115635670B (en) | Injection blow molding process for medical sealing bottle | |
| CN114347433A (en) | Repeated blow molding transformation device of blow molding system of blow molding machine and control method thereof | |
| CN116682090A (en) | Vehicle target detection method based on improved YOLOv3 algorithm | |
| US20070252304A1 (en) | Method for making multi-layer preform | |
| CN105619745A (en) | Preparation method of FFS (Form-Fill-Seal) three-layer co-extrusion heavy packaging film | |
| CN114936753A (en) | Production mold management method and management system of intelligent workshop based on MES | |
| WO2002062558A1 (en) | Method and device for design of preform | |
| US20240083097A1 (en) | Apparatus and method for forming plastic preforms into plastic containers with regulation of the pressure rise time | |
| CN111002564A (en) | Blow molding process parameter online regulation and control method | |
| CN116985384A (en) | Blow molding and product machining integrated quality control method | |
| EP1584439A1 (en) | Vulcanized tire size allocating method, tire manufacturing method, and vulcanizing process setting method |
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 |