Automatic mold changing control system for injection molding machine

Abstract

The present application relates to an automatic mold change control system for an injection molding machine. It includes: collecting mold positioning images by a camera, and collecting a set of mold positioning reference images marked as accurately positioned from a database, and using image recognition and analysis technology based on computer vision to extract positioning state features and mask salient features of the mold positioning images and the mold positioning reference images, so as to automatically confirm the accurate alignment of the new mold based on the comparison of multiple positioning state semantic difference coefficients between the positioning state salient features of each mold positioning reference image and the mold positioning state detection features with a preset threshold. In this way, through computer vision technology, the system can automatically identify and calibrate the mold position, reduce positioning inaccuracies caused by minor differences or wear, and improve overall accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of injection molding machines, and in particular to an automatic mold changing control system for an injection molding machine. Background Art

[0002] Injection molding machine mold change refers to the operation of removing one mold from the injection molding machine and replacing it with another mold during the injection molding production process. With the growing market demand for product personalization and diversification, this requires manufacturers to be able to respond quickly to market changes and produce customized products that meet consumer needs. Therefore, the efficiency and accuracy of injection molding machine mold change become particularly critical.

[0003] However, although the traditional automatic mold changing system of injection molding machines has achieved a certain degree of automation, there are still some limitations in actual operation. Specifically, the need for manual intervention still exists, especially in the final positioning and fixing stage of the mold. Inaccurate positioning may occur due to slight differences or wear of the mold, and manual assistance is required to ensure accuracy. In addition, such systems are usually highly dependent on preset programs and mold information, and have poor adaptability to non-standardized or special molds, which may lead to reduced mold change efficiency or failure.

[0004] Therefore, an optimized automatic mold change control system for an injection molding machine is desired. Summary of the invention

[0005] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0006] In the first aspect, the present application provides an automatic mold changing control system for an injection molding machine, the system comprising: a mold number changing module, used to select the mold number to be replaced through the HMI; a current mold status checking module, used to automatically check the status of the current mold to ensure that the current mold is in a safe and detachable state; a current mold disassembly module, used to send a disassembly instruction to a hydraulic mold changing device through a control unit to disassemble the current mold through the hydraulic mold changing device, and, during the disassembly process, monitor the movement of the current mold in real time through a position sensor; a new mold selection module, used to select a new mold from a mold library; a new mold moving module, used to move the new mold to the injection molding machine through the hydraulic mold changing device, and confirm whether the new mold is accurately aligned through a positioning system; a new mold fixing module, used to fix the new mold on the injection molding machine through a clamping device.

[0007] Optionally, the new mold moving module includes: a mold positioning image acquisition unit, which is used to obtain a mold positioning image acquired by a camera; an accurately positioned mold positioning reference image acquisition unit, which is used to acquire a set of mold positioning reference images marked as accurately positioned from a database; a mold positioning state reference feature extraction unit, which is used to input each mold positioning reference image marked as accurately positioned in the set of mold positioning reference images marked as accurately positioned into a positioning state image feature extractor to obtain a set of mold positioning state reference feature maps; a mold positioning state reference feature significant unit, which is used to input each mold positioning state reference feature map in the set of mold positioning state reference feature maps into a mask significant map based on feature gradient correlation distribution. a mold positioning state feature extraction and saliency unit, used to input the mold positioning image into the positioning state image feature extractor and the mask saliency based on feature gradient association distribution to obtain a mold positioning state detection feature map; a positioning state semantic difference coefficient calculation unit, used to calculate the positioning state semantic difference coefficient between each significant mold positioning state reference feature map in the set of significant mold positioning state reference feature maps and the mold positioning state detection feature map to obtain a set of positioning state semantic difference coefficients; a mold accurate alignment judgment unit, used to confirm that the new mold is accurately aligned in response to the minimum value in the set of positioning state semantic difference coefficients being greater than or equal to a preset threshold.

[0008] Optionally, the mold positioning state reference feature extraction unit is used to: input each mold positioning reference image marked as accurately positioned in the set of mold positioning reference images marked as accurately positioned into a positioning state image feature extractor based on a hole convolutional neural network model to obtain a set of mold positioning state reference feature maps.

[0009] Optionally, the mold positioning state reference feature saliency unit includes: a mold positioning state reference feature gradient amplitude value calculation subunit, which is used to calculate the multi-directional gradient value distribution of each position in the mold positioning state reference feature map, and determine the gradient amplitude value of each position in the mold positioning state reference feature map based on the multi-directional gradient value distribution of each position to obtain the mold positioning state reference feature gradient amplitude distribution feature map; a mold positioning state reference feature gradient amplitude local description operator calculation subunit, which is used to calculate the gradient amplitude local description operator of each position in the mold positioning state reference feature gradient amplitude distribution feature map to obtain the mold positioning state reference feature gradient amplitude local significant distribution feature map; a gated mask subunit, which is used to input the mold positioning state reference feature gradient amplitude local significant distribution feature map into a gated masker based on the GELU function to obtain the mold positioning state reference feature gradient amplitude local significant gated mask feature map; a position point multiplication calculation subunit, which is used to calculate the position point multiplication between the mold positioning state reference feature gradient amplitude local significant gated mask feature map and the mold positioning state reference feature map to obtain the significant mold positioning state reference feature map.

[0010] Optionally, the mold positioning state reference characteristic gradient amplitude value calculation subunit is used to: calculate the gradient value along the width direction of each characteristic value in the mold positioning state reference characteristic map to obtain the mold positioning state reference width direction characteristic gradient value characteristic map; calculate the gradient value along the height direction of each characteristic value in the mold positioning state reference characteristic map to obtain the mold positioning state reference height direction characteristic gradient value characteristic map; calculate the gradient value along the channel direction of each characteristic value in the mold positioning state reference characteristic map to obtain the mold positioning state reference channel direction characteristic gradient value characteristic map; calculate the square root of the sum of the squares of the characteristic values ​​at corresponding positions in the mold positioning state reference width direction characteristic gradient value characteristic map, the mold positioning state reference height direction characteristic gradient value characteristic map and the mold positioning state reference channel direction characteristic gradient value characteristic map to obtain the mold positioning state reference characteristic gradient amplitude distribution characteristic map.

[0011] Optionally, the mold positioning state reference feature gradient amplitude local description operator calculation subunit is used to: determine the gradient amplitude local neighborhood range, and calculate the sequence of the mold positioning state reference feature gradient amplitude neighborhood distribution feature map based on the gradient amplitude local neighborhood range and the mold positioning state reference feature gradient amplitude distribution feature map; count the number of feature maps in the sequence of the mold positioning state reference feature gradient amplitude neighborhood distribution feature map to obtain the mold positioning state reference feature gradient amplitude neighborhood number statistics; calculate the mold positioning state reference feature gradient amplitude distribution feature map and the mold positioning state reference feature gradient amplitude neighborhood distribution feature map The position differences between each mold positioning state reference feature gradient amplitude neighborhood distribution feature map in the sequence are divided by the mold positioning state reference feature gradient amplitude distribution feature map by position point to obtain a sequence of mold positioning state reference feature gradient relative amplitude distribution neighborhood feature maps; each mold positioning state reference feature gradient relative amplitude distribution neighborhood feature map in the sequence of mold positioning state reference feature gradient relative amplitude distribution neighborhood feature maps is added by position point and divided by the mold positioning state reference feature gradient amplitude neighborhood number statistics value by position point to obtain the mold positioning state reference feature gradient amplitude local significant distribution feature map.

[0012] Optionally, the mold positioning state feature extraction and saliency unit is used to: input the mold positioning image into the positioning state image feature extractor based on the void convolutional neural network model and the mask saliency device based on the feature gradient correlation distribution to obtain the mold positioning state detection feature map.

[0013] Optionally, the positioning state semantic difference coefficient calculation unit includes: a feature pooling processing subunit, which is used to perform feature pooling processing on each significant mold positioning state reference feature map in the set of significant mold positioning state reference feature maps and the mold positioning state detection feature map to obtain a set of significant mold positioning state reference feature vectors and a mold positioning state detection feature vector; a vector position difference calculation subunit, which is used to calculate the position difference between each significant mold positioning state reference feature vector in the set of significant mold positioning state reference feature vectors and the mold positioning state detection feature vector to obtain a set of mold positioning state difference feature vectors; a covariance matrix calculation subunit, which is used to calculate the significant mold positioning state reference feature vector The covariance matrix between each significant mold positioning state reference feature vector in the set and the mold positioning state detection feature vector is calculated, and the inverse of the covariance matrix is ​​calculated to obtain a set of mold positioning state inverse covariance matrices; a mold positioning state offset value calculation subunit is used to obtain a set of mold positioning state offset values ​​based on the offset value between each group of corresponding mold positioning state differential feature vectors and the mold positioning state inverse covariance matrix in the set of mold positioning state differential feature vectors and the set of mold positioning state inverse covariance matrices; a mold positioning state offset value square root calculation subunit is used to calculate the square root of each mold positioning state offset value in the set of mold positioning state offset values ​​to obtain a set of positioning state semantic difference coefficients.

[0014] Optionally, the mold positioning state offset value calculation subunit is used to: calculate the transposed vector of the mold positioning state differential feature vector and the product of the mold positioning state inverse covariance matrix and the mold positioning state differential feature vector to obtain the mold positioning state offset value.

[0015] The above technical solution is adopted, by collecting mold positioning images by a camera, and collecting a set of mold positioning reference images marked as accurately positioned from a database, and using computer vision-based image recognition and analysis technology to extract positioning state features and mask salient features of the mold positioning images and the mold positioning reference images, so as to automatically confirm the accurate alignment of the new mold based on the comparison of multiple positioning state semantic difference coefficients between the positioning state salient features of each mold positioning reference image and the mold positioning state detection features with a preset threshold. In this way, through computer vision technology, the system can automatically identify and calibrate the mold position, reduce positioning inaccuracies caused by minor differences or wear, and improve overall accuracy.

[0016] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0018] In the attached picture: Figure 1 It is a block diagram of an automatic mold change control system for an injection molding machine according to an exemplary embodiment.

[0019] Figure 2 The present invention is a flow chart of an automatic mold change control method for an injection molding machine according to an exemplary embodiment.

[0020] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0021] Figure 4 It is an application scenario diagram of an automatic mold change control system for an injection molding machine according to an exemplary embodiment. DETAILED DESCRIPTION

[0022] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0023] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0024] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0025] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0026] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0027] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0028] At present, the molds of plastic machines are mostly large and heavy, and the upper and lower molds are cumbersome and inconvenient. Manual mold change is relatively dangerous, so many automatic mold change systems have appeared on the market. However, the market needs a more intelligent and more reliable automatic mold change system with network interface control. Therefore, this application provides an automatic mold change system with network control; according to product requirements, high-end chips are used as a development platform to ensure product quality and reliability.

[0029] Among them, this application studies the communication reliability and transmission speed of network communication in the mold changing system; and the efficiency, safety, accuracy, etc. of the mold changing system under the condition of automatic mold changing for upper and lower molds.

[0030] In this way, it can be achieved: 1. Use two communication control interfaces, one uses modbus communication, and the other uses network communication; make the product more universal and give customers more choices.

[0031] 2. The input and output ports are driven by isolated optocouplers to ensure that the input and output will not interfere with the mold changing system, making the product safer and more reliable.

[0032] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0033] Figure 1 FIG. 1 is a block diagram of an automatic mold change control system for an injection molding machine according to an exemplary embodiment. Figure 1 As shown, the system 100 includes: a mold number replacement module 101, which is used to select the mold number that needs to be replaced through the HMI.

[0034] The current mold state checking module 102 is used to automatically check the state of the current mold to ensure that the current mold is in a safe and detachable state.

[0035] The current mold disassembly module 103 is used to send a disassembly instruction to the hydraulic mold changing device through the control unit so as to disassemble the current mold through the hydraulic mold changing device, and, during the disassembly process, monitor the movement of the current mold in real time through the position sensor.

[0036] The new mold selection module 104 is used to select a new mold from the mold library.

[0037] The new mold moving module 105 is used to move the new mold to the injection molding machine through the hydraulic mold changing device, and confirm whether the new mold is accurately aligned through the positioning system.

[0038] The new mold fixing module 106 is used to fix the new mold on the injection molding machine through a mold locking device.

[0039] Correspondingly, in the above-mentioned new mold moving module, the technical concept of the present application is to collect mold positioning images by a camera, and collect a set of mold positioning reference images marked as accurately positioned from a database, and use image recognition and analysis technology based on computer vision to extract positioning state features and mask salient features of the mold positioning images and the mold positioning reference images, so as to automatically confirm the accurate alignment of the new mold based on the comparison of multiple positioning state semantic difference coefficients between the positioning state salient features of each mold positioning reference image and the mold positioning state detection features with a preset threshold. In this way, through computer vision technology, the system can automatically identify and calibrate the mold position, reduce positioning inaccuracies caused by minor differences or wear, and improve overall accuracy. At the same time, the system no longer relies too much on preset programs and mold information, but enhances the adaptability to non-standardized or special molds through image recognition and analysis technology, and thus provides a more intelligent automatic mold change positioning method for injection molding machines.

[0040] In one embodiment of the present application, the new mold moving module includes: a mold positioning image acquisition unit, which is used to obtain a mold positioning image acquired by a camera; an accurately positioned mold positioning reference image acquisition unit, which is used to acquire a set of mold positioning reference images marked as accurately positioned from a database; a mold positioning state reference feature extraction unit, which is used to input each mold positioning reference image marked as accurately positioned in the set of mold positioning reference images marked as accurately positioned into a positioning state image feature extractor to obtain a set of mold positioning state reference feature maps; a mold positioning state reference feature significant unit, which is used to input each mold positioning state reference feature map in the set of mold positioning state reference feature maps into a feature gradient correlation distribution-based mold positioning state reference feature map extractor; and a mold positioning state reference feature significant unit, which is used to input each mold positioning state reference feature map in the set of mold positioning state reference feature maps into a feature gradient correlation distribution-based mold positioning state reference feature map extractor. A mask salient device is used to obtain a set of significant mold positioning state reference feature maps; a mold positioning state feature extraction salient unit is used to input the mold positioning image into the positioning state image feature extractor and the mask salient device based on feature gradient correlation distribution to obtain a mold positioning state detection feature map; a positioning state semantic difference coefficient calculation unit is used to calculate the positioning state semantic difference coefficient between each significant mold positioning state reference feature map in the set of significant mold positioning state reference feature maps and the mold positioning state detection feature map to obtain a set of positioning state semantic difference coefficients; a mold accurate alignment judgment unit is used to confirm that the new mold is accurately aligned in response to the minimum value in the set of positioning state semantic difference coefficients being greater than or equal to a preset threshold.

[0041] Specifically, in the technical solution of the present application, first, a mold positioning image captured by a camera is obtained, and a set of mold positioning reference images marked as accurately positioned is collected from a database. Next, considering that each mold positioning reference image marked as accurately positioned in the set of mold positioning reference images marked as accurately positioned contains feature information about the positioning state, and the hole convolutional neural network model can increase the receptive field range of the network while maintaining the receptive field size, thereby extracting richer and more semantically informative positioning state features. Based on this, in the technical solution of the present application, each mold positioning reference image marked as accurately positioned in the set of mold positioning reference images marked as accurately positioned is input into a positioning state image feature extractor based on a hole convolutional neural network model to capture and extract the key feature information of the mold positioning state reference, thereby obtaining a set of mold positioning state reference feature maps. In particular, the essence of the positioning state image feature extractor based on the hole convolutional neural network model here is a hole convolutional neural network model.

[0042] In one embodiment of the present application, the mold positioning state reference feature extraction unit is used to: input each mold positioning reference image marked as accurately positioned in the set of mold positioning reference images marked as accurately positioned into a positioning state image feature extractor based on a hole convolutional neural network model to obtain a set of mold positioning state reference feature maps.

[0043] Further, considering that each mold positioning state reference feature map in the set of the mold positioning state reference feature map has different saliency and key areas in different local areas, and these key areas are crucial to the accuracy of mold positioning. Therefore, in the technical solution of the present application, each mold positioning state reference feature map in the set of the mold positioning state reference feature map is input into a mask salient device based on feature gradient association distribution to obtain a set of significant mold positioning state reference feature maps. That is, the mask salient device based on feature gradient association distribution is a feature salient enhancement technology based on feature gradient amplitude value measurement mask saliency. Specifically, first, the mold positioning state reference feature map is calculated by calculating the gradient value of each position along the width, height and channel direction, and the gradient amplitude value of each position is calculated based on the gradient value of each direction to highlight the edge features of the positioning state in the image to obtain a mold positioning state reference feature gradient amplitude distribution feature map. In particular, these edge features often contain key positioning state information. Next, by calculating the local description operator of each position in the mold positioning state reference feature gradient amplitude distribution feature map, local texture features such as edges, corners, spots, etc. are extracted to enhance the significant change area in the feature map to obtain the mold positioning state reference feature gradient amplitude local significant distribution feature map. Then, the mold positioning state reference feature gradient amplitude local significant distribution feature map is nonlinearly mapped and masked by a gated masker based on the GELU function to obtain the mold positioning state reference feature gradient amplitude local significant gated mask feature map. That is, the GELU function can perform nonlinear transformation on the feature map, highlight the key feature area of ​​the positioning state in the image, suppress the non-key area, and thus better highlight the key information of the positioning state. The masking process can adaptively and dynamically adjust the weight information of each feature area to depict the significant positioning state feature information. Finally, the mold positioning state reference feature gradient amplitude local significant gated mask feature map and the mold positioning state reference feature map are point-by-point multiplied to obtain a significant mold positioning state reference feature map that combines the original mold positioning state reference feature and the gradient distribution significance feature.

[0044] In one embodiment of the present application, the mold positioning state reference feature saliency unit includes: a mold positioning state reference feature gradient amplitude value calculation subunit, which is used to calculate the multi-directional gradient value distribution of each position in the mold positioning state reference feature map, and determine the gradient amplitude value of each position in the mold positioning state reference feature map based on the multi-directional gradient value distribution of each position to obtain the mold positioning state reference feature gradient amplitude distribution feature map; a mold positioning state reference feature gradient amplitude local description operator calculation subunit, which is used to calculate the gradient amplitude local description operator of each position in the mold positioning state reference feature gradient amplitude distribution feature map to obtain the mold positioning state reference feature gradient amplitude local significant distribution feature map; a gated mask subunit, which is used to input the mold positioning state reference feature gradient amplitude local significant distribution feature map into a gated masker based on a GELU function to obtain a mold positioning state reference feature gradient amplitude local significant gated mask feature map; a position point multiplication calculation subunit, which is used to calculate the position point multiplication between the mold positioning state reference feature gradient amplitude local significant gated mask feature map and the mold positioning state reference feature map to obtain the significant mold positioning state reference feature map.

[0045] Further, in one embodiment of the present application, the mold positioning state reference characteristic gradient amplitude value calculation subunit is used to: calculate the gradient value of each characteristic value in the mold positioning state reference characteristic map along the width direction to obtain the mold positioning state reference width direction characteristic gradient value characteristic map; calculate the gradient value of each characteristic value in the mold positioning state reference characteristic map along the height direction to obtain the mold positioning state reference height direction characteristic gradient value characteristic map; calculate the gradient value of each characteristic value in the mold positioning state reference characteristic map along the channel direction to obtain the mold positioning state reference channel direction characteristic gradient value characteristic map; calculate the square root of the sum of the squares of the characteristic values ​​at corresponding positions in the mold positioning state reference height direction characteristic gradient value characteristic map, the mold positioning state reference height direction characteristic gradient value characteristic map and the mold positioning state reference channel direction characteristic gradient value characteristic map to obtain the mold positioning state reference characteristic gradient amplitude distribution characteristic map.

[0046] Furthermore, in one embodiment of the present application, the mold positioning state reference feature gradient amplitude local description operator calculation subunit is used to: determine the gradient amplitude local neighborhood range, and calculate the sequence of the mold positioning state reference feature gradient amplitude neighborhood distribution feature map based on the gradient amplitude local neighborhood range and the mold positioning state reference feature gradient amplitude distribution feature map; count the number of feature maps in the sequence of the mold positioning state reference feature gradient amplitude neighborhood distribution feature map to obtain the mold positioning state reference feature gradient amplitude neighborhood number statistics; calculate the mold positioning state reference feature gradient amplitude distribution feature map and the mold positioning state reference feature gradient amplitude The position differences between each mold positioning state reference feature gradient amplitude neighborhood distribution feature map in the sequence of neighborhood distribution feature maps are divided by the mold positioning state reference feature gradient amplitude distribution feature map by position point to obtain a sequence of mold positioning state reference feature gradient relative amplitude distribution neighborhood feature maps; each mold positioning state reference feature gradient relative amplitude distribution neighborhood feature map in the sequence of mold positioning state reference feature gradient relative amplitude distribution neighborhood feature map is added by position point and divided by the mold positioning state reference feature gradient amplitude neighborhood number statistics by position point to obtain the mold positioning state reference feature gradient amplitude local significant distribution feature map.

[0047] Specifically, the mold positioning state reference feature map is input into a mask salient device based on feature gradient correlation distribution, and processed with the following gradient mask salient formula to obtain the salient mold positioning state reference feature map; wherein the gradient mask salient formula is: ;in, , , , , and They are respectively the first , , , , and The eigenvalues ​​at the positions, The first position in the width direction of the mold positioning state reference feature map is The gradient amplitude value at each position, The first position in the height direction of the mold positioning state reference feature map is The gradient amplitude value at each position, The mold positioning state reference characteristic diagram is the first The gradient amplitude value at each position, The mold positioning state reference characteristic gradient amplitude distribution characteristic map is The eigenvalues ​​at the positions, The mold positioning state reference characteristic gradient amplitude distribution characteristic map is The eigenvalues ​​at the positions, The range is Neighborhood of express The number of elements in , The local significant distribution feature map of the reference characteristic gradient amplitude of the mold positioning state is represented by The eigenvalues ​​at the positions, represents the Gaussian error linear gating function, The reference feature gradient amplitude of the mold positioning state is represented by the local significant gated mask feature map. The eigenvalues ​​at the positions, A local significant gated mask feature map of the reference feature gradient amplitude of the mold positioning state, A reference characteristic diagram for the mold positioning state, It means point multiplication by position. A reference feature diagram for the significant mold positioning state.

[0048] Similarly, considering that the mold positioning image also contains characteristic information of the positioning state, in the technical solution of the present application, the mold positioning image is input into the positioning state image feature extractor based on the hole convolutional neural network model to mine and extract key positioning state characteristic information. Then, in order to further optimize the significant positioning area state features in the mold positioning image, the mold positioning features after convolution coding are further input into the mask salient device based on the feature gradient correlation distribution to obtain the mold positioning state detection feature map. That is, the mask salient device based on the feature gradient correlation distribution can effectively extract the significant area features of the mold positioning state, thereby improving the accuracy of subsequent positioning state detection.

[0049] In one embodiment of the present application, the mold positioning state feature extraction and saliency unit is used to: input the mold positioning image into the positioning state image feature extractor based on the void convolutional neural network model and the mask saliency based on the feature gradient correlation distribution to obtain the mold positioning state detection feature map.

[0050] Then, in order to quantify the degree of difference between the detection result and the reference result, so as to determine the final positioning state judgment result, in the technical solution of the present application, the positioning state semantic difference coefficient between each significant mold positioning state reference feature map in the set of the significant mold positioning state reference feature map and the mold positioning state detection feature map is calculated to obtain a set of positioning state semantic difference coefficients. Specifically, firstly, by pooling the reference and detection feature maps, the dimension of the feature is reduced while retaining the key positioning state feature information in the feature to obtain a set of significant mold positioning state reference feature vectors and mold positioning state detection feature vectors. Then, the difference vector and covariance matrix between each significant mold positioning state reference feature vector and the mold positioning state detection feature vector are calculated. That is, the difference vector can quantify the specific difference between the reference feature vector and the detection feature vector, providing a direct measure for the accuracy of mold positioning, while the covariance matrix can describe the change of the difference vector, which helps to understand the mold positioning state more comprehensively. Finally, the positioning state semantic difference coefficient between each significant mold positioning state reference feature map and the mold positioning state detection feature map calculated based on differential features and covariance features is used to accurately measure the difference between the significant mold positioning state reference features and the mold positioning state detection features, thereby providing a quantitative indicator for the accuracy of mold positioning.

[0051] In one embodiment of the present application, the positioning state semantic difference coefficient calculation unit is used for: a feature pooling processing subunit, which is used to perform feature pooling processing on each significant mold positioning state reference feature map in the set of the significant mold positioning state reference feature map and the mold positioning state detection feature map to obtain a set of significant mold positioning state reference feature vectors and a mold positioning state detection feature vector; a vector position difference calculation subunit, which is used to calculate the position difference between each significant mold positioning state reference feature vector in the set of the significant mold positioning state reference feature vector and the mold positioning state detection feature vector to obtain a set of mold positioning state difference feature vectors; a covariance matrix calculation subunit, which is used to calculate the significant mold positioning state reference feature map. A covariance matrix between each significant mold positioning state reference feature vector in the set of feature vectors and the mold positioning state detection feature vector is calculated, and the inverse of the covariance matrix is ​​calculated to obtain a set of mold positioning state inverse covariance matrices; a mold positioning state offset value calculation subunit is used to obtain a set of mold positioning state offset values ​​based on the offset value between each group of corresponding mold positioning state differential feature vectors and the mold positioning state inverse covariance matrix in the set of mold positioning state differential feature vectors and the set of mold positioning state inverse covariance matrix; a mold positioning state offset value square root calculation subunit is used to calculate the square root of each mold positioning state offset value in the set of mold positioning state offset values ​​to obtain a set of positioning state semantic difference coefficients.

[0052] Furthermore, in one embodiment of the present application, the mold positioning state offset value calculation subunit is used to: calculate the transposed vector of the mold positioning state differential feature vector and the product of the mold positioning state inverse covariance matrix and the mold positioning state differential feature vector to obtain the mold positioning state offset value.

[0053] Specifically, calculating the positioning state semantic difference coefficients between each significant mold positioning state reference feature map in the set of significant mold positioning state reference feature maps and the mold positioning state detection feature map to obtain a set of positioning state semantic difference coefficients, including: performing feature pooling processing on each significant mold positioning state reference feature map in the set of significant mold positioning state reference feature maps and the mold positioning state detection feature map to obtain a set of significant mold positioning state reference feature vectors and a mold positioning state detection feature vector; calculating the set of positioning state semantic difference coefficients between each significant mold positioning state reference feature vector in the set of significant mold positioning state reference feature vectors and the mold positioning state detection feature vector using the following semantic difference calculation formula; wherein the semantic difference calculation formula is: ;in, is the first in the set of reference feature vectors of the significant mold positioning state A significant mold positioning state reference feature vector, is the mold positioning state detection feature vector, is the transpose of a vector, For the said The covariance matrix between the significant mold positioning state reference feature vector and the mold positioning state detection feature vector, It is The positioning state semantic difference coefficient between a significant mold positioning state reference feature vector and the mold positioning state detection feature vector.

[0054] Then, in response to the minimum value in the set of the positioning state semantic difference coefficient being greater than or equal to a preset threshold, the accurate alignment of the new mold is confirmed. That is, the positioning state semantic difference coefficient between each significant mold positioning state reference feature map in the set of the significant mold positioning state reference feature map and the mold positioning state detection feature map is compared with a preset threshold to automatically confirm the accurate alignment of the new mold. In this way, through computer vision technology, the system can automatically identify and calibrate the mold position, reduce positioning inaccuracies caused by minor differences or wear, and improve overall accuracy. At the same time, the system no longer relies too much on preset programs and mold information, but enhances its adaptability to non-standardized or special molds through image recognition and analysis technology, thereby providing a more intelligent automatic mold change positioning method for injection molding machines.

[0055] Preferably, considering that each significant mold positioning state reference feature map in the set of significant mold positioning state reference feature maps and the mold positioning state detection feature map respectively represent the image semantic features of each mold positioning reference image and the mold positioning image that are significantly enhanced based on the feature gradient correlation distribution, when calculating the positioning state semantic difference coefficients therebetween to map to the common image application feature distribution difference metric space, there will also be image semantic feature aggregation mapping alignment conflicts to the common image application feature distribution difference metric space due to the significant enhancement distribution differences of the source image semantics based on the feature gradient correlation distribution, thereby causing the loss of aggregation key information and affecting the calculation accuracy of the set of positioning state semantic difference coefficients.

[0056] Based on this, in the preferred example, when calculating the positioning state semantic difference coefficient between each significant mold positioning state reference feature map in the set of the significant mold positioning state reference feature map and the mold positioning state detection feature map to obtain a set of positioning state semantic difference coefficients, the respective significant mold positioning state reference feature maps and the mold positioning state detection feature map are jointly optimized. Specifically, the optimization process includes the following steps: after the respective significant mold positioning state reference feature maps and the mold positioning state detection feature maps are expanded into respective significant mold positioning state reference feature vectors and mold positioning state detection feature vectors, they are further cascaded into mold positioning state state reference-detection cascade vector; clustering all eigenvalues ​​of the mold positioning state reference-detection cascade vector based on the distance between eigenvalues, such as the difference absolute value distance, and determining the ratio of the number of features of cluster features to the number of features of the mold positioning state reference-detection cascade vector; arranging the cluster features into a mold positioning state reference-detection cluster vector, and dividing the second norm of the mold positioning state reference-detection cluster vector by the second norm of the mold positioning state reference-detection cascade vector to obtain a first mold positioning state reference-detection cluster related weight value; converting the first norm of the mold positioning state reference-detection cluster vector exponentially to the first ratio; The power value is divided by a second power value of a norm of the mold positioning state reference-detection cascade vector with the ratio value as the exponent to obtain a second mold positioning state reference-detection cluster related weight value; for each eigenvalue of the mold positioning state reference-detection cluster vector, it is multiplied by the inverse of the difference between the first mold positioning state reference-detection cluster related weight value and the second mold positioning state reference-detection cluster related weight value to obtain the optimized eigenvalue of the mold positioning state reference-detection cluster vector; for each eigenvalue other than the cluster in the mold positioning state reference-detection cascade vector, it is multiplied by the first mold positioning state reference-detection cluster related weight value and the inverse of the difference between the first mold positioning state reference-detection cluster related weight value and the second mold positioning state reference-detection cluster related weight value The inverse of the sum of the weight values ​​related to the second mold positioning state reference-detection cluster is obtained to obtain the optimized out-of-class eigenvalue of the mold positioning state reference-detection cascade vector; the optimized eigenvalue of the mold positioning state reference-detection cluster vector and the optimized out-of-class eigenvalue of the mold positioning state reference-detection cascade vector are combined into an optimized mold positioning state reference-detection cascade vector; and the optimized mold positioning state reference-detection cascade vector is split into each optimized significant mold positioning state reference feature vector and optimized mold positioning state detection feature vector, and restored to each optimized significant mold positioning state reference feature map and optimized mold positioning state detection feature map.

[0057] The optimization process of the mold positioning state reference-detection cascade vector is expressed as: ; is the mold positioning state reference-detection cascade vector, for example, The number of features, is the mold positioning state reference-detection cluster vector, for example, The number of features, represents the cluster feature set corresponding to the mold positioning state reference-detection cluster vector, and Represents the binary norm and the uninorm of the vector respectively. Power, is the ratio of the number of features, is the eigenvalue of each position of the mold positioning state reference-detection cluster vector, It is the characteristic value of each position of the optimized mold positioning state reference-detection cascade vector.

[0058] Here, in order to avoid the loss of key suffix semantic information relative to the original feature set as a whole due to aggregation conflict between the respective significant mold positioning state reference feature graphs and the mold positioning state detection feature graphs based on aggregated features, the clustering ratio of the number of features of the mold positioning state reference-detection clustering vector relative to the number of features of the mold positioning state reference-detection cascade vector is used as a decision function to perform an adversarial decision on the set absolute representation of the norm of the mold positioning state reference-detection clustering vector and the mold positioning state reference-detection cascade vector, and the decision function is respectively compared with the mold positioning state reference-detection clustering vector and the mold positioning state reference-detection cascade vector. The clustering intrinsic conflict representation of the two norms of the state reference-detection cascade vector is positively and negatively interacted to construct the solid alignment guardrail of the optimized significant mold positioning state reference feature map and the optimized mold positioning state detection feature map based on the aggregated features and the original feature set as a whole, so as to achieve the mitigation of the intention of harmful information loss based on the aggregated risk transferability of the optimized significant mold positioning state reference feature map and the optimized mold positioning state detection feature map, and improve the calculation accuracy of the positioning state semantic difference coefficient between the optimized significant mold positioning state reference feature map and the optimized mold positioning state detection feature map. In this way, through computer vision technology, the system can automatically identify and calibrate the mold position, reduce the positioning inaccuracy caused by minor differences or wear, and improve the overall accuracy. At the same time, the system no longer relies too much on preset programs and mold information, but enhances the adaptability to non-standardized or special molds through image recognition and analysis technology, and provides a more intelligent automatic mold change positioning method for injection molding machines.

[0059] In summary, the above scheme is adopted, by collecting mold positioning images by a camera, and collecting a set of mold positioning reference images marked as accurately positioned from a database, and using image recognition and analysis technology based on computer vision to extract positioning state features and mask salient features of the mold positioning images and the mold positioning reference images, so as to automatically confirm the accurate alignment of the new mold according to the comparison of multiple positioning state semantic difference coefficients between the positioning state salient features of each mold positioning reference image and the mold positioning state detection features with a preset threshold. In this way, through computer vision technology, the system can automatically identify and calibrate the mold position, reduce positioning inaccuracies caused by minor differences or wear, and improve overall accuracy. At the same time, the system no longer relies too much on preset programs and mold information, but enhances the adaptability to non-standardized or special molds through image recognition and analysis technology, and thus provides a more intelligent automatic mold change positioning method for injection molding machines.

[0060] Figure 2 is a flow chart of an automatic mold change control method for an injection molding machine according to an exemplary embodiment. Figure 2 As shown, the method includes: step S201, selecting the mold number to be replaced through the HMI.

[0061] Step S202: automatically check the status of the current mold to ensure that the current mold is in a safe and detachable state.

[0062] Step S203: Sending a disassembly instruction to the hydraulic mold changing device through the control unit to disassemble the current mold through the hydraulic mold changing device, and, during the disassembly process, monitoring the movement of the current mold in real time through the position sensor.

[0063] Step S204: Select a new mold from the mold library.

[0064] Step S205: Move the new mold to the injection molding machine through the hydraulic mold changing device, and confirm whether the new mold is accurately aligned through the positioning system.

[0065] Step S206: fix the new mold on the injection molding machine through a mold locking device.

[0066] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0067] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0068] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0069] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are executed.

[0070] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0071] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0072] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0073] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0074] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0075] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the test parameter acquisition module can also be described as a "module for acquiring device test parameters corresponding to the target device".

[0076] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0077] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0078] Figure 4 is an application scenario diagram of an automatic mold change control system for an injection molding machine according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, a mold positioning image captured by a camera is obtained (for example, Figure 4 A set of mold positioning reference images annotated as accurately positioned are collected from a database (e.g., Figure 4 Then, the obtained mold positioning image and the set of accurately positioned mold positioning reference images are input to a server (for example, as Figure 4 In S) as shown in , the server can process the mold positioning image and the set of accurately positioned mold positioning reference images based on the automatic mold change control algorithm of the injection molding machine to confirm that the new mold is accurately positioned.

[0079] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

[0080] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0081] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely exemplary forms of implementation. With respect to the apparatus in the above-mentioned embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.

Claims

1. An automatic mold change control system for an injection molding machine, characterized in that: include: The mold number replacement module is used to select the mold number to be replaced through the HMI; A current mold state checking module is used to automatically check the state of the current mold to ensure that the current mold is in a safe and removable state; a current mold disassembly module is used to send a disassembly instruction to the hydraulic mold changing device through the control unit to disassemble the current mold through the hydraulic mold changing device, and, during the disassembly process, monitor the movement of the current mold in real time through the position sensor; a new mold selection module is used to select a new mold from the mold library; A new mold moving module is used to move the new mold to the injection molding machine through the hydraulic mold changing device, and confirm whether the new mold is accurately aligned through the positioning system; A new mold fixing module, used for fixing the new mold on the injection molding machine through a mold locking device; The new mold moving module includes: a mold positioning image acquisition unit, which is used to obtain a mold positioning image acquired by a camera; an accurately positioned mold positioning reference image acquisition unit, which is used to acquire a set of mold positioning reference images marked as accurately positioned from a database; a mold positioning state reference feature extraction unit, which is used to input each mold positioning reference image marked as accurately positioned in the set of mold positioning reference images marked as accurately positioned into a positioning state image feature extractor to obtain a set of mold positioning state reference feature maps; a mold positioning state reference feature saliency unit, which is used to input each mold positioning state reference feature map in the set of mold positioning state reference feature maps into a mask saliency based on feature gradient correlation distribution. To obtain a set of significant mold positioning state reference feature maps; a mold positioning state feature extraction and saliency unit, used to input the mold positioning image into the positioning state image feature extractor and the mask saliency based on feature gradient association distribution to obtain a mold positioning state detection feature map; a positioning state semantic difference coefficient calculation unit, used to calculate the positioning state semantic difference coefficient between each significant mold positioning state reference feature map in the set of significant mold positioning state reference feature maps and the mold positioning state detection feature map to obtain a set of positioning state semantic difference coefficients; a mold accurate alignment judgment unit, used to confirm that the new mold is accurately aligned in response to the minimum value in the set of positioning state semantic difference coefficients being greater than or equal to a preset threshold.

2. The automatic mold change control system for an injection molding machine according to claim 1, characterized in that: The mold positioning state reference feature extraction unit is used to: input each mold positioning reference image marked as accurately positioned in the set of mold positioning reference images marked as accurately positioned into a positioning state image feature extractor based on a hole convolutional neural network model to obtain a set of mold positioning state reference feature maps.

3. The automatic mold change control system for an injection molding machine according to claim 2, characterized in that: The mold positioning state reference feature significant unit includes: a mold positioning state reference feature gradient amplitude value calculation subunit, which is used to calculate the multi-directional gradient value distribution of each position in the mold positioning state reference feature map, and determine the gradient amplitude value of each position in the mold positioning state reference feature map based on the multi-directional gradient value distribution of each position to obtain the mold positioning state reference feature gradient amplitude distribution feature map; a mold positioning state reference feature gradient amplitude local description operator calculation subunit, which is used to calculate the gradient amplitude local description operator of each position in the mold positioning state reference feature gradient amplitude distribution feature map to obtain the mold positioning state reference feature gradient amplitude local significant distribution feature map; a gated mask subunit, which is used to input the mold positioning state reference feature gradient amplitude local significant distribution feature map into a gated masker based on a GELU function to obtain a mold positioning state reference feature gradient amplitude local significant gated mask feature map; and a position point multiplication calculation subunit, which is used to calculate the position point multiplication between the mold positioning state reference feature gradient amplitude local significant gated mask feature map and the mold positioning state reference feature map to obtain the significant mold positioning state reference feature map.

4. The automatic mold change control system for an injection molding machine according to claim 3, characterized in that: The mold positioning state reference characteristic gradient amplitude value calculation subunit is used to: calculate the gradient value of each characteristic value in the mold positioning state reference characteristic map along the width direction to obtain the mold positioning state reference width direction characteristic gradient value characteristic map; calculate the gradient value of each characteristic value in the mold positioning state reference characteristic map along the height direction to obtain the mold positioning state reference height direction characteristic gradient value characteristic map; calculate the gradient value of each characteristic value in the mold positioning state reference characteristic map along the channel direction to obtain the mold positioning state reference channel direction characteristic gradient value characteristic map; calculate the square root of the sum of the squares of the characteristic values ​​at corresponding positions in the mold positioning state reference width direction characteristic gradient value characteristic map, the mold positioning state reference height direction characteristic gradient value characteristic map and the mold positioning state reference channel direction characteristic gradient value characteristic map to obtain the mold positioning state reference characteristic gradient amplitude distribution characteristic map.

5. The automatic mold change control system for an injection molding machine according to claim 4, characterized in that: The mold positioning state reference feature gradient amplitude local description operator calculation subunit is used to: determine the gradient amplitude local neighborhood range, and calculate the sequence of the mold positioning state reference feature gradient amplitude neighborhood distribution feature map based on the gradient amplitude local neighborhood range and the mold positioning state reference feature gradient amplitude distribution feature map; count the number of feature maps in the sequence of the mold positioning state reference feature gradient amplitude neighborhood distribution feature map to obtain the mold positioning state reference feature gradient amplitude neighborhood number statistics; calculate the mold positioning state reference feature gradient amplitude distribution feature map and the sequence of the mold positioning state reference feature gradient amplitude neighborhood distribution feature map The positional differences between the mold positioning state reference feature gradient amplitude neighborhood distribution feature maps in the column are divided by the mold positioning state reference feature gradient amplitude distribution feature map by position point to obtain a sequence of mold positioning state reference feature gradient relative amplitude distribution neighborhood feature maps; the positional addition of each mold positioning state reference feature gradient relative amplitude distribution neighborhood feature map in the sequence of the mold positioning state reference feature gradient relative amplitude distribution neighborhood feature map is performed by position point and divided by the mold positioning state reference feature gradient amplitude neighborhood number statistics value by position point to obtain the mold positioning state reference feature gradient amplitude local significant distribution feature map.

6. The automatic mold change control system for an injection molding machine according to claim 5, characterized in that: The mold positioning state feature extraction and saliency unit is used to: input the mold positioning image into the positioning state image feature extractor based on the void convolutional neural network model and the mask saliency device based on the feature gradient correlation distribution to obtain the mold positioning state detection feature map.

7. The automatic mold change control system for an injection molding machine according to claim 6, characterized in that: The positioning state semantic difference coefficient calculation unit includes: a feature pooling processing subunit, which is used to perform feature pooling processing on each significant mold positioning state reference feature map in the set of the significant mold positioning state reference feature map and the mold positioning state detection feature map to obtain a set of significant mold positioning state reference feature vectors and a mold positioning state detection feature vector; a vector position difference calculation subunit, which is used to calculate the position difference between each significant mold positioning state reference feature vector in the set of the significant mold positioning state reference feature vector and the mold positioning state detection feature vector to obtain a set of mold positioning state difference feature vectors; a covariance matrix calculation subunit, which is used to calculate the set of the significant mold positioning state reference feature vectors. The covariance matrix between each significant mold positioning state reference feature vector in the set and the mold positioning state detection feature vector is calculated, and the inverse of the covariance matrix is ​​calculated to obtain a set of mold positioning state inverse covariance matrices; a mold positioning state offset value calculation subunit is used to obtain a set of mold positioning state offset values ​​based on the offset value between each group of corresponding mold positioning state differential feature vectors and the mold positioning state inverse covariance matrix in the set of mold positioning state differential feature vectors and the set of mold positioning state inverse covariance matrix; a mold positioning state offset value square root calculation subunit is used to calculate the square root of each mold positioning state offset value in the set of mold positioning state offset values ​​to obtain a set of positioning state semantic difference coefficients.

8. The automatic mold change control system for an injection molding machine according to claim 7, characterized in that: The mold positioning state offset value calculation subunit is used to calculate the transposed vector of the mold positioning state differential feature vector and the product of the mold positioning state inverse covariance matrix and the mold positioning state differential feature vector to obtain the mold positioning state offset value.

Images