CN116552049A

CN116552049A - Disposable paper cup production equipment and method thereof

Info

Publication number: CN116552049A
Application number: CN202310738849.8A
Authority: CN
Inventors: 刘勇江; 黄邦友; 冷松平; 熊强
Original assignee: Jiaxing Huanqiang Machinery Co ltd
Current assignee: Jiaxing Huanqiang Machinery Co ltd
Priority date: 2023-06-21
Filing date: 2023-06-21
Publication date: 2023-08-08

Abstract

The utility model relates to the field of intelligent production, and particularly discloses a disposable paper cup production device and a method thereof, which can be based on state characteristics of disposable paper cups and high-dimensional implicit characteristics among different numbers of heating temperature values in different time spans, so that classification characteristic representations comprising the heating temperature characteristics and the state change characteristics of the disposable paper cups are obtained by utilizing logic association between the state characteristics and the heating temperature values. Therefore, the temperature of the disposable paper cup production equipment is adaptively controlled based on the classification characteristics, so that high-quality products are guaranteed to be produced, and the production efficiency of the equipment is improved.

Description

Disposable paper cup production equipment and method thereof

Technical Field

The application relates to the field of intelligent production, and more particularly relates to a disposable paper cup production device and a method thereof.

Background

The disposable paper cup production equipment comprises a base paper processing module, a forming module, a coating module, an internal mold punching module, a printing module and a packaging module. In the forming module, the shape and quality of the paper cup are affected by temperature. If the temperature is not proper, the paper cup is too fragile or unstable in shape, and the using effect of the product is affected. Meanwhile, the temperature change in the production process of the disposable paper cup happens at any time. In addition, the heating time and temperature requirements may be different for each cup due to the different thickness and shape of the paper.

The self-adaptive control of the temperature can be realized through artificial intelligence, and the temperature can be dynamically adjusted according to actual conditions, so that high-quality and stable products can be ensured to be produced. These factors all need to be addressed by adaptive control. The self-adaptive control generally uses the technical means of a sensor, a computer and the like, can acquire the temperature information of each part of the equipment in real time, and can carry out accurate adjustment according to actual conditions. For example, if the paper temperature is detected to be too low, the system automatically increases the power of the heater to increase the temperature. Conversely, if the paper temperature is too high, the system will decrease the heating power to decrease the temperature.

Accordingly, an optimized disposable paper cup manufacturing apparatus is desired that is capable of adaptively adjusting the heating temperature based on the relationship between the state characteristics of paper cups and the heating temperature, ensuring the production of high quality products, and improving the production efficiency of the apparatus.

Disclosure of Invention

The present application has been made in order to solve the above technical problems. Embodiments of the present application provide a disposable paper cup manufacturing apparatus and method thereof that can obtain a classification feature representation including a heating temperature feature and a disposable paper cup state change feature using a logical association between a high-dimensional implicit feature between the state feature of a disposable paper cup and a different number of heating temperature values over different time spans. Therefore, the temperature of the disposable paper cup production equipment is adaptively controlled based on the classification characteristics, so that high-quality products are guaranteed to be produced, and the production efficiency of the equipment is improved.

According to one aspect of the present application, there is provided a disposable paper cup manufacturing apparatus comprising:

the data acquisition module is used for acquiring a monitoring video of the disposable paper cup in a preset time period and heating temperature values of a plurality of preset time points in the preset time period;

the sampling module is used for extracting a plurality of disposable paper cup monitoring key frames from the disposable paper cup monitoring video in the preset time period;

the depth feature coding module is used for enabling the plurality of disposable paper cup monitoring key frames to pass through a first convolution neural network model comprising a depth fusion module to obtain a plurality of disposable paper cup monitoring feature matrixes;

the three-dimensional convolution encoding module is used for acquiring a state change feature vector of the disposable paper cup by using a second convolution neural network model of a three-dimensional convolution kernel after aggregating the plurality of the monitoring feature matrices of the disposable paper cup into a three-dimensional feature tensor along a sample dimension;

the multi-scale encoding module is used for arranging the heating temperature values of the plurality of preset time points into heating temperature input vectors according to the time dimension and then obtaining heating temperature feature vectors through the multi-scale neighborhood feature extraction module;

the responsiveness estimation module is used for calculating responsiveness estimation of the state change feature vector of the disposable paper cup relative to the heating temperature feature vector so as to obtain a classification feature matrix; and

And the detection result generation module is used for passing the classification feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the heating temperature at the current time point should be increased or decreased.

In the above-mentioned disposable paper cup production equipment, the sampling module is used for: the plurality of throw-away monitoring key frames are extracted from the throw-away monitoring video for the predetermined period of time at a predetermined sampling frequency.

In the above-mentioned disposable paper cup production facility, the depth characteristic coding module includes:

a shallow feature extraction unit, configured to extract a shallow feature map from an mth layer of the first convolutional neural network model, where M is greater than or equal to 1 and less than or equal to 6;

a deep feature extraction unit, configured to extract a deep feature map from an nth layer of the first convolutional neural network model, where N/M is greater than or equal to 5 and less than or equal to 10;

the fusion unit is used for fusing the shallow feature map and the deep feature map by using a depth feature fusion module of the first convolutional neural network model so as to obtain a fusion feature map; and

and the dimension reduction unit is used for carrying out global pooling on the fusion feature map along the channel dimension so as to obtain the disposable paper cup monitoring feature matrix.

In the above-mentioned disposable paper cup production equipment, the three-dimensional convolution coding module includes:

the coding unit is used for carrying out three-dimensional convolution coding on the three-dimensional feature tensor by using the second convolution neural network model so as to obtain a disposable paper cup state change feature diagram; and

and the dimension reduction unit is used for carrying out global average pooling on each feature matrix of the disposable paper cup state change feature diagram along the channel dimension so as to obtain the disposable paper cup state change feature vector.

In the above-mentioned disposable paper cup production equipment, the three-dimensional convolution coding module is used for:

input data are respectively subjected to forward transfer of layers by using the second convolution neural network model using the three-dimensional convolution kernel:

performing three-dimensional convolution processing on the input data based on the three-dimensional convolution check to obtain a convolution characteristic diagram;

carrying out mean pooling treatment based on a local feature matrix on the convolution feature map to obtain a pooled feature map; and

non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;

the output of the last layer of the second convolutional neural network model is the state change characteristic diagram of the disposable paper cup, and the input of the first layer of the second convolutional neural network model is the three-dimensional characteristic tensor.

In the above-mentioned disposable paper cup production facility, the multiscale coding module includes:

a first scale feature extraction unit, configured to input the heating temperature input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale heating temperature feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length;

a second scale feature extraction unit configured to input the heating temperature input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale heating temperature feature vector, where the second convolution layer has a second one-dimensional convolution kernel of a second length, and the first length is different from the second length; and

and the class probability combining unit is used for carrying out class probability simultaneous projection between all the sub-dimensions based on the feature set on the first scale heating temperature feature vector and the second scale heating temperature feature vector so as to obtain the heating temperature feature vector.

In the above-mentioned disposable paper cup production equipment, the multiscale coding module is used for: performing one-dimensional convolution coding on the heating temperature input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following first convolution formula to obtain a first-scale heating temperature feature vector;

Wherein the first convolution formula is:

wherein a is the width of the first convolution kernel in the X direction, F (a) is a first convolution kernel parameter vector, G (X-a) is a local vector matrix calculated by a convolution kernel function, w is the size of the first convolution kernel, X represents the heating temperature input vector, and Cov (X) is the convolution processing of the heating temperature input vector;

the inputting the heating temperature input vector into the second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale heating temperature feature vector includes: performing one-dimensional convolution coding on the heating temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following second convolution formula to obtain a second-scale heating temperature feature vector;

wherein the second convolution formula is:

wherein b is the width of the second convolution kernel in the X direction, F (b) is a second convolution kernel parameter vector, G (X-b) is a local vector matrix calculated by a convolution kernel function, m is the size of the second convolution kernel, X represents the heating temperature input vector, and Cov (X) is to carry out convolution processing on the heating temperature input vector.

In the above-mentioned disposable paper cup producing apparatus, the probability-like united unit includes:

A covariance subunit, configured to calculate a covariance matrix between the first-scale heating temperature feature vector and the second-scale heating temperature feature vector;

a decomposition subunit, configured to decompose eigenvalues of the covariance matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors corresponding to the eigenvalues;

a main feature extraction subunit, configured to extract feature vectors corresponding to the first two feature values from the plurality of feature vectors to obtain a first main feature vector and a second main feature vector;

the pre-classification subunit is used for respectively passing the first main feature vector and the second main feature vector through a pre-classifier to obtain a first probability value and a second probability value; the method comprises the steps of,

and the weighted sub-unit is used for calculating the weighted sum of the first scale heating temperature characteristic vector and the second scale heating temperature characteristic vector by taking the first probability value and the second probability value as weights so as to obtain the heating temperature characteristic vector.

In the above-mentioned disposable paper cup producing apparatus, the responsiveness estimating module is configured to:

calculating a responsiveness estimate of the disposable cup state change feature vector relative to the heating temperature feature vector with a responsiveness estimate formula to obtain a classification feature matrix;

Wherein, the responsiveness estimation formula is:

wherein V is _a Representing the state change characteristic vector of the disposable paper cup, V _b Representing the heating temperature feature vector, M representing the classification feature matrix,representing matrix multiplication.

In the above-mentioned disposable paper cup production device, the detection result generation module is configured to:

expanding the classification feature matrix into classification feature vectors according to row vectors or column vectors;

performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and

and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

According to another aspect of the present application, there is also provided a method for producing a disposable paper cup, comprising:

acquiring a monitoring video of a disposable paper cup in a preset time period and heating temperature values of a plurality of preset time points in the preset time period;

extracting a plurality of disposable paper cup monitoring key frames from the disposable paper cup monitoring video of the preset time period;

the plurality of disposable paper cup monitoring key frames pass through a first convolution neural network model comprising a depth fusion module to obtain a plurality of disposable paper cup monitoring feature matrixes;

Aggregating the plurality of disposable paper cup monitoring feature matrixes into a three-dimensional feature tensor along the dimension of the sample, and obtaining a state change feature vector of the disposable paper cup through a second convolution neural network model using a three-dimensional convolution kernel;

the heating temperature values of the plurality of preset time points are arranged into heating temperature input vectors according to the time dimension, and then the heating temperature input vectors are processed through a multi-scale neighborhood feature extraction module to obtain heating temperature feature vectors;

calculating the response estimation of the state change feature vector of the disposable paper cup relative to the heating temperature feature vector to obtain a classification feature matrix; and

the classification feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the heating temperature at the current time point should be increased or decreased.

Compared with the prior art, the method for producing the disposable paper cup can be based on the state characteristics of the disposable paper cup and the high-dimensional implicit characteristics among different numbers of heating temperature values in different time spans, so that the classification characteristic representation comprising the heating temperature characteristics and the state change characteristics of the disposable paper cup is obtained by utilizing the logic association between the state characteristics and the heating temperature values. Therefore, the temperature of the disposable paper cup production equipment is adaptively controlled based on the classification characteristics, so that high-quality products are guaranteed to be produced, and the production efficiency of the equipment is improved.

Drawings

The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.

Fig. 1 is an application scenario diagram of a disposable paper cup manufacturing apparatus according to an embodiment of the present application.

Fig. 2 is a block diagram of a disposable paper cup manufacturing apparatus according to an embodiment of the present application.

Fig. 3 is a construction view of a paper disposable cup manufacturing apparatus according to an embodiment of the present application.

Fig. 4 is a block diagram of a shade feature coding module in a method of manufacturing a disposable paper cup according to an embodiment of the present application.

Fig. 5 is a block diagram of a shade fusion module in a method of manufacturing a disposable paper cup according to an embodiment of the present application.

Fig. 6 is a block diagram of a class probability union unit in a method of producing a throw-away paper cup according to an embodiment of the present application.

Fig. 7 is a flowchart of a method of producing a disposable paper cup according to an embodiment of the present application.

Fig. 8 is a block diagram of an electronic device 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 apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.

Summary of the application

As described above, in the molding module, both the shape and quality of the paper cup molding are affected by temperature. If the temperature is not proper, the paper cup is too fragile or unstable in shape, and the using effect of the product is affected. Meanwhile, the temperature change in the production process of the disposable paper cup happens at any time. In addition, the heating time and temperature requirements may be different for each cup due to the different thickness and shape of the paper. Accordingly, an optimized disposable paper cup manufacturing apparatus is desired that is capable of adaptively adjusting the heating temperature based on the relationship between the state characteristics of paper cups and the heating temperature, ensuring the production of high quality products, and improving the production efficiency of the apparatus.

To above-mentioned technical problem, in the technical scheme of this application, expect to adjust disposable paper cup production facility's heating temperature based on disposable paper cup state change and different heating temperature values in the different time span self-adaptation, through this kind of mode, need not the manual control disposable paper cup production facility's heating temperature, and because of having considered disposable paper cup more data dimension and not receiving the restriction of scene, consequently, the disposable paper cup production facility that this application provided has stronger suitability and intelligence.

At present, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.

Deep learning and neural network provide new solution ideas and schemes for the construction of disposable paper cup production equipment.

Specifically, in the technical scheme of the application, firstly, a monitoring video of a disposable paper cup in a preset time period and heating temperature values of a plurality of preset time points in the preset time period are obtained. It will be appreciated that temperature variations in the disposable paper cup can affect the status characteristics of the disposable paper cup, particularly the color characteristics. Particularly, in the technical scheme of the application, along with the change of the temperature of the disposable paper cup production equipment, the state characteristics of the disposable paper cup also have obvious change, and the change characteristics of the state characteristics of the disposable paper cup in the disposable paper cup monitoring video have complex nonlinear relation with the temperature of the disposable paper cup production equipment.

In order to capture and utilize the implicit association, in the technical scheme of the application, a deep neural network model based on deep learning is used for processing the disposable paper cup monitoring video so as to obtain a state change feature vector of the disposable paper cup. In particular, considering that many image frames in all image frame sequences of the paper cup monitoring video are highly similar and even repeated, the information redundancy is caused, and the interference is caused to the feature extraction. Therefore, before feature extraction, in the technical solution of the present application, the throw-away paper cup monitoring video is first sampled, and in a specific example, a plurality of throw-away paper cup monitoring key frames are extracted from the throw-away paper cup monitoring video of the predetermined period of time at a predetermined sampling frequency.

And then, passing the plurality of disposable paper cup monitoring key frames through a first convolution neural network model comprising a depth fusion module to obtain a plurality of disposable paper cup monitoring feature matrixes. That is, a convolutional neural network model having excellent performance in the field of image feature extraction is used as a feature extractor to capture high-dimensional local image implicit features of each of the plurality of disposable paper cup monitoring key frames. Considering that as the convolutional coding depth of the convolutional neural network model increases, the extracted image features are more abstract and reflect the essence of the object, in particular, the shallow features of the convolutional neural network model represent appearance, lines, textures and colors, and the deep features of the convolutional neural network model represent object types, object features and the like. Considering that in the technical solution of the present application, in the disposable paper cup production apparatus, the shape change of the disposable paper cup is expected to be focused more, in the technical solution of the present application, the structure of the convolutional neural network model is adjusted to integrate the depth feature fusion mechanism into the feature extraction mechanism of the convolutional neural network model.

And then, the plurality of disposable paper cup monitoring feature matrices are aggregated into a three-dimensional feature tensor along the dimension of the sample, and then a second convolution neural network model of the three-dimensional convolution kernel is used for obtaining a disposable paper cup state change feature vector. That is, in a high-dimensional feature space, the plurality of disposable cup monitoring feature matrices are information aggregated along a sample dimension to obtain a three-dimensional feature tensor, and a convolutional neural network model using a three-dimensional convolutional kernel is used as a feature extractor to capture the disposable cup state change feature. The second convolutional neural network model is three-dimensional convolutional encoded using a three-dimensional convolutional kernel, as compared to a conventional convolutional neural network model, wherein the three-dimensional convolutional kernel has three-dimensional dimensions: a width dimension, a height dimension, and a channel dimension, the width dimension and the height dimension corresponding to a local space of each image frame, and the channel dimension corresponding to a time dimension of the three-dimensional feature tensor, thereby enabling extraction of a change feature of a state feature of the disposable paper cup in the space dimension in the time dimension in a process of performing three-dimensional convolution encoding.

According to the technical scheme of the application, the heating temperature values at the preset time points are arranged into heating temperature input vectors according to the time dimension and then pass through the multi-scale domain feature extraction module to obtain heating temperature feature vectors. That is, the heating temperature values at the plurality of predetermined time points are first vectorized to obtain a heating temperature input vector, that is, a time-series distribution of the heating temperature values. And then, carrying out multi-scale one-dimensional convolution coding on the heating temperature input vector by using a multi-scale neighborhood feature extraction module comprising a plurality of parallel one-dimensional convolution layers so as to capture high-dimensional implicit features among different numbers of heating temperature values in different time spans, and carrying out feature fusion on associated features of different scales so as to obtain the heating temperature feature vector.

In the technical scheme of the application, the heating temperature is the cause of the state change of the disposable paper cup method, that is, the heating temperature and the state change of the disposable paper cup have a correlation on a logic level, and the classification characteristic representation comprising the heating temperature characteristic and the state change characteristic of the disposable paper cup is obtained by utilizing the logic correlation between the heating temperature and the state change of the disposable paper cup. Specifically, a responsiveness estimate of the disposable cup state change feature vector relative to the heating temperature feature vector is calculated to obtain a classification feature matrix. And after the classification feature matrix is obtained, the classification feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the heating temperature at the current time point should be increased or decreased.

Thus, the heating temperature is adjusted based on the state of the disposable paper cup so that the heating temperature reaches the optimal state of the production of the disposable paper cup.

Particularly, in the technical scheme of the application, when the heating temperature values at the plurality of preset time points are arranged into heating temperature input vectors according to the time dimension and then pass through a multi-scale neighborhood feature extraction module to obtain heating temperature feature vectors, the multi-scale neighborhood feature extraction module uses one-dimensional convolution cores with different scales to carry out multi-scale one-dimensional convolution coding on the heating temperature input vectors so as to obtain first-scale heating temperature feature vectors and second-scale heating temperature feature vectors. Because of the encoding characteristics of the multi-scale neighborhood feature extraction module, the feature distribution of the first-scale heating temperature feature vector may have spatial migration with respect to the feature distribution of the second-scale heating temperature feature vector due to different feature extraction scales. Therefore, if the fusion effect of the first scale heating temperature feature vector and the second scale heating temperature feature vector under the condition of space migration can be improved, the expression effect of the heating temperature feature vector can be improved, and further high-quality data base support is provided for the response estimation calculation of the state change feature vector of the disposable paper cup relative to the heating temperature feature vector, so that the accuracy of classification judgment of the classification feature matrix is improved.

Based on the above, in the technical solution of the present application, a quasi-probabilistic simultaneous projection between each sub-dimension based on a feature set is performed on the first-scale heating temperature feature vector and the second-scale heating temperature feature vector to obtain the heating temperature feature vector. Specifically, the process of performing a quasi-probabilistic simultaneous projection between each sub-dimension based on a feature set on the first-scale heating temperature feature vector and the second-scale heating temperature feature vector to obtain the heating temperature feature vector includes: firstly, calculating a covariance matrix between the first scale heating temperature characteristic vector and the second scale heating temperature characteristic vector; performing eigenvalue decomposition on the covariance matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors corresponding to the eigenvalues; extracting feature vectors corresponding to the first two feature values from the plurality of feature vectors to obtain a first main feature vector and a second main feature vector; respectively passing the first main feature vector and the second main feature vector through a pre-classifier to obtain a first probability value and a second probability value; and calculating a weighted sum of the first scale heating temperature feature vector and the second scale heating temperature feature vector by taking the first probability value and the second probability value as weights to obtain a heating temperature feature vector.

Here, the first scale heating temperature feature vector and the second scale heating temperature feature vector are projected based on the quasi-probability co-projection between the sub-dimensions of the feature set, so that the high-dimensional feature representations of the first scale heating temperature feature vector and the second scale heating temperature feature vector can be mapped into a relatively low-dimensional space, and the orthogonality and the category information between the first scale heating temperature feature vector and the second scale heating temperature feature vector are utilized to enable different types of data in the first scale heating temperature feature vector and the second scale heating temperature feature vector to have larger distances in the relatively low-dimensional space, and meanwhile, the internal structure of the data is maintained, so that the data expression capability of the heating temperature feature vector is improved.

Fig. 1 is an application scenario diagram of a disposable paper cup manufacturing apparatus according to an embodiment of the present application. As shown in fig. 1, in this application scenario, first, a disposable cup (e.g., F as illustrated in fig. 1) is collected by a camera (e.g., C as illustrated in fig. 1), a video of a disposable cup monitoring for the predetermined period, and heating temperature values at a plurality of predetermined time points within the predetermined period, which are collected by a temperature sensor (e.g., se as illustrated in fig. 1). Further, the paper cup monitoring video for the predetermined period of time, the heating temperature values for a plurality of predetermined time points within the predetermined period of time, are input to a server (e.g., S as illustrated in fig. 1) in which an algorithm for paper cup production is deployed, wherein the server is capable of processing the paper cup monitoring video for the predetermined period of time, the heating temperature values for a plurality of predetermined time points within the predetermined period of time, based on the algorithm for paper cup production, to obtain a classification result for indicating that the heating temperature for the current time point should be increased or decreased.

Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.

Exemplary System

Fig. 2 is a block diagram of a disposable paper cup manufacturing apparatus according to an embodiment of the present application. As shown in fig. 2, the paper cup manufacturing apparatus 100 according to the embodiment of the present application includes: a data acquisition module 110, configured to acquire a monitoring video of a disposable paper cup in a predetermined period of time, and heating temperature values at a plurality of predetermined time points in the predetermined period of time; a sampling module 120 for extracting a plurality of throw-away paper cup monitoring key frames from the throw-away paper cup monitoring video for the predetermined period of time; the depth feature encoding module 130 is configured to pass the plurality of disposable paper cup monitoring key frames through a first convolutional neural network model including a depth fusion module to obtain a plurality of disposable paper cup monitoring feature matrices; the three-dimensional convolution encoding module 140 is configured to aggregate the plurality of disposable paper cup monitoring feature matrices into a three-dimensional feature tensor along a sample dimension, and obtain a disposable paper cup state change feature vector by using a second convolution neural network model of the three-dimensional convolution kernel; the multi-scale encoding module 150 is configured to arrange the heating temperature values at the plurality of predetermined time points into heating temperature input vectors according to a time dimension, and then obtain heating temperature feature vectors through the multi-scale neighborhood feature extraction module; a responsiveness estimation module 160, configured to calculate a responsiveness estimate of the disposable cup state change feature vector relative to the heating temperature feature vector to obtain a classification feature matrix; and a detection result generating module 170, configured to pass the classification feature matrix through a classifier to obtain a classification result, where the classification result is used to indicate that the heating temperature at the current time point should be increased or decreased.

Fig. 3 is a construction view of a paper disposable cup manufacturing apparatus according to an embodiment of the present application. As shown in fig. 3, in the system architecture, first, a monitoring video of a disposable cup for a predetermined period of time, heating temperature values at a plurality of predetermined time points within the predetermined period of time are acquired. Then, a plurality of throw-away paper cup monitoring key frames are extracted from the throw-away paper cup monitoring video for the predetermined period of time. And then, the plurality of disposable paper cup monitoring key frames are passed through a first convolution neural network model comprising a depth fusion module to obtain a plurality of disposable paper cup monitoring feature matrices. And then, the plurality of disposable paper cup monitoring feature matrices are aggregated into a three-dimensional feature tensor along the dimension of the sample, and then a second convolution neural network model of the three-dimensional convolution kernel is used for obtaining a state change feature vector of the disposable paper cup. And then, arranging the heating temperature values of the plurality of preset time points into heating temperature input vectors according to a time dimension, and obtaining heating temperature feature vectors through a multi-scale neighborhood feature extraction module. Then, calculating the response estimation of the state change feature vector of the disposable paper cup relative to the heating temperature feature vector to obtain a classification feature matrix. Finally, the classification feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the heating temperature at the current time point should be increased or decreased.

In the above-described disposable paper cup manufacturing apparatus 100, the data acquisition module 110 is configured to acquire a monitoring video of a disposable paper cup for a predetermined period of time, and heating temperature values at a plurality of predetermined time points within the predetermined period of time. As described above, in the molding module, both the shape and quality of the paper cup molding are affected by temperature. If the temperature is not proper, the paper cup is too fragile or unstable in shape, and the using effect of the product is affected. Meanwhile, the temperature change in the production process of the disposable paper cup happens at any time. In addition, the heating time and temperature requirements may be different for each cup due to the different thickness and shape of the paper. Accordingly, an optimized disposable paper cup manufacturing apparatus is desired that is capable of adaptively adjusting the heating temperature based on the relationship between the state characteristics of paper cups and the heating temperature, ensuring the production of high quality products, and improving the production efficiency of the apparatus.

To above-mentioned technical problem, in the technical scheme of this application, expect to adjust disposable paper cup production facility's heating temperature based on disposable paper cup state change and different heating temperature values in the different time span self-adaptation, through this kind of mode, need not the manual control disposable paper cup production facility's temperature, and because of having considered disposable paper cup more data dimension and not receiving the restriction of scene, consequently, the disposable paper cup production facility that this application provided has stronger suitability and intelligence.

In the above-described paper cup manufacturing apparatus 100, the sampling module 120 is configured to extract a plurality of paper cup monitoring key frames from the paper cup monitoring video for the predetermined period of time. In order to capture and utilize the implicit association, in the technical scheme of the application, a deep neural network model based on deep learning is used for processing the disposable paper cup monitoring video so as to obtain a state change feature vector of the disposable paper cup. In particular, considering that many image frames in all image frame sequences of the paper cup monitoring video are highly similar and even repeated, the information redundancy is caused, and the interference is caused to the feature extraction. Therefore, before feature extraction, in the technical solution of the present application, the throw-away paper cup monitoring video is first sampled, and in a specific example, a plurality of throw-away paper cup monitoring key frames are extracted from the throw-away paper cup monitoring video of the predetermined period of time at a predetermined sampling frequency.

Specifically, in the embodiment of the present application, the sampling module 120 is configured to extract the plurality of keyframes for monitoring the disposable paper cup from the video for monitoring the disposable paper cup for the predetermined period of time at a predetermined sampling frequency.

In the above-mentioned disposable paper cup production apparatus 100, the depth feature encoding module 130 is configured to pass the plurality of disposable paper cup monitoring key frames through the first convolutional neural network model including the depth fusion module to obtain a plurality of disposable paper cup monitoring feature matrices. And passing the plurality of disposable paper cup monitoring key frames through a first convolution neural network model comprising a depth fusion module to obtain a plurality of disposable paper cup monitoring feature matrixes. That is, a convolutional neural network model having excellent performance in the field of image feature extraction is used as a feature extractor to capture high-dimensional local image implicit features of each of the plurality of disposable paper cup monitoring key frames. Considering that as the convolutional coding depth of the convolutional neural network model increases, the extracted image features are more abstract and reflect the essence of the object, in particular, the shallow features of the convolutional neural network model represent appearance, lines, textures and colors, and the deep features of the convolutional neural network model represent object types, object features and the like. Considering that in the technical solution of the present application, in the production of the disposable paper cup, attention is expected to be paid more to the color change of the disposable paper cup, therefore, in the technical solution of the present application, the structure of the convolutional neural network model is adjusted to integrate the depth feature fusion mechanism into the feature extraction mechanism of the convolutional neural network model.

Fig. 4 is a block diagram of a depth feature encoding module in a disposable paper cup manufacturing apparatus according to an embodiment of the present application. As shown in fig. 4, the depth feature encoding module 130 is configured to: a shallow feature extraction unit 131, configured to extract a shallow feature map from an mth layer of the first convolutional neural network model, where M is greater than or equal to 1 and less than or equal to 6; a deep feature extraction unit 132 for extracting a deep feature map from an nth layer of the first convolutional neural network model, wherein N/M is 5 or more and 10 or less; a fusion unit 133, configured to fuse the shallow feature map and the deep feature map by using a deep-shallow feature fusion module of the first convolutional neural network model to obtain a fused feature map; and a dimension reduction unit 134, configured to perform global pooling along a channel dimension on the fused feature map to obtain the disposable paper cup monitoring feature matrix.

In the above-mentioned disposable paper cup production apparatus 100, the three-dimensional convolution encoding module 140 is configured to aggregate the plurality of disposable paper cup monitoring feature matrices into a three-dimensional feature tensor along the sample dimension, and obtain the state change feature vector of the disposable paper cup by using the second convolution neural network model of the three-dimensional convolution kernel. And aggregating the plurality of disposable paper cup monitoring feature matrices into a three-dimensional feature tensor along the dimension of the sample, and obtaining a state change feature vector of the disposable paper cup through a second convolution neural network model using a three-dimensional convolution kernel. That is, in a high-dimensional feature space, the plurality of disposable cup monitoring feature matrices are information aggregated along a sample dimension to obtain a three-dimensional feature tensor, and a convolutional neural network model using a three-dimensional convolutional kernel is used as a feature extractor to capture the disposable cup state change feature. The second convolutional neural network model is three-dimensional convolutional encoded using a three-dimensional convolutional kernel, as compared to a conventional convolutional neural network model, wherein the three-dimensional convolutional kernel has three-dimensional dimensions: a width dimension, a height dimension, and a channel dimension, the width dimension and the height dimension corresponding to a local space of each image frame, and the channel dimension corresponding to a time dimension of the three-dimensional feature tensor, thereby enabling extraction of a change feature of a state feature of the disposable paper cup in the space dimension in the time dimension in a process of performing three-dimensional convolution encoding.

Specifically, in the embodiment of the present application, the three-dimensional convolutional encoding module 140 includes: the coding unit is used for carrying out three-dimensional convolution coding on the three-dimensional feature tensor by using the second convolution neural network model so as to obtain a disposable paper cup state change feature diagram; and the dimension reduction unit is used for carrying out global average pooling on each feature matrix of the disposable paper cup state change feature diagram along the channel dimension so as to obtain the disposable paper cup state change feature vector.

Specifically, in the embodiment of the present application, the three-dimensional convolutional encoding module 140 includes: input data are respectively subjected to forward transfer of layers by using the second convolution neural network model using the three-dimensional convolution kernel: performing three-dimensional convolution processing on the input data based on the three-dimensional convolution check to obtain a convolution characteristic diagram; carrying out mean pooling treatment based on a local feature matrix on the convolution feature map to obtain a pooled feature map; non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map; the output of the last layer of the second convolutional neural network model is the state change characteristic diagram of the disposable paper cup, and the input of the first layer of the second convolutional neural network model is the three-dimensional characteristic tensor.

In the above-mentioned disposable paper cup production apparatus 100, the multi-scale encoding module 150 is configured to arrange the heating temperature values at the plurality of predetermined time points into the heating temperature input vector according to the time dimension, and then obtain the heating temperature feature vector through the multi-scale neighborhood feature extraction module. According to the technical scheme of the application, the heating temperature values at the preset time points are arranged into heating temperature input vectors according to the time dimension and then pass through the multi-scale domain feature extraction module to obtain heating temperature feature vectors. That is, the heating temperature values at the plurality of predetermined time points are first vectorized to obtain a heating temperature input vector, that is, a time-series distribution of the heating temperature values. And then, carrying out multi-scale one-dimensional convolution coding on the heating temperature input vector by using a multi-scale neighborhood feature extraction module comprising a plurality of parallel one-dimensional convolution layers so as to capture high-dimensional implicit features among different numbers of heating temperature values in different time spans, and carrying out feature fusion on associated features of different scales so as to obtain the heating temperature feature vector.

Fig. 5 is a block diagram of a multi-scale coding module in a disposable paper cup manufacturing apparatus according to an embodiment of the present application. As shown in fig. 5, the multi-scale encoding module 150 includes: a first scale feature extraction unit 151, configured to input the heating temperature input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first scale heating temperature feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length; a second scale feature extraction unit 152, configured to input the heating temperature input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second scale heating temperature feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and a class probability combining unit 153, configured to perform a class probability simultaneous projection between each sub-dimension based on a feature set on the first-scale heating temperature feature vector and the second-scale heating temperature feature vector to obtain the heating temperature feature vector.

Specifically, in the embodiment of the present application, the multi-scale encoding module 150 is configured to: performing one-dimensional convolution coding on the heating temperature input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following first convolution formula to obtain a first-scale heating temperature feature vector; wherein the first convolution formula is:

wherein a is the width of the first convolution kernel in the X direction, F (a) is a first convolution kernel parameter vector, G (X-a) is a local vector matrix calculated by a convolution kernel function, w is the size of the first convolution kernel, X represents the heating temperature input vector, and Cov (X) is the convolution processing of the heating temperature input vector; the inputting the heating temperature input vector into the second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale heating temperature feature vector includes: performing one-dimensional convolution coding on the heating temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following second convolution formula to obtain a second-scale heating temperature feature vector; wherein the second convolution formula is:

Fig. 6 is a block diagram of a class probability association unit in a disposable paper cup manufacturing apparatus according to an embodiment of the present application. As shown in fig. 6, the class probability combining unit 153 includes: a covariance subunit 1531 for calculating a covariance matrix between the first-scale heating temperature feature vector and the second-scale heating temperature feature vector; a decomposition subunit 1532, configured to decompose eigenvalues of the covariance matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors corresponding to the eigenvalues; a main feature extraction subunit 1533, configured to extract feature vectors corresponding to the first two feature values from the plurality of feature vectors to obtain a first main feature vector and a second main feature vector; a pre-classification subunit 1534, configured to pass the first principal eigenvector and the second principal eigenvector through a pre-classifier to obtain a first probability value and a second probability value, respectively; and a weighted bitwise sub-unit 1535 for calculating a weighted sum of the first scale heating temperature feature vector and the second scale heating temperature feature vector with the first probability value and the second probability value as weights to obtain a heating temperature feature vector.

In the above-described disposable paper cup manufacturing apparatus 100, the responsiveness estimation module 160 is configured to calculate a responsiveness estimation of the disposable paper cup state change feature vector with respect to the heating temperature feature vector to obtain a classification feature matrix. In the technical scheme of the application, the heating temperature is the cause of the state change of the disposable paper cup method, that is, the heating temperature and the state change of the disposable paper cup have a correlation on a logic level, and the classification characteristic representation comprising the heating temperature characteristic and the state change characteristic of the disposable paper cup is obtained by utilizing the logic correlation between the heating temperature and the state change of the disposable paper cup. Specifically, a responsiveness estimate of the disposable cup state change feature vector relative to the heating temperature feature vector is calculated to obtain a classification feature matrix.

Specifically, in the embodiment of the present application, the responsiveness estimation module 160 is configured to: calculating a responsiveness estimate of the disposable cup state change feature vector relative to the heating temperature feature vector with a responsiveness estimate formula to obtain a classification feature matrix; wherein, the responsiveness estimation formula is:

In the above-described disposable paper cup manufacturing apparatus 100, the detection result generation module 170 is configured to pass the classification feature matrix through a classifier to obtain a classification result indicating that the heating temperature at the current time point should be increased or decreased.

Specifically, in the embodiment of the present application, the detection result generating module 170 is configured to: expanding the classification feature matrix into classification feature vectors according to row vectors or column vectors; performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.

Exemplary method

Fig. 7 illustrates a flow chart of a method of producing a disposable paper cup according to an embodiment of the present application. As shown in fig. 7, the method for producing a disposable paper cup according to an embodiment of the present application includes the steps of: s110, acquiring a monitoring video of a disposable paper cup in a preset time period and heating temperature values of a plurality of preset time points in the preset time period; s120, extracting a plurality of disposable paper cup monitoring key frames from the disposable paper cup monitoring video of the preset time period; s130, passing the plurality of disposable paper cup monitoring key frames through a first convolution neural network model comprising a depth fusion module to obtain a plurality of disposable paper cup monitoring feature matrixes; s140, aggregating the plurality of disposable paper cup monitoring feature matrixes into a three-dimensional feature tensor along a sample dimension, and obtaining a state change feature vector of the disposable paper cup through a second convolution neural network model using a three-dimensional convolution kernel; s150, arranging the heating temperature values of the plurality of preset time points into heating temperature input vectors according to time dimensions, and then obtaining heating temperature feature vectors through a multi-scale neighborhood feature extraction module; s160, calculating the response estimation of the state change feature vector of the disposable paper cup relative to the heating temperature feature vector to obtain a classification feature matrix; and S170, passing the classification feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the heating temperature at the current time point is increased or reduced.

Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described disposable paper cup manufacturing method have been described in detail in the above description of the disposable paper cup manufacturing apparatus with reference to fig. 1 to 6, and thus, repetitive descriptions thereof will be omitted.

As described above, the paper cup manufacturing apparatus 100 according to the embodiment of the present application can be implemented in various terminal apparatuses, such as a paper cup manufacturing server, etc. In one example, the disposable paper cup manufacturing device 100 according to embodiments of the present application may be integrated into the terminal device as one software module and/or hardware module. For example, the disposable paper cup manufacturing device 100 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 disposable paper cup manufacturing apparatus 100 may also be one of the plurality of hardware modules of the terminal device.

Alternatively, in another example, the disposable paper cup manufacturing device 100 and the terminal device may be separate devices, and the disposable paper cup manufacturing device 100 may be connected to the terminal device through a wired and/or wireless network, and transmit interactive information in a prescribed data format

Exemplary electronic device

Next, an electronic device according to an embodiment of the present application is described with reference to fig. 8. Fig. 8 illustrates a block diagram of an electronic device according to an embodiment of the present application. As shown in fig. 8, the electronic device 10 includes one or more processors 11 and a memory 12.

The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by processor 11 to perform the functions in the methods of producing disposable paper cups of the various embodiments of the present application described above and/or other desired functions. Various contents such as a heating temperature, a change in the state of the disposable cup, and the like may also be stored in the computer-readable storage medium.

In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).

The input means 13 may comprise, for example, a keyboard, a mouse, etc.

The output device 14 may output various information to the outside, including that the heating temperature at the current time point should be increased or should be decreased, and the like. The output means 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.

Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 8 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.

The basic principles of the present application have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not intended to be limited to the details disclosed herein as such.

The block diagrams of the devices, apparatuses, devices, systems referred to in this application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.

It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent to 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, this description is not intended to limit the embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims

1. A disposable paper cup manufacturing apparatus comprising:

2. The disposable paper cup manufacturing apparatus of claim 1, wherein the sampling module is configured to: the plurality of throw-away monitoring key frames are extracted from the throw-away monitoring video for the predetermined period of time at a predetermined sampling frequency.

3. The throw-away paper cup manufacturing apparatus of claim 2, wherein the shade feature encoding module comprises:

4. The throw-away paper cup manufacturing apparatus of claim 3, wherein the three-dimensional convolutional encoding module comprises:

5. The throw-away paper cup manufacturing apparatus of claim 4, wherein the three-dimensional convolutional encoding module is configured to:

6. The throw-away paper cup manufacturing apparatus of claim 5, wherein the multi-scale encoding module comprises:

7. The throw-away paper cup manufacturing apparatus of claim 6, wherein the multi-scale encoding module is configured to: performing one-dimensional convolution coding on the heating temperature input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following first convolution formula to obtain a first-scale heating temperature feature vector;

wherein the first convolution formula is:

the heating temperature input vector is input into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second-scale heating temperature feature vector, and the second-scale heating temperature feature vector is used for: performing one-dimensional convolution coding on the heating temperature input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following second convolution formula to obtain a second-scale heating temperature feature vector;

Wherein the second convolution formula is:

8. The throw-away paper cup producing apparatus of claim 7, wherein the probabilistic association unit includes:

9. The disposable paper cup manufacturing apparatus of claim 8, wherein said responsiveness estimation module is configured to:

wherein, the responsiveness estimation formula is:

10. A method of producing a disposable paper cup comprising: