Automatic sole pressing control method of intelligent shoe production line and production line thereof

Abstract

The present invention relates to the field of shoemaking process technology, and in particular to an automatic sole pressing control method for an intelligent shoemaking production line and its production line. An automatic sole pressing control method for an intelligent shoemaking production line includes S1, data entry; S2, collecting single shoe data; S3, clustering processing; S4, multi-version application; S5, production line application. The present invention records the historical data of shoes of each version in the production line, adds a pressure sensor in the shoe last and sets a pressure threshold, so as to determine the elongation of each sole pressing component during the pressing of the shoe, in order to standardize the pressing data of shoes of the same version and size, after collecting multiple groups of historical data, a clustering algorithm is performed to select the most appropriate pressing data as a unified standard, thereby avoiding the disadvantage that the pressing effect of each pair of shoes depends entirely on manual judgment during the mass production process, improving production efficiency and liberating labor.

Description

Technical Field

[0001] The present invention relates to the technical field of shoemaking technology, and in particular to an automatic sole pressing control method of an intelligent shoemaking production line and a production line thereof. Background Art

[0002] Most of the existing shoe sole pressing work is still mainly manual, with low production efficiency. At the same time, during the process of gluing and pressing the soles, harmful substances in the glue will be inhaled by employees, causing harm to their bodies. During the pressing process, employees are required to operate the pressing device skillfully, and the slightest carelessness will cause harm to their hands. The pressing process is also the process with the highest injury rate in the entire shoemaking process. The purpose is to replace the traditional manual pressing steps with the automatic pressing device in the intelligent shoemaking production line, but how to achieve accurate pressing of shoes and form unified and standardized operation data has become a problem. Summary of the invention

[0003] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description and other drawings of the description.

[0004] The purpose of the present invention is to overcome the above-mentioned shortcomings and provide an automatic sole pressing control method for an intelligent shoemaking production line and a production line thereof. By recording the historical data of shoes of various types in the production line, a pressure sensor is added to the shoe last and a pressure threshold is set, so as to determine the elongation of each sole pressing component in the process of pressing the shoes. In order to standardize the pressing data of shoes of the same type and size, after collecting multiple groups of historical data, a clustering algorithm is performed to select the most appropriate pressing data as a unified standard, thereby avoiding the disadvantage that the pressing effect of each pair of shoes in the batch production process depends entirely on manual judgment, thereby improving production efficiency and liberating labor.

[0005] The present invention provides an automatic sole pressing control method for an intelligent shoe production line, comprising:

[0006] S1. Data entry: The producer statistically classifies the shoe patterns that need to be pressed in the intelligent production line, and enters the information of each shoe pattern into the production line terminal;

[0007] S2. Collecting data of a single shoe: The sole pressing device is provided with several retractable sole pressing components. The shoe to be pressed is filled with a shoe last to ensure the stability of the shoe shape during the sole pressing process. A pressure sensor is added to the shoe last. A pressure threshold is set for the pressure sensor. The sole pressing process of a single shoe is recorded. A set of data is generated according to the name of each sole pressing component, the elongation of the sole pressing component and the sole pressing time.

[0008] S3, clustering processing: batch pressing of the shoes of the pattern in step S2, and performing K-means clustering algorithm on the production data of the pattern and batch of shoes, setting the cluster center with the same number of shoe sizes as the batch, clustering the production data into multiple clusters according to the shoe size, calculating the cluster center of each cluster, finding the nearest point to the cluster center, and setting the data of the nearest point as the unified pressing data of the shoes of the pattern and size, and storing it at the production line terminal;

[0009] S4, multi-version application: after obtaining the sole pressing data of multiple sizes of shoes of one version, repeat the steps of S2-S3, perform clustering operation on shoes of multiple versions, form batch sole pressing data and save it to the production line terminal;

[0010] S5. Production line application: A camera is installed at the entrance of the intelligent shoemaking production line to classify the shoes entering the intelligent shoemaking production line. After identifying the shoe style and size, the bottom pressing data stored in the production line terminal is called out, and the robot arm is controlled to grab the shoes into the bottom pressing device. The bottom pressing device controls the bottom pressing component to automatically press the bottom of the shoe.

[0011] In some embodiments, in step S2, when the end of the bottom pressing component contacts the shoe, the bottom pressing component begins to press the shoe. During the contact process, the bottom pressing component continues to extend until the pressure sensor in the shoe last detects that the pressure threshold is reached. After continuous pressure is applied for a certain period of time, the bottom pressing process is completed, the bottom pressing component retracts, and the next bottom pressing action is performed.

[0012] In some embodiments, during the routine pressing process of the same type of shoes, the names of the pressing components and the pressing time in the data group will not change, but will be set by the manufacturer. The only change is the elongation of the pressing components, which is obtained through a clustering algorithm. If the pressing effect of the shoes does not meet the standards, the pressing effect can be improved by changing the pressing time or re-clustering the shoes of this type to change the elongation of the pressing components.

[0013] In some embodiments, in step S3, for shoes of this version with different sizes, the change value of the elongation of the sole component in the data group is large, and for shoes of this version with the same size, the change value of the elongation of the sole component in the data group is small, so that multiple clusters can be generated according to size.

[0014] In some embodiments, the bottom pressing component may be offset due to frictional heat during operation, thereby reducing the pressing effect. In order to compensate for the error, an S6 error prediction step is added: first, a long short-term memory network model is established to obtain the operating speed, operating time and operating distance of each bottom pressing component under multiple temperature conditions, and the long short-term memory network model is trained to obtain a mature long short-term memory network model. The long short-term memory network model is input into the production line terminal. In actual application, the current bottom pressing component temperature is obtained in real time through calculation and input into the model to obtain the predicted offset.

[0015] In some embodiments, an error compensation step S7 is included: after obtaining the predicted offset, it is combined with the unified sole pressing data of the shoe of the same type and size obtained in step S4 to adjust the elongation of the sole pressing component for error compensation.

[0016] In some embodiments, the long short-term memory network model includes: an input gate, an output gate, a forget gate and a memory cell, and an LSTM unit consists of a memory cell and three gate structures.

[0017] In some embodiments, in step S6, a control variable method is used to control the reciprocating motion of each bottom pressure component at different operating speeds and different operating times, and segmented measurement points are preset to collect temperature changes and three-dimensional errors at different segmented points. By monitoring the expansion and deformation of each bottom pressure component, the temperature of the bottom pressure component can be inferred. Since there is a proportional relationship between the temperature of the bottom pressure component and the expansion and deformation, the current temperature of the bottom pressure component can be obtained through the expansion and deformation, thereby obtaining the current temperature of each bottom pressure component in real time at the production line terminal.

[0018] An intelligent shoemaking production line comprises a production line provided with a movable mechanical arm, a camera arranged at the entrance of the production line, and a plurality of sole pressing devices evenly distributed on both sides of the production line, wherein the sole pressing device is provided with a shoe-shaped groove and a plurality of sole pressing components arranged around the groove, and the sole pressing component comprises a driving motor and a telescopic rod.

[0019] By adopting the above technical solution, the beneficial effects of the present invention are:

[0020] The present invention records the historical data of shoes of various types in the production line, adds a pressure sensor in the shoe last and sets a pressure threshold, so as to determine the elongation of each bottom pressing component in the process of pressing the shoe. In order to standardize the pressing data of shoes of the same type and size, after collecting multiple groups of historical data, a clustering algorithm is performed to select the most appropriate pressing data as a unified standard, thereby avoiding the disadvantage that the pressing effect of each pair of shoes in the batch production process depends entirely on manual judgment, thereby improving production efficiency and liberating labor.

[0021] The present invention is also provided with an error compensation step. During the operation of the bottom pressing component, the temperature will gradually rise with time, and the originally set elongation will also be offset. After the current temperature is determined by the current operating state, the temperature is input into a mature long short-term memory network model to obtain a predicted offset, which is combined with the unified bottom pressing data set in the terminal to achieve error compensation.

[0022] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0023] Undoubtedly, these and other objects of the present invention will become more apparent after the following detailed description of the preferred embodiment described with reference to various figures and drawings.

[0024] In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, one or several preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation of the present invention.

[0026] In the drawings, the same reference numerals are used for the same components and the drawings are schematic and not necessarily drawn to scale.

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only one or several embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on such drawings without paying creative work.

[0028] Figure 1 It is a schematic diagram of the overall flow of the automatic bottom pressing control method in some embodiments of the present invention;

[0029] Figure 2 is a schematic diagram of an error compensation process in some embodiments of the present invention;

[0030] Figure 3 It is a schematic diagram of the overall structure of the intelligent production line in some embodiments of the present invention;

[0031] Figure 4 It is a schematic diagram of the overall structure of the bottom pressing device in some embodiments of the present invention.

[0032] Description of main reference numerals:

[0033] 1. Production line;

[0034] 2. Robotic arm;

[0035] 3. Bottom pressing device;

[0036] 31. groove; 32. bottom pressing part. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but are not used to limit the present invention.

[0038] In addition, in the description of the present invention, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0039] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral body; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. However, if it is indicated as a direct connection, it means that the two connected bodies are not connected through a transition structure, but are connected to form a whole through a connecting structure. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0040] In the present invention, unless otherwise clearly specified and limited, the first feature "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in an appropriate manner in any one or more embodiments or examples.

[0041] Reference Figure 1 and Figure 3 , Figure 1 It is a schematic diagram of the overall flow of the automatic bottom pressing control method in some embodiments of the present invention; Figure 3 The figure is a schematic diagram of the overall structure of the intelligent production line in some embodiments of the present invention.

[0042] According to some embodiments of the present invention, the present invention provides an automatic sole pressing control method for an intelligent shoe production line, comprising:

[0043] S1. Data entry: The producer statistically classifies the shoe patterns that need to be pressed in the intelligent production line, and enters the information of each shoe pattern into the production line terminal;

[0044] S2, collect data of a single shoe: Figure 4 As shown, Figure 4 The schematic diagram of the overall structure of the sole pressing device in some embodiments of the present invention is shown in FIG. 3 . The sole pressing device 3 is provided with several retractable sole pressing components. The shoe to be sole pressed is filled with a shoe last to ensure the stability of the shoe shape during the sole pressing process. A pressure sensor is added to the shoe last. A pressure threshold is set for the pressure sensor. The sole pressing process of a single shoe is recorded. A set of data groups is generated according to the name of each sole pressing component, the elongation of the sole pressing component and the sole pressing time.

[0045] When the end of the bottom pressing component contacts the shoe, the bottom pressing component starts to press the shoe. During the contact process, the bottom pressing component continues to extend until the pressure sensor in the shoe last detects that the pressure threshold has been reached. After a certain period of continuous pressure application, the bottom pressing process is completed, the bottom pressing component retracts, and the next bottom pressing action is performed.

[0046] In the actual process of batch sole pressing of shoes, each pair of shoes will be filled with a shoe last. However, the cost of adding a pressure sensor in each shoe last is too high. Therefore, batch sole pressing cannot be achieved by simply setting a pressure sensor in each shoe last and setting a pressure threshold. The present invention forms unified data by conducting experiments on a small number of shoes (compared to actual batch production) in advance and collecting data.

[0047] S3, clustering processing: batch pressing of the shoes of the pattern in step S2, and performing K-means clustering algorithm on the production data of the pattern and batch of shoes, setting the cluster center with the same number of shoe sizes as the batch, clustering the production data into multiple clusters according to the shoe size, calculating the cluster center of each cluster, finding the nearest point to the cluster center, and setting the data of the nearest point as the unified pressing data of the shoes of the pattern and size, and storing it at the production line terminal;

[0048] For shoes of this type with different sizes, the elongation change value of the bottom pressing component in the data group is large, and for shoes of this type with the same size, the elongation change value of the bottom pressing component in the data group is small, so that multiple clusters can be generated according to the size;

[0049] In the process of conventionally pressing shoes of the same type, the names and pressing times of the pressing components in the data group will not change, and are set by the manufacturer. The only change is the elongation of the pressing components, which is obtained through a clustering algorithm. If the pressing effect of the shoes does not meet the standard, the pressing effect can be improved by changing the pressing time or re-clustering the shoes of this type to change the elongation of the pressing components.

[0050] S4, multi-version application: after obtaining the sole pressing data of multiple sizes of shoes of one version, repeat the steps of S2-S3, perform clustering operation on shoes of multiple versions, form batch sole pressing data and save it to the production line terminal;

[0051] S5. Production line application: A camera is set at the entrance of the intelligent shoemaking production line to classify the shoes entering the intelligent shoemaking production line. After identifying the shoe style and size, the bottom pressing data stored in the production line terminal is called out, and the robot arm 2 is controlled to grab the shoes into the bottom pressing device 3. The bottom pressing device 3 controls the bottom pressing component to automatically press the bottom of the shoe.

[0052] like Figure 2 As shown, Figure 2 The figure is a schematic diagram of the error compensation process in some embodiments of the present invention. During operation, the bottom pressing component may be offset due to frictional heat, thereby reducing the pressing effect. In order to perform error compensation, an S6 error prediction step is added: first, a long short-term memory network model is established to obtain the operating speed, operating time and operating distance of each bottom pressing component under multiple temperature conditions, the long short-term memory network model is trained to obtain a mature long short-term memory network model, and the long short-term memory network model is input into the production line terminal. In actual application, the current bottom pressing component temperature is obtained in real time through calculation and input into the model to obtain the predicted offset.

[0053] The long short-term memory network model includes: an input gate, an output gate, a forget gate and a memory cell. An LSTM unit consists of a memory cell and three gate structures.

[0054] The control variable method is adopted to control the reciprocating motion of each bottom pressure component at different operating speeds and different operating times. The segmented measurement points are preset, and the temperature changes and three-dimensional errors at different segmented points are collected. By monitoring the expansion and deformation of each bottom pressure component, the temperature of the bottom pressure component can be calculated. Since there is a proportional relationship between the temperature of the bottom pressure component and the expansion and deformation, the current temperature of the bottom pressure component can be obtained through the expansion and deformation, so as to obtain the current temperature of each bottom pressure component in real time at the production line terminal.

[0055] S7 error compensation step: after obtaining the predicted offset, it is combined with the unified sole pressing data of the shoe of the same type and size obtained in step S4 to adjust the elongation of the sole pressing component for error compensation.

[0056] The present invention also includes an intelligent shoemaking production line, which includes a production line 1 provided with a movable mechanical arm 2, a camera arranged at the entrance of the production line 1, and several bottom pressing devices 3 evenly distributed on both sides of the production line 1, wherein the bottom pressing device 3 is provided with a shoe-shaped groove 31 and several bottom pressing components 32 arranged around the groove 31, and the bottom pressing component includes a driving motor and a telescopic rod.

[0057] It should be understood that the embodiments disclosed in the present invention are not limited to the specific processing steps or materials disclosed herein, but should be extended to equivalent substitutions of such features understood by ordinary technicians in the relevant field. It should also be understood that the terms used herein are only used for the purpose of describing specific embodiments and are not meant to be limiting.

[0058] The "embodiment" mentioned in the specification means that the specific features or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. Therefore, the phrases or "embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment.

[0059] In addition, the described features or characteristics may be combined in one or more embodiments in any other suitable manner. In the above description, some specific details, such as thickness, quantity, etc., are provided to provide a comprehensive understanding of the embodiments of the present invention. However, those skilled in the relevant art will understand that the present invention can be implemented without one or more of the above specific details or can also be implemented using other methods, components, materials, etc.

Claims

1. An automatic sole pressing control method for an intelligent shoe production line, characterized in that: include: S1. Data entry: The producer statistically classifies the shoe patterns that need to be pressed in the intelligent production line, and enters the information of each shoe pattern into the production line terminal; S2. Collecting data of a single shoe: The sole pressing device is provided with several retractable sole pressing components. The shoe to be pressed is filled with a shoe last to ensure the stability of the shoe shape during the sole pressing process. A pressure sensor is added to the shoe last. A pressure threshold is set for the pressure sensor. The sole pressing process of a single shoe is recorded. A set of data is generated according to the name of each sole pressing component, the elongation of the sole pressing component and the sole pressing time. S3, clustering processing: batch pressing of the shoes of the pattern in step S2, and performing K-means clustering algorithm on the production data of the pattern and batch of shoes, setting the cluster center with the same number of shoe sizes as the batch, clustering the production data into multiple clusters according to the shoe size, calculating the cluster center of each cluster, finding the nearest point to the cluster center, and setting the data of the nearest point as the unified pressing data of the shoes of the pattern and size, and storing it at the production line terminal; S4, multi-version application: after obtaining the sole pressing data of multiple sizes of shoes of one version, repeat the steps of S2-S3, perform clustering operation on shoes of multiple versions, form batch sole pressing data and save it to the production line terminal; S5. Production line application: A camera is set at the entrance of the intelligent shoe production line to classify the shoes entering the intelligent shoe production line. After identifying the shoe version and size, the bottom pressing data stored in the production line terminal is called out, and the robot arm is controlled to grab the shoes into the bottom pressing device. The bottom pressing device controls the bottom pressing component to automatically press the bottom of the shoes. The bottom pressing component will be offset due to friction and heat during operation, thereby reducing the pressing effect. In order to compensate for the error, an S6 error prediction step is added: first, a long short-term memory network model is established to obtain the operating speed, operating time and operating distance of each bottom pressing component under multiple temperature conditions, and the long short-term memory network model is trained to obtain a mature long short-term memory network model. The long short-term memory network model is input into the production line terminal. In actual application, the current bottom pressing component temperature is obtained in real time through calculation and input into the model to obtain the predicted offset.

2. The automatic sole pressing control method of the intelligent shoe production line according to claim 1 is characterized in that: In step S2, when the end of the bottom pressing component contacts the shoe, it starts to press the bottom. During the contact process, the bottom pressing component continues to extend until the pressure sensor in the shoe last detects that the pressure threshold has been reached. After continuous pressure for a certain period of time, the bottom pressing process is completed, the bottom pressing component retracts, and the next bottom pressing action is performed.

3. The automatic sole pressing control method of the intelligent shoe production line according to claim 1 is characterized in that: In the process of conventionally pressing shoes of the same type, the names and pressing times of the pressing components in the data group will not change, and are set by the manufacturer. The only change is the elongation of the pressing components, which is obtained through a clustering algorithm. If the pressing effect of the shoes does not meet the standard, the pressing effect can be improved by changing the pressing time or re-clustering the shoes of this type to change the elongation of the pressing components.

4. The automatic sole pressing control method of the intelligent shoe production line according to claim 1 is characterized in that: In step S3, for shoes of this version with different sizes, the elongation change value of the sole component in the data group is large, and for shoes of this version with the same size, the elongation change value of the sole component in the data group is small, so that multiple clusters can be generated according to size.

5. The automatic sole pressing control method of the intelligent shoe production line according to claim 1 is characterized in that: The method comprises an error compensation step S7: after obtaining the predicted offset, combining it with the unified sole pressing data of the shoe of the same type and size obtained in step S4 to adjust the elongation of the sole pressing component for error compensation.

6. The automatic sole pressing control method of the intelligent shoe production line according to claim 1 is characterized in that: The long short-term memory network model includes: an input gate, an output gate, a forget gate and a memory cell. An LSTM unit consists of a memory cell and three gate structures.

7. The automatic sole pressing control method of the intelligent shoe production line according to claim 1 is characterized in that: In step S6, the control variable method is used to control the reciprocating motion of each bottom pressure component at different operating speeds and different operating times. The segmented measurement points are preset, and the temperature changes and three-dimensional errors at different segmented points are collected. By monitoring the expansion and deformation of each bottom pressure component, the temperature of the bottom pressure component can be calculated. Since there is a proportional relationship between the temperature of the bottom pressure component and the expansion and deformation, the current temperature of the bottom pressure component can be obtained through the expansion and deformation, thereby obtaining the current temperature of each bottom pressure component in real time at the production line terminal.

8. An intelligent shoe production line, characterized in that: The intelligent shoemaking production line is controlled by the automatic sole pressing control method of any one of claims 1 to 7, the intelligent shoemaking production line includes a production line provided with a movable robotic arm, a camera arranged at the entrance of the production line, and a plurality of sole pressing devices evenly distributed on both sides of the production line, the sole pressing device is provided with a shoe-shaped groove and a plurality of sole pressing components arranged around the groove, the sole pressing component including a driving motor and a telescopic rod.

Images