Method and system for automatic bottle unscrambling of filling machine for special-shaped bottles

Through industrial cameras and intelligent positioning technology, the problems of inaccurate positioning and inefficiency of special-shaped bottles are solved, and efficient and accurate positioning of special-shaped bottles and automatic stabilization of bottles are achieved, which improves filling production efficiency and product quality.

CN118701686BActive Publication Date: 2024-12-06PERWIN SCI & TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411178423.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-06
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

The existing filling and bottle care methods are inaccurate in positioning the special-shaped bottles and are inefficient, which leads to bottle body contamination and cannot meet the needs of modern filling production lines.

Method used

Using industrial cameras to capture and extract the image of special-shaped bottles and combine the automatic bottle feeding mechanism and filling machine to configure the positioner to achieve efficient and accurate positioning of special-shaped bottles through intelligent positioning technology, optimize bottle control parameters, and avoid bottle mucus contamination. .

Benefits of technology

It realizes efficient and precise positioning and automatic stabilization of special-shaped bottles, improves filling production efficiency and product quality, and is suitable for special-shaped bottles of various shapes and sizes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118701686B_ABST
    Figure CN118701686B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for automatic bottle unscrambling of a filling machine for special-shaped bottles, and relates to the field of packaging control technology. The method comprises: searching and matching based on a multi-dimensional appearance feature set of special-shaped bottles and a control data set of special-shaped bottles, determining bottle feeding control parameters to feed the target special-shaped bottles into the filling machine, configuring a locator for the filling machine to obtain the current spatial image information of the target special-shaped bottles, performing feature loss analysis on the preset special-shaped bottle spatial image and the current spatial image information, obtaining the spatial position information of the special-shaped bottles, and performing filling analysis based on this, and determining the target filling control parameter set to perform filling and bottle unscrambling feedback control on the target special-shaped bottles. The method achieves efficient and accurate positioning of special-shaped bottles through intelligent positioning technology, optimizes bottle unscrambling control parameters, avoids the problem of mucus contamination of the bottle body, is applicable to special-shaped bottles of various shapes and sizes, ensures automatic and stable bottle unscrambling during filling, and thus improves the filling production efficiency and product quality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of packaging control, and in particular to a method and system for automatically unscrambling bottles of a filling machine for special-shaped bottles. Background Art

[0002] With the rapid development of the packaging industry, special-shaped bottles have been widely used in the market due to their unique appearance and good visual effects. In the pharmaceutical industry, the packaging application of special-shaped bottles is also an indispensable part. Due to the particularity of the pharmaceutical industry, these bottles need to meet specific packaging, storage and transportation requirements to ensure the quality and safety of drugs. However, due to the non-standard shape of special-shaped bottles, the existing filling and bottle sorting methods have problems such as inaccurate positioning, low efficiency, and bottle contamination, which cannot meet the needs of modern filling production lines. Summary of the invention

[0003] The present application provides a method and system for automatic bottle unscrambling of a filling machine for special-shaped bottles, thereby solving the technical problems of inaccurate positioning, low efficiency, bottle body contamination and inability to meet the needs of modern filling production lines in the prior art filling and bottle unscrambling methods. The application achieves efficient and accurate positioning of special-shaped bottles through intelligent positioning technology, optimizes bottle unscrambling control parameters, avoids the problem of mucus contamination of the bottle body, is suitable for special-shaped bottles of various shapes and sizes, ensures automatic and stable bottle unscrambling during filling, and thus improves the filling production efficiency and product quality.

[0004] In view of the above problems, the present invention provides a method and system for automatically unscrambling bottles in a filling machine for special-shaped bottles.

[0005] In a first aspect, the present application provides a method for automatic bottle unscrambling of a filling machine for special-shaped bottles, the method comprising: S1: arranging an industrial camera in an automatic bottle feeding mechanism, using the industrial camera to capture an image of a target special-shaped bottle, obtaining target appearance image information, performing convolution feature extraction on the target appearance image information, and obtaining a multi-dimensional appearance feature set of the special-shaped bottle, wherein the multi-dimensional appearance feature set of the special-shaped bottle includes appearance size, shape and position; S2: acquiring a control data set of the special-shaped bottle of the automatic bottle feeding mechanism, performing retrieval matching based on the multi-dimensional appearance feature set of the special-shaped bottle and the control data set of the special-shaped bottle, determining a bottle feeding control parameter, and the automatic The bottle feeding mechanism feeds the target special-shaped bottle into the filling machine based on the bottle feeding control parameters; S3: determining a preset special-shaped bottle spatial image according to the target appearance image information analysis, configuring a locator for the filling machine, acquiring the current spatial image information of the target special-shaped bottle through the locator, performing feature loss analysis on the preset special-shaped bottle spatial image and the current spatial image information, and obtaining the special-shaped bottle spatial posture information; S4: performing filling analysis on the special-shaped bottle spatial posture information, determining a target filling control parameter set, and using an assisted positioning device to perform filling and bottle unscrambling feedback control on the target special-shaped bottle based on the target filling control parameter set.

[0006] On the other hand, the present application also provides a system for automatically unscrambling bottles in a filling machine for special-shaped bottles, the system comprising: a special-shaped bottle feature acquisition module, which is used to set an industrial camera in an automatic bottle feeding mechanism, use the industrial camera to capture images of target special-shaped bottles, obtain target appearance image information, perform convolution feature extraction on the target appearance image information, and obtain a multi-dimensional appearance feature set of special-shaped bottles, wherein the multi-dimensional appearance feature set of special-shaped bottles includes appearance size, shape and position; a bottle feeding control parameter determination module, which is used to collect and obtain a special-shaped bottle control data set of the automatic bottle feeding mechanism, perform retrieval and matching based on the multi-dimensional appearance feature set of special-shaped bottles and the special-shaped bottle control data set, and determine the bottle feeding control parameters, wherein the multi-dimensional appearance feature set of special-shaped bottles and the multi-dimensional appearance feature set of special-shaped bottles are extracted from the special-shaped bottle control data set. The automatic bottle feeding mechanism feeds the target special-shaped bottle into the filling machine based on the bottle feeding control parameters; the feature loss analysis module is used to determine the preset special-shaped bottle spatial image according to the target appearance image information analysis, configure a locator for the filling machine, collect and obtain the current spatial image information of the target special-shaped bottle through the locator, perform feature loss analysis on the preset special-shaped bottle spatial image and the current spatial image information, and obtain the special-shaped bottle spatial posture information; the bottle unscrambling feedback control module is used to perform filling analysis on the special-shaped bottle spatial posture information, determine the target filling control parameter set, and use an assisted positioning device to perform filling and bottle unscrambling feedback control on the target special-shaped bottle based on the target filling control parameter set.

[0007] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0008] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] Due to the use of an industrial camera set in the automatic bottle feeding mechanism, the industrial camera is used to capture the image and extract convolution features of the target special-shaped bottle, obtain the multi-dimensional appearance feature set of the special-shaped bottle, retrieve and match the special-shaped bottle control data set based on the special-shaped bottle multi-dimensional appearance feature set, determine the bottle feeding control parameters, the automatic bottle feeding mechanism sends the target special-shaped bottle into the filling machine based on the bottle feeding control parameters, configure the filling machine with a locator, collect and obtain the current spatial image information of the target special-shaped bottle through the locator, perform feature loss analysis on the preset special-shaped bottle spatial image and the current spatial image information, obtain the spatial posture information of the special-shaped bottle, perform filling analysis, determine the target filling control parameter set, and use the auxiliary positioning device to perform filling and bottle unscrambling feedback control on the target special-shaped bottle based on the target filling control parameter set. The technical solution achieves efficient and accurate positioning of special-shaped bottles through intelligent positioning technology, optimizes bottle unscrambling control parameters, avoids the problem of bottle body mucus contamination, is suitable for special-shaped bottles of various shapes and sizes, ensures automatic and stable bottle unscrambling during filling, and thus improves the filling production efficiency and product quality.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a schematic flow chart of a method for automatically unscrambling bottles in a filling machine for special-shaped bottles in this application;

[0013] Figure 2 A schematic diagram of a flow chart for determining bottle feeding control parameters in a method for automatic bottle unscrambling of a filling machine for special-shaped bottles in the present application;

[0014] Figure 3This is a schematic diagram of the structure of the automatic bottle unscrambling system of the filling machine for special-shaped bottles in this application;

[0015] Figure 4 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0016] Explanation of reference numerals: special-shaped bottle feature acquisition module 11, bottle feeding control parameter determination module 12, feature loss analysis module 13, bottle sorting feedback control module 14, bus 1110, processor 1120, transceiver 1130, bus interface 1140, memory 1150, operating system 1151, application program 1152 and user interface 1160. DETAILED DESCRIPTION

[0017] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0018] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0019] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0020] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0021] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0022] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0023] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0024] The present application is described below in conjunction with the drawings in the present application.

[0025] Embodiment 1

[0026] like Figure 1 As shown, the present application provides a method for automatically unscrambling bottles of a filling machine for special-shaped bottles, the method comprising:

[0027] Step S1: an industrial camera is arranged in the automatic bottle feeding mechanism, and an image of a target irregular-shaped bottle is captured by the industrial camera to obtain target appearance image information, and convolution feature extraction is performed on the target appearance image information to obtain a multi-dimensional appearance feature set of the irregular-shaped bottle, wherein the multi-dimensional appearance feature set of the irregular-shaped bottle includes appearance size, shape and position;

[0028] Specifically, in order to realize the intelligent positioning control of special-shaped bottles, an industrial camera is set in the automatic bottle feeding mechanism to collect and identify images of special-shaped bottles, wherein the automatic bottle feeding mechanism may be a conveyor belt, a vibration plate or other suitable feeding mechanism, and its design can ensure that the bottles move forward smoothly and orderly. The special-shaped bottles are placed at the input end of the automatic bottle feeding mechanism, and the industrial camera is used to capture the image of the target special-shaped bottles to obtain the target appearance image information, which is a high-precision appearance image of the target special-shaped bottle. The target appearance image information is subjected to convolution feature extraction by a convolutional neural network to obtain a multi-dimensional appearance feature set of the special-shaped bottles, which includes key feature information such as the appearance size, shape and position of the target special-shaped bottles. The appearance feature basis is provided for the subsequent adjustment of the parameters of the automatic bottle feeding mechanism to identify and adapt to special-shaped bottles of different shapes, thereby ensuring that the special-shaped bottles can smoothly enter the filling machine.

[0029] Step S2: acquiring a control data set of special-shaped bottles of the automatic bottle feeding mechanism, searching and matching the control data set of special-shaped bottles based on the multi-dimensional appearance feature set of the special-shaped bottles, and determining bottle feeding control parameters, and the automatic bottle feeding mechanism feeds the target special-shaped bottles into the filling machine based on the bottle feeding control parameters;

[0030] Furthermore, the bottle feeding control parameters are determined in S2, and the steps of the present application also include:

[0031] S21: extracting and marking the appearance features of each control data in the special-shaped bottle control data set to obtain the special-shaped bottle appearance feature control data set;

[0032] S22: performing similarity analysis on the multi-dimensional appearance feature set of the special-shaped bottle and the control data set of appearance features of the special-shaped bottle to obtain a special-shaped bottle appearance similarity set;

[0033] S23: performing optimal reverse matching on the appearance similarity set of the irregular-shaped bottles to obtain matching control parameters, and determining the appearance deviation parameters of the irregular-shaped bottles according to the matching control parameters;

[0034] S24: Adaptively adjusting the matching control parameter based on the appearance deviation parameter of the special-shaped bottle to determine the bottle feeding control parameter.

[0035] Specifically, by collecting the historical control parameter records of the automatic bottle feeding mechanism, the corresponding special-shaped bottle control data set is obtained, and the special-shaped bottle control data set includes historical special-shaped bottle multi-dimensional appearance feature data and the corresponding automatic bottle feeding mechanism control parameter set. Based on the special-shaped bottle multi-dimensional appearance feature set and the special-shaped bottle control data set, the special-shaped bottle appearance feature is first extracted and marked for each control data in the special-shaped bottle control data set, and the special-shaped bottle appearance feature control data set after feature marking is obtained. Then, the cosine similarity algorithm is used to perform similarity analysis on the special-shaped bottle multi-dimensional appearance feature set and each control data in the special-shaped bottle appearance feature control data set, and the calculated special-shaped bottle appearance similarity set is obtained, which is used for the rapid matching of bottle feeding control parameters.

[0036] The appearance similarity set of the shaped bottles is optimized to obtain the appearance feature data of the shaped bottle with the greatest similarity and perform reverse matching to obtain the matching control parameters corresponding to the similarity, wherein the matching control parameters include the applicable bottle diameter, conveyor belt speed, vibration plate frequency, etc. The appearance deviation parameter of the shaped bottle is determined according to the matching control parameters, wherein the appearance deviation parameter of the shaped bottle is the deviation value between the appearance of the matched shaped bottle and the appearance of the target shaped bottle, such as the bottle body size deviation. The matching control parameters are adaptively adjusted based on the shaped bottle appearance deviation parameters through bottle feeding control experience. For example, the applicable bottle diameter of the automatic bottle feeding mechanism is adjusted for deviation compensation according to the shaped bottle size deviation to determine the optimized bottle feeding control parameters. The automatic bottle feeding mechanism feeds the target shaped bottle into the filling machine based on the bottle feeding control parameters, thereby realizing precise control of the applicability of the bottle feeding mechanism to be applicable to shaped bottles of various shapes and sizes, thereby ensuring that the bottle can smoothly enter the filling machine.

[0037] Step S3: determining a preset shaped bottle spatial image according to the target appearance image information, configuring a locator for the filling machine, acquiring current spatial image information of the target shaped bottle through the locator, performing feature loss analysis on the preset shaped bottle spatial image and the current spatial image information, and obtaining spatial pose information of the shaped bottle;

[0038] like Figure 2 As shown, further, the spatial position information of the special-shaped bottle is obtained in S3, and the steps of this application also include:

[0039] S31: Building a feature twin network, wherein the feature twin network includes a preset twin sub-network and a target twin sub-network, and the preset twin sub-network and the target twin sub-network are shared weight networks;

[0040] S32: Based on the preset twin network and the target twin network, feature extraction processing is performed on the preset special-shaped bottle space image and the current space image information respectively, and a preset special-shaped bottle feature set and a target special-shaped bottle feature set are output;

[0041] S33: performing loss analysis on the preset special-shaped bottle feature set and the target special-shaped bottle feature set using a feature loss function to obtain special-shaped bottle position loss data;

[0042] S34: performing deviation correction analysis based on the special-shaped bottle posture loss data to obtain the special-shaped bottle spatial posture information.

[0043] Specifically, a preset shaped bottle spatial image is determined based on the target appearance image information analysis. The preset shaped bottle spatial image is a standard shaped bottle spatial image set according to the appearance characteristics of the shaped bottle and the filling procedure, including the appearance size, shape and preset filling position of the shaped bottle. To ensure the filling effect, the target shaped bottle must meet the preset shaped bottle spatial image. The filling machine is equipped with a locator, which is a device specially designed to accurately identify and locate the position and posture of the bottle. When the shaped bottle is fed into the filling machine by the automatic bottle feeding mechanism, it will reach the detection area of ​​the locator, and the current spatial image information of the target shaped bottle is collected and acquired through the locator. Feature loss analysis is performed on the preset shaped bottle spatial image and the current spatial image information. By comparing the current actual image with the preset shaped bottle spatial image, the precise position and posture of the shaped bottle can be accurately located.

[0044] The specific process of image feature loss analysis is as follows: first, a feature twin network is built. The feature twin network is a network structure formed by comparing the similarity of two image samples and splicing weight-sharing neural networks. It specifically includes a preset twin network and a target twin network. The preset twin network and the target twin network are shared weight networks, that is, the preset twin network and the target twin network have the same network structure, which is a convolutional neural network, and the data processing method steps are also the same, which are used to extract the appearance features and spatial position features of special-shaped bottles. Based on the preset twin network, feature extraction processing is performed on the preset special-shaped bottle spatial image, and a preset special-shaped bottle feature set is output, including the appearance features and spatial position features of the preset special-shaped bottle spatial image. At the same time, feature extraction processing is performed on the current spatial image information based on the target twin network, and a target special-shaped bottle feature set is output, including the appearance features and spatial position features of the current spatial image information.

[0045] The feature loss function is used to perform loss analysis on the preset special-shaped bottle feature set and the target special-shaped bottle feature set, wherein the feature loss function can be a weighted function of the convolution feature comparison value, that is, the convolution feature comparison difference of the two image sample feature data is averaged and weighted, and the calculation result is used as the special-shaped bottle posture loss data. Deviation correction analysis is performed based on the special-shaped bottle posture loss data, that is, the actual posture correction is performed on the spatial position and appearance posture deviation data of the target special-shaped bottle that does not meet the standard, and the corrected special-shaped bottle spatial posture information is obtained. Through the rapid comparison and analysis of the special-shaped bottle posture loss features, efficient and accurate positioning of the special-shaped bottle is achieved, and the filling loss caused by inaccurate positioning is reduced, so as to improve the accuracy of subsequent filling control parameters and filling efficiency.

[0046] Step S4: performing filling analysis on the spatial position information of the special-shaped bottle, determining a target filling control parameter set, and using an assisted positioning device to perform filling and bottle unscrambling feedback control on the target special-shaped bottle based on the target filling control parameter set.

[0047] Furthermore, the target filling control parameter set is determined in S4, and the steps of this application also include:

[0048] S41: extracting influencing factors of the filling nozzle of the filling machine to obtain influencing factor information of the filling nozzle, wherein the influencing factor information of the filling nozzle includes liquid properties, nozzle design and liquid filling temperature;

[0049] S42: Acquire a filling machine control database, perform clustering division based on the filling nozzle influencing factor information and the filling machine control space, and generate a filling machine factor clustering control database;

[0050] S43: Acquire the filling element attribute information of the target special-shaped bottle, perform mapping and matching with the filling machine element clustering control database based on the filling element attribute information, and construct a filling machine control space;

[0051] S44: performing an association optimization analysis in the filling machine control space based on the spatial position information of the special-shaped bottle to determine the target filling control parameter set.

[0052] Furthermore, the target filling control parameter set is determined in S44, and the steps of the present application further include:

[0053] Extracting effect indicators from the filling machine control space to obtain a filling control effect indicator set, and generating a filling control effect fitness evaluation function by fitting the filling control effect indicator set;

[0054] Based on the correlation similarity analysis between the spatial position information of the special-shaped bottle and the control space of the filling machine, a filling control parameter selection threshold is obtained;

[0055] Randomly generating a plurality of filling control parameter sets according to the filling control parameter selection threshold, and evaluating and calculating the plurality of filling control parameter sets by the filling control effect fitness evaluation function to obtain a plurality of filling control effect fitnesses;

[0056] The plurality of filling control parameter sets are clustered and divided for optimization based on the plurality of filling control effect fitnesses to determine the target filling control parameter set.

[0057] Furthermore, the step of determining the target filling control parameter set in this application further includes:

[0058] Performing clustering ratio division on the multiple filling control parameter sets according to the multiple filling control effect fitnesses to determine multiple filling control parameter clusters;

[0059] Constructing a learning factor, and performing control parameter learning and updating in the plurality of filling control parameter clusters based on the learning factor until a preset convergence requirement is met, thereby obtaining a plurality of filling control optimization parameter clusters;

[0060] The fitness sum of the plurality of filling control optimization parameter set clusters is calculated, and based on the fitness sum, parameter cluster comparison and optimization are performed to obtain a filling control optimization parameter library, and the target filling control parameter set is preferentially determined according to the filling control optimization parameter library.

[0061] Specifically, a filling analysis is performed on the spatial posture information of the special-shaped bottle. First, the influencing factors of the filling nozzle of the filling machine are extracted to obtain the influencing factor information of the filling nozzle. The influencing factor information of the filling nozzle is the influencing factor of the filling effect of the special-shaped bottle, including liquid properties. The physical properties of the filling liquid, such as viscosity, density, surface tension, etc., will directly affect the performance of the filling nozzle; nozzle design. The diameter, length, shape and internal structure of the filling nozzle will affect its filling effect; liquid filling temperature. The temperature of the filling liquid will also affect its flow performance in the nozzle. For example, high-temperature liquid may cause the nozzle material to expand and deform, while low-temperature liquid may cause the liquid to condense or clog in the nozzle.

[0062] The filling machine control database is acquired through big data technology, and the filling machine control database includes historical filling machine influencing factor data, shaped bottle spatial posture data, and corresponding filling control parameters and filling effect data. Based on the filling nozzle influencing factor information and the filling machine control space, clustering is performed, that is, the control data in the filling machine control space is classified according to the filling nozzle influencing factor information, and then the control data of the same factor category after division are integrated into one category to generate an integrated filling machine element clustering control database. The filling element attribute information of the target shaped bottle is obtained through the production management system, and the filling element attribute information includes liquid properties, nozzle design, and liquid filling temperature. Based on the mapping and matching of the filling element attribute information and the filling machine element clustering control database, the control data in the filling machine element clustering control database that is similar to the filling element attribute information is screened to construct the filling machine control space, and the filling machine control space is used as the optimization range of the filling control parameters of the target shaped bottle to reduce the parameter optimization range and improve the parameter optimization efficiency.

[0063] Based on the spatial position information of the special-shaped bottle, an associated optimization analysis is performed in the control space of the filling machine. First, the filling effect data in the control space of the filling machine are extracted to obtain a filling control effect index set, which is used to evaluate the filling effect of the special-shaped bottle, including filling accuracy, leakage rate, filling cost consumption, etc. The filling control data in the control space of the filling machine are evaluated and fitted by the filling control effect index set to generate a filling control effect fitness evaluation function, which is used to evaluate the filling effect of the filling control parameters. The greater the fitness, the better the filling effect of the filling control parameters. Based on the spatial position information of the special-shaped bottle and the control space of the filling machine, an associated similarity analysis is performed to obtain a filling control parameter selection threshold in the control space of the filling machine that is similar to the spatial position information of the special-shaped bottle. The filling control parameter selection threshold is the value range of filling control parameters such as the filling nozzle angle, filling speed, and filling flow.

[0064] According to the filling control parameter selection threshold, a plurality of filling control parameter sets are randomly generated, and the plurality of filling control parameter sets are evaluated and calculated by the filling control effect fitness evaluation function to obtain a plurality of corresponding filling control effect fitnesses. Based on the plurality of filling control effect fitnesses, the plurality of filling control parameter sets are clustered and divided for optimization. First, the plurality of filling control parameter sets are clustered and divided in proportion by the plurality of filling control effect fitnesses, and a preset number of filling control parameter sets with the best filling control effect fitnesses are selected as cluster centers. The remaining filling control parameter sets are proportionally allocated according to the filling control effect fitnesses of the cluster center parameters to determine the corresponding plurality of filling control parameter set clusters. A learning factor is constructed, where the learning factor is the optimization update step size of each filling control parameter in the filling control parameter cluster, and based on the learning factor, each filling control parameter is optimized and learned and updated toward the cluster center control parameter in the multiple filling control parameter clusters, and the updated filling control parameter with the best fitness is replaced as the cluster center until a preset convergence requirement is met, such as reaching a preset number of optimization updates, to obtain multiple filling control optimization parameter clusters after optimization and update.

[0065] The fitness sum of the multiple filling control optimization parameter clusters is calculated, and based on the fitness sum, parameter clusters are compared and optimized to obtain the parameter cluster with the largest fitness sum as the filling control optimization parameter library, which includes the optimal filling control parameters and the remaining suboptimal filling control parameters in the cluster. According to the filling control optimization parameter library, the optimal filling control parameters are preferably determined as the target filling control parameter set, and an assisted positioning device is used to perform filling and bottle unscrambling feedback control on the target special-shaped bottle based on the target filling control parameter set, wherein the assisted positioning device is an auxiliary device for positioning and fixing the target special-shaped bottle, and through the precise positioning function, it is ensured that the filling machine nozzle can be accurately and stably inserted into the special-shaped bottle for filling control. Efficient and precise positioning of special-shaped bottles is achieved, and bottle unscrambling control parameters are optimized, the problem of mucus contamination of the bottle body is avoided, and automatic and stable bottle unscrambling is ensured during filling, thereby improving filling production efficiency and product quality.

[0066] Furthermore, the application steps also include:

[0067] Control and monitor the filling state of the target special-shaped bottle to obtain the special-shaped bottle filling feedback parameter; if the special-shaped bottle filling feedback parameter does not reach the preset filling effect, perform abnormal identification on the special-shaped bottle filling feedback parameter to obtain the filling abnormality characteristic parameter;

[0068] Determine a bottle unscrambling adjustment strategy according to the filling abnormality characteristic parameters, and set parameter variation rules according to the bottle unscrambling adjustment strategy;

[0069] The filling control optimization parameter library is mutated and updated based on the parameter variation rule, and parameter optimization analysis is performed through the updated filling control optimization parameter library.

[0070] Specifically, after the nozzle is inserted into the bottle mouth, the control system will start the filling program. To ensure the filling effect of the special-shaped bottle, the filling status of the target special-shaped bottle is controlled and monitored to obtain the special-shaped bottle filling feedback parameters, which include the special-shaped bottle filling effect information and the special-shaped bottle status information. If the special-shaped bottle filling feedback parameters do not reach the preset filling effect, the special-shaped bottle filling feedback parameters are abnormally identified to obtain filling abnormality characteristic parameters, which are the filling abnormality state characteristics of the special-shaped bottle, such as bottle tilt, filling dirt, etc. The bottle unscrambling adjustment strategy is determined according to the filling abnormality characteristic parameters. The bottle unscrambling adjustment strategy is a bottle unscrambling scheme that matches the filling abnormality characteristic parameters. For example, if the special-shaped bottles are not arranged neatly or are dirty, corresponding position or flow adjustment operations will be performed.

[0071] According to the bottle unscrambling adjustment strategy, parameter variation rules are set, and the parameter variation rules are the basis for optimizing and adjusting the filling control parameters. For example, the filling nozzle angle and the filling flow parameters are preset to reduce the parameter adjustment of the variation direction. Based on the parameter variation rules, each filling control parameter in the filling control optimization parameter library is mutated and updated, and the parameter optimization analysis is performed through the updated filling control optimization parameter library to determine the optimal filling effect parameter as the current filling control parameter to adapt to the bottle unscrambling operation under the current abnormal filling state. Improve the filling control accuracy of special-shaped bottles, ensure automatic and stable bottle unscrambling, and thus improve the filling production efficiency and product quality.

[0072] In summary, the method and system for automatic bottle unscrambling of a filling machine for special-shaped bottles provided in the present application have the following technical effects:

[0073] Due to the use of an industrial camera set in the automatic bottle feeding mechanism, the industrial camera is used to capture the image and extract convolution features of the target special-shaped bottle, obtain the multi-dimensional appearance feature set of the special-shaped bottle, retrieve and match the special-shaped bottle control data set based on the special-shaped bottle multi-dimensional appearance feature set, determine the bottle feeding control parameters, the automatic bottle feeding mechanism sends the target special-shaped bottle into the filling machine based on the bottle feeding control parameters, configure the filling machine with a locator, collect and obtain the current spatial image information of the target special-shaped bottle through the locator, perform feature loss analysis on the preset special-shaped bottle spatial image and the current spatial image information, obtain the spatial posture information of the special-shaped bottle, perform filling analysis, determine the target filling control parameter set, and use the auxiliary positioning device to perform filling and bottle unscrambling feedback control on the target special-shaped bottle based on the target filling control parameter set. The technical solution achieves efficient and accurate positioning of special-shaped bottles through intelligent positioning technology, optimizes bottle unscrambling control parameters, avoids the problem of bottle body mucus contamination, is suitable for special-shaped bottles of various shapes and sizes, ensures automatic and stable bottle unscrambling during filling, and thus improves the filling production efficiency and product quality.

[0074] Embodiment 2

[0075] Based on the same inventive concept as the method for automatic bottle unscrambling of a filling machine for special-shaped bottles in the aforementioned embodiment, the present invention also provides a system for automatic bottle unscrambling of a filling machine for special-shaped bottles, such as Figure 3 As shown, the system comprises:

[0076] The special-shaped bottle feature acquisition module 11 is used to set an industrial camera in the automatic bottle feeding mechanism, use the industrial camera to capture the image of the target special-shaped bottle, obtain the target appearance image information, perform convolution feature extraction on the target appearance image information, and obtain a multi-dimensional appearance feature set of the special-shaped bottle, wherein the multi-dimensional appearance feature set of the special-shaped bottle includes appearance size, shape and position;

[0077] A bottle feeding control parameter determination module 12 is used to collect and obtain a control data set of special-shaped bottles of the automatic bottle feeding mechanism, perform retrieval and matching based on the multi-dimensional appearance feature set of the special-shaped bottles and the control data set of the special-shaped bottles, and determine the bottle feeding control parameters. The automatic bottle feeding mechanism feeds the target special-shaped bottles into the filling machine based on the bottle feeding control parameters;

[0078] The feature loss analysis module 13 is used to determine a preset shaped bottle spatial image according to the target appearance image information, configure a locator for the filling machine, acquire the current spatial image information of the target shaped bottle through the locator, perform feature loss analysis on the preset shaped bottle spatial image and the current spatial image information, and obtain the spatial pose information of the shaped bottle;

[0079] The bottle unscrambling feedback control module 14 is used to perform filling analysis on the spatial position information of the special-shaped bottle, determine a target filling control parameter set, and use an assisted positioning device to perform filling and bottle unscrambling feedback control on the target special-shaped bottle based on the target filling control parameter set.

[0080] Furthermore, the system also includes:

[0081] A feature extraction and identification unit, used for performing appearance feature extraction and identification on each control data in the special-shaped bottle control data set to obtain a special-shaped bottle appearance feature control data set;

[0082] A similarity analysis unit, used for performing similarity analysis on the multi-dimensional appearance feature set of the special-shaped bottle and the control data set of appearance feature of the special-shaped bottle to obtain a similarity set of appearance of the special-shaped bottle;

[0083] A deviation parameter determination unit, configured to perform optimal reverse matching on the appearance similarity set of the irregular-shaped bottles to obtain matching control parameters, and determine the appearance deviation parameters of the irregular-shaped bottles according to the matching control parameters;

[0084] The adaptive adjustment unit is used to adaptively adjust the matching control parameter based on the appearance deviation parameter of the special-shaped bottle to determine the bottle feeding control parameter.

[0085] Furthermore, the system also includes:

[0086] A feature twin network building unit, used to build a feature twin network, wherein the feature twin network includes a preset twin sub-network and a target twin sub-network, and the preset twin sub-network and the target twin sub-network are shared weight networks;

[0087] A feature extraction processing unit, used for performing feature extraction processing on the preset special-shaped bottle space image and the current space image information respectively based on the preset twin network and the target twin network, and outputting a preset special-shaped bottle feature set and a target special-shaped bottle feature set;

[0088] A feature set loss analysis unit, used to perform loss analysis on the preset special-shaped bottle feature set and the target special-shaped bottle feature set using a feature loss function to obtain special-shaped bottle pose loss data;

[0089] The deviation correction analysis unit is used to perform deviation correction analysis based on the special-shaped bottle posture loss data to obtain the special-shaped bottle spatial posture information.

[0090] Furthermore, the system also includes:

[0091] An influencing factor extraction unit is used to extract influencing factors of a filling nozzle of the filling machine to obtain influencing factor information of the filling nozzle, wherein the influencing factor information of the filling nozzle includes liquid properties, nozzle design and liquid filling temperature;

[0092] A spatial clustering division unit, used for collecting and acquiring a filling machine control database, performing clustering division based on the filling nozzle influencing factor information and the filling machine control space, and generating a filling machine factor clustering control database;

[0093] A control space construction unit, used for acquiring filling element attribute information of the target special-shaped bottle, mapping and matching the filling element attribute information with the filling machine element clustering control database, and constructing a filling machine control space;

[0094] The associated optimization analysis unit is used to perform associated optimization analysis in the control space of the filling machine based on the spatial posture information of the special-shaped bottle to determine the target filling control parameter set.

[0095] Furthermore, the system also includes:

[0096] An effect index extraction unit, used for extracting effect indexes from the filling machine control space to obtain a filling control effect index set, and generating a filling control effect fitness evaluation function by fitting the filling control effect index set;

[0097] An association similarity analysis unit, used to perform association similarity analysis based on the spatial position information of the special-shaped bottle and the control space of the filling machine to obtain a filling control parameter selection threshold;

[0098] A parameter effect evaluation calculation unit, used for randomly generating a plurality of filling control parameter sets according to the filling control parameter selection threshold, and evaluating and calculating the plurality of filling control parameter sets through the filling control effect fitness evaluation function to obtain a plurality of filling control effect fitnesses;

[0099] The clustering and optimization unit is used to perform clustering and optimization on the multiple filling control parameter sets based on the multiple filling control effect fitnesses to determine the target filling control parameter set.

[0100] Furthermore, the system also includes:

[0101] A clustering ratio division unit, configured to perform clustering ratio division on the plurality of filling control parameter sets according to the plurality of filling control effect fitnesses, and determine a plurality of filling control parameter clusters;

[0102] A parameter learning and updating unit, used for constructing a learning factor, and performing control parameter learning and updating in the plurality of filling control parameter clusters based on the learning factor until a preset convergence requirement is met, thereby obtaining a plurality of filling control optimization parameter clusters;

[0103] The parameter cluster comparison and optimization unit is used to calculate the fitness sum of the multiple filling control optimization parameter set clusters, and perform parameter cluster comparison and optimization based on the fitness sum to obtain a filling control optimization parameter library, and preferably determine the target filling control parameter set based on the filling control optimization parameter library.

[0104] Furthermore, the system also includes:

[0105] A characteristic abnormality identification unit is used to control and monitor the filling state of the target special-shaped bottle, obtain the filling feedback parameters of the special-shaped bottle, and if the filling feedback parameters of the special-shaped bottle do not reach the preset filling effect, identify the abnormality of the filling feedback parameters of the special-shaped bottle to obtain the filling abnormality characteristic parameters;

[0106] A variation rule setting unit, used for determining a bottle unscrambling adjustment strategy according to the filling abnormality characteristic parameters, and setting a parameter variation rule according to the bottle unscrambling adjustment strategy;

[0107] The parameter optimization analysis unit is used to mutate and update the filling control optimization parameter library based on the parameter variation rule, and perform parameter optimization analysis through the updated filling control optimization parameter library.

[0108] The foregoing Figure 1 The various variations and specific examples of the method for automatic bottle unscrambling of a filling machine for special-shaped bottles in the first embodiment are also applicable to the system for automatic bottle unscrambling of a filling machine for special-shaped bottles in the present embodiment. Through the above detailed description of the method for automatic bottle unscrambling of a filling machine for special-shaped bottles, those skilled in the art can clearly understand the implementation method of the system for automatic bottle unscrambling of a filling machine for special-shaped bottles in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0109] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and run on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method embodiment for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0110] Exemplary Electronic Devices

[0111] For details, see Figure 4As shown, the present application also provides an electronic device, which includes a bus 1110 , a processor 1120 , a transceiver 1130 , a bus interface 1140 , a memory 1150 and a user interface 1160 .

[0112] In the present application, the electronic device further includes: a computer program stored in the memory 1150 and executable on the processor 1120, and when the computer program is executed by the processor 1120, each process of the above-mentioned method embodiment for controlling output data is implemented.

[0113] The transceiver 1130 is configured to receive and send data under the control of the processor 1120 .

[0114] In the present application, a bus architecture (represented by bus 1110 ) may include any number of interconnected buses and bridges. Bus 1110 connects various circuits including one or more processors represented by processor 1120 and a memory represented by memory 1150 .

[0115] Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. Such architectures include, by way of example and not limitation, an Industry Standard Architecture bus, a Micro Channel Architecture bus, an expansion bus, a Video Electronics Standards Association, a Peripheral Component Interconnect bus.

[0116] The processor 1120 may be an integrated circuit chip having signal processing capabilities. In the implementation process, each step of the above method embodiment may be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processors include: a general-purpose processor, a central processing unit, a network processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, a complex programmable logic device, a programmable logic array, a microcontroller unit or other programmable logic device, a discrete gate, a transistor logic device, and a discrete hardware component. The various methods, steps, and logic block diagrams disclosed in this application may be implemented or executed. For example, the processor may be a single-core processor or a multi-core processor, and the processor may be integrated into a single chip or located on multiple different chips.

[0117] Processor 1120 may be a microprocessor or any conventional processor. The method steps disclosed in the present application may be directly executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a readable storage medium known in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, a register, etc. The readable storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0118] The bus 1110 may also connect various other circuits such as peripheral devices, voltage regulators or power management circuits, and the bus interface 1140 provides an interface between the bus 1110 and the transceiver 1130, which are well known in the art. Therefore, this application will not further describe them.

[0119] The transceiver 1130 may be one element or multiple elements, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on a transmission medium. For example, the transceiver 1130 receives external data from other devices, and the transceiver 1130 is used to send data processed by the processor 1120 to other devices. Depending on the nature of the computer device, a user interface 1160 may also be provided, such as a touch screen, a physical keyboard, a display, a mouse, a speaker, a microphone, a trackball, a joystick, or a stylus.

[0120] It should be understood that in the present application, the memory 1150 may further include a memory remotely arranged relative to the processor 1120, and these remotely arranged memories may be connected to the server through a network. One or more parts of the above network may be a self-organizing network, an intranet, an extranet, a virtual private network, a local area network, a wireless local area network, a wide area network, a wireless wide area network, a metropolitan area network, the Internet, a public switched telephone network, a plain old telephone service network, a cellular telephone network, a wireless network, a wireless fidelity network, and a combination of two or more of the above networks. For example, the cellular telephone network and the wireless network may be a global mobile communication device, a code division multiple access device, a global microwave interconnection access device, a general packet radio service device, a wideband code division multiple access device, a long term evolution device, a LTE frequency division duplex device, a LTE time division duplex device, an advanced long term evolution device, a universal mobile communication device, an enhanced mobile broadband device, a massive machine type communication device, an ultra-reliable low latency communication device, and the like.

[0121] It should be understood that the memory 1150 in the present application may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory includes: a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory.

[0122] Volatile memory includes random access memory, which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronously linked dynamic random access memory, and direct memory bus random access memory. The memory 1150 of the electronic device described in the present application includes, but is not limited to, the above and any other suitable types of memory.

[0123] In the present application, the memory 1150 stores the following elements of the operating system 1151 and the application program 1152: executable modules, data structures, or subsets thereof, or extended sets thereof.

[0124] Specifically, the operating system 1151 includes various device programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 1152 includes various application programs, such as a media player and a browser, which are used to implement various application services. The program implementing the method of the present application may be included in the application 1152. The application 1152 includes applets, objects, components, logic, data structures, and other computer device executable instructions that perform specific tasks or implement specific abstract data types.

[0125] In addition, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned method embodiment for controlling output data are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0126] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for automatically unscrambling bottles in a filling machine for special-shaped bottles, characterized in that: The method comprises: S1: an industrial camera is arranged in the automatic bottle feeding mechanism, and an image of a target irregular-shaped bottle is captured by the industrial camera to obtain target appearance image information, and convolution feature extraction is performed on the target appearance image information to obtain a multi-dimensional appearance feature set of the irregular-shaped bottle, wherein the multi-dimensional appearance feature set of the irregular-shaped bottle includes appearance size, shape and position; S2: Acquire the control data set of the special-shaped bottles of the automatic bottle feeding mechanism, perform retrieval and matching based on the multi-dimensional appearance feature set of the special-shaped bottles and the control data set of the special-shaped bottles, determine the bottle feeding control parameters, and the automatic bottle feeding mechanism feeds the target special-shaped bottles into the filling machine based on the bottle feeding control parameters; S3: determining a preset shaped bottle spatial image according to the target appearance image information, configuring a locator for the filling machine, acquiring current spatial image information of the target shaped bottle through the locator, performing feature loss analysis on the preset shaped bottle spatial image and the current spatial image information, and obtaining spatial pose information of the shaped bottle; S4: Perform filling analysis on the spatial position information of the special-shaped bottle, determine a target filling control parameter set, and use an assisted positioning device to perform filling and bottle unscrambling feedback control on the target special-shaped bottle based on the target filling control parameter set; The bottle feeding control parameters are determined in S2, including: S21: extracting and marking the appearance features of each control data in the special-shaped bottle control data set to obtain the special-shaped bottle appearance feature control data set; S22: performing similarity analysis on the multi-dimensional appearance feature set of the special-shaped bottle and the control data set of appearance features of the special-shaped bottle to obtain a special-shaped bottle appearance similarity set; S23: performing optimal reverse matching on the appearance similarity set of the irregular-shaped bottles to obtain matching control parameters, and determining the appearance deviation parameters of the irregular-shaped bottles according to the matching control parameters; S24: Adaptively adjusting the matching control parameter based on the appearance deviation parameter of the special-shaped bottle to determine the bottle feeding control parameter; The spatial position information of the special-shaped bottle is obtained in S3, including: S31: Building a feature twin network, wherein the feature twin network includes a preset twin sub-network and a target twin sub-network, and the preset twin sub-network and the target twin sub-network are shared weight networks; S32: Based on the preset twin network and the target twin network, feature extraction processing is performed on the preset special-shaped bottle space image and the current space image information respectively, and a preset special-shaped bottle feature set and a target special-shaped bottle feature set are output; S33: performing loss analysis on the preset special-shaped bottle feature set and the target special-shaped bottle feature set using a feature loss function to obtain special-shaped bottle position loss data; S34: performing deviation correction analysis based on the special-shaped bottle posture loss data to obtain the special-shaped bottle spatial posture information; Determining the target filling control parameter set in S4 includes: S41: extracting influencing factors of the filling nozzle of the filling machine to obtain influencing factor information of the filling nozzle, wherein the influencing factor information of the filling nozzle includes liquid properties, nozzle design and liquid filling temperature; S42: Acquire a filling machine control database, perform clustering division based on the filling nozzle influencing factor information and the filling machine control space, and generate a filling machine factor clustering control database; S43: Acquire the filling element attribute information of the target special-shaped bottle, perform mapping and matching with the filling machine element clustering control database based on the filling element attribute information, and construct a filling machine control space; S44: performing an association optimization analysis in the filling machine control space based on the spatial position information of the special-shaped bottle to determine the target filling control parameter set.

2. The method according to claim 1, characterized in that Determining the target filling control parameter set in S44 includes: Extracting effect indicators from the filling machine control space to obtain a filling control effect indicator set, and generating a filling control effect fitness evaluation function by fitting the filling control effect indicator set; Based on the correlation similarity analysis between the spatial position information of the special-shaped bottle and the control space of the filling machine, a filling control parameter selection threshold is obtained; Randomly generating a plurality of filling control parameter sets according to the filling control parameter selection threshold, and evaluating and calculating the plurality of filling control parameter sets by the filling control effect fitness evaluation function to obtain a plurality of filling control effect fitnesses; The plurality of filling control parameter sets are clustered and divided for optimization based on the plurality of filling control effect fitnesses to determine the target filling control parameter set.

3. The method according to claim 2, characterized in that Determining the target filling control parameter set includes: Performing clustering ratio division on the multiple filling control parameter sets according to the multiple filling control effect fitnesses to determine multiple filling control parameter clusters; Constructing a learning factor, and performing control parameter learning and updating in the plurality of filling control parameter clusters based on the learning factor until a preset convergence requirement is met, thereby obtaining a plurality of filling control optimization parameter clusters; The fitness sum of the plurality of filling control optimization parameter set clusters is calculated, and based on the fitness sum, parameter cluster comparison and optimization are performed to obtain a filling control optimization parameter library, and the target filling control parameter set is preferentially determined according to the filling control optimization parameter library.

4. The method according to claim 3, characterized in that The method comprises: Control and monitor the filling state of the target special-shaped bottle to obtain the special-shaped bottle filling feedback parameter; if the special-shaped bottle filling feedback parameter does not reach the preset filling effect, perform abnormal identification on the special-shaped bottle filling feedback parameter to obtain the filling abnormality characteristic parameter; Determine a bottle unscrambling adjustment strategy according to the filling abnormality characteristic parameters, and set parameter variation rules according to the bottle unscrambling adjustment strategy; The filling control optimization parameter library is mutated and updated based on the parameter variation rule, and parameter optimization analysis is performed through the updated filling control optimization parameter library.

5. Automatic bottle unscrambling system for filling machines of special-shaped bottles, characterized in that: A method for automatically unscrambling bottles in a filling machine for special-shaped bottles according to any one of claims 1 to 4, the system comprising: The module for obtaining the feature of the shaped bottle is used to set an industrial camera in the automatic bottle feeding mechanism, use the industrial camera to capture the image of the target shaped bottle, obtain the target appearance image information, perform convolution feature extraction on the target appearance image information, and obtain a multi-dimensional appearance feature set of the shaped bottle, wherein the multi-dimensional appearance feature set of the shaped bottle includes appearance size, shape and position; A bottle feeding control parameter determination module is used to collect and obtain the special-shaped bottle control data set of the automatic bottle feeding mechanism, perform retrieval and matching based on the special-shaped bottle multi-dimensional appearance feature set and the special-shaped bottle control data set, and determine the bottle feeding control parameters. The automatic bottle feeding mechanism feeds the target special-shaped bottle into the filling machine based on the bottle feeding control parameters; A feature loss analysis module is used to determine a preset shaped bottle spatial image according to the target appearance image information, configure a locator for the filling machine, collect and obtain the current spatial image information of the target shaped bottle through the locator, perform feature loss analysis on the preset shaped bottle spatial image and the current spatial image information, and obtain the spatial pose information of the shaped bottle; The bottle unscrambling feedback control module is used to perform filling analysis on the spatial posture information of the special-shaped bottle, determine a target filling control parameter set, and use an assisted positioning device to perform filling and bottle unscrambling feedback control on the target special-shaped bottle based on the target filling control parameter set.

6. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the method for automatic bottle unscrambling of a filling machine for special-shaped bottles according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method for automatic bottle unscrambling of a filling machine for special-shaped bottles according to any one of claims 1 to 4 are implemented.

Citation Information

Patent Citations

  • Linear rotation and correction type directed feeding device for special-shaped bottle

    CN104150423A

  • Full-automatic bottle arranging device and method

    CN105083952A

  • High-speed bottle arrangement device

    CN108609372A

  • Special-shaped bottle shape capturing method and equipment based on industrial digital printing and storage medium

    CN118189852A

  • Method and instrument for measuring three-dimensional shape, and program

    JP2003269928A