An online monitoring system for milk powder bar production process

Abstract

The application discloses an online monitoring system for milk powder strip production process, belongs to the online monitoring field, and comprises a raw material marking module, a metering and weighing module, a raw material proportioning and coordinating processing module, an airtightness detection module and a visual processing module. The application integrates advanced online monitoring device technology and an intelligent control system, solves the problems of inaccurate length and weight control, insufficient packaging sealing detection, production adjustment lag, and lack of real-time data acquisition and tracing in the prior art. The application aims to realize accurate monitoring and automatic adjustment of the milk powder strip production process, ensure the consistency of product quality and the improvement of production efficiency, and provide the production line with quick response and flexible customization capabilities.

Description

Technical Field

[0001] This invention belongs to the field of online monitoring, and in particular relates to an online monitoring system for the production process of milk powder strips. Background Technology

[0002] As a highly portable dairy product with standardized dosage, milk powder bars are experiencing increasing market demand. The production and packaging process of milk powder bars involves multiple stages, including powder filling, bar cutting, sealing, and finished product testing. The quality of these stages directly determines the product's appearance, performance, and shelf life. However, existing milk powder bar packaging processes have several problems, such as inconsistent bar length and weight, packaging sealing issues, and insufficient real-time monitoring and data traceability capabilities.

[0003] Most existing technical solutions optimize a single process step and fail to comprehensively consider all key factors in the production of milk powder bars, such as length, weight, packaging sealing, and real-time monitoring and data traceability during production. Therefore, existing technical solutions have significant limitations in improving production efficiency and quality stability. Summary of the Invention

[0004] To solve the above-mentioned technical problems, the present invention provides an online monitoring system for the production process of milk powder strips, comprising:

[0005] The raw material marking module is used to mark the raw materials before milk powder bars are canned, so as to obtain the marked raw materials;

[0006] The metering and weighing module is used to measure the marked raw materials to obtain the metered raw materials;

[0007] The raw material proportioning and coordination processing module is used to perform partitioned filling of the metered raw materials to obtain the filled raw materials.

[0008] An airtightness testing module is used to test the airtightness of the filled raw materials before and after roll film packaging.

[0009] The vision processing module is used to acquire image information of all processes based on a CCD industrial camera and build a neural network model. The image information is then input into the neural network model for calculation to obtain monitoring results.

[0010] Preferably, the weighing module is further used to: weigh the raw materials; if the weight of each raw material exceeds a set normal threshold, it is determined that there is a quality problem with the current milk powder strip ratio, so that the current raw materials continue to enter the raw material ratio coordination and processing module through the rotating worktable, and the raw material ratio is readjusted by the raw material ratio coordination and processing module to enter the next round of raw material ratio.

[0011] Preferably, the airtightness detection module includes:

[0012] The pre-packaging inspection unit is used to test the airtightness of the roll film;

[0013] The post-packaging testing unit is used to monitor the airtightness of the packaged raw materials.

[0014] Preferably, the pre-packaging inspection unit includes: a vent and a container;

[0015] The operation of the pre-packaging detection unit includes: blowing uniform gas through the vent hole onto the surface of the roll film, and placing a container filled with water on the other side of the roll film surface. If air bubbles appear in the water in the container, it is determined that the roll film has leaked air.

[0016] Preferably, the operation of the packaging detection unit includes: using a push rod to squeeze the outer packaging of the milk powder strip after the roll film is packaged; while squeezing the outer packaging of the milk powder strip, using a CCD industrial camera to acquire the deformation of the strip shape of the milk powder strip outer packaging, generating a deformation image; calculating the deformation image through an image processing algorithm to obtain the edge deformation process; and obtaining the roll film detection result based on the edge deformation process.

[0017] Preferably, the operation of the post-packaging detection unit further includes: calculating the rate of change of the edge angle over time during the edge deformation process, and setting a standard airtight deformation rate. If the standard airtight deformation rate is greater than the rate of change of the edge angle over time, the milk powder packaging is determined to be airtight; if the standard airtight deformation rate is less than or equal to the rate of change of the edge angle over time, the milk powder packaging is determined to be airtight.

[0018] Preferably, it further includes a size measurement module for measuring the size of the roll film.

[0019] Preferably, the size measurement module is further configured to: acquire film roll image information;

[0020] The image information is processed by grayscale conversion and threshold segmentation to obtain the image information of the roll film surface;

[0021] The image information on the surface of the roll film is split into RGB channels and converted to HSV color to obtain new image information;

[0022] Calculate the threshold of each channel in the new image information to obtain the standard deviation of pixels in each channel;

[0023] The Th value is obtained based on the standard deviation of pixels in each channel and the standard deviation of pixels in the original image.

[0024] A preset threshold is obtained, and the Th value is compared with the preset threshold. If the Th value is greater than the preset threshold, the edge pixel information of the roll film is extracted using the Canny algorithm and a first-level wavelet transform is performed to obtain the edge pixel information.

[0025] The current size of the roll film is obtained by statistically analyzing the edge pixel information.

[0026] Compared with the prior art, the present invention has the following advantages and technical effects:

[0027] The online monitoring device system of this invention adopts a modular design, integrating multiple functional modules such as a vision processing module, an intelligent metering and weighing module, a size measurement module, an airtightness detection module, a raw material marking module, and a raw material proportioning coordination module. Each module has a clearly defined function and works collaboratively, covering the entire process of milk powder strip bottling, thereby achieving the purpose of real-time online monitoring and process control. Attached Figure Description

[0028] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0029] Figure 1 This is a schematic diagram of a milk powder bar canning device and an online monitoring system according to an embodiment of the present invention;

[0030] Figure 2 This is a schematic diagram of the airtightness testing device before packaging according to an embodiment of the present invention;

[0031] Figure 3 This is a schematic diagram of the airtightness testing device after packaging according to an embodiment of the present invention;

[0032] Figure 4 This is a schematic diagram of the image algorithm design process according to an embodiment of the present invention;

[0033] Figure 5 This is a schematic diagram of the information storage and processing module according to an embodiment of the present invention;

[0034] Figure 6 This is a schematic diagram of a neural network product quality assessment model according to an embodiment of the present invention;

[0035] The components include: 1. Horizontal conveying worktable; 2. Air tightness detection module; 3. Rotary worktable; 4. Metering and weighing module; 5. Raw material proportioning and coordination module; 6. CCD industrial camera; 7. Motion mechanism; 8. Raw material marking module; 9. Vent hole; 10. Film roll surface; 11. Container; 12. Water; 13. Push rod; 14. Milk powder strip. Detailed Implementation

[0036] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0037] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0038] Example 1

[0039] like Figure 1 As shown, this embodiment provides an online monitoring system for the production process of milk powder strips, including:

[0040] Raw material marking module 8 is used to mark the raw materials before milk powder bars are canned, so as to obtain the marked raw materials;

[0041] The metering and weighing module 4 is used to measure the marked raw materials to obtain the metered raw materials;

[0042] The raw material proportioning and coordination processing module 5 is used to perform partitioned filling of the metered raw materials to obtain the filled raw materials.

[0043] Air tightness testing module 2 is used to test the air tightness of the filled raw material before and after roll film packaging;

[0044] The vision processing module is used to acquire image information of all processes based on a CCD industrial camera and build a neural network model. The image information is then input into the neural network model for calculation to obtain monitoring results.

[0045] The raw material marking module 8 is used for marking the raw materials before canning the milk powder bars, enabling rapid marking and storage of corresponding raw material information. After the raw materials are filled, they are placed in fixed containers, each with a unique QR code label containing specific information about the raw material. The containers, filled with raw materials, are transported by conveyor belt to a rotating worktable. Furthermore, a CCD industrial camera 6 captures real-time images of the worktable, including images of the raw materials and the QR codes on the containers. The QR codes can be decoded using the images captured by the CCD industrial camera 6, and the decoded information is transmitted to a computer to determine the origin of the raw materials.

[0046] The weighing module 4 is used to measure the weight of the raw materials for the milk powder strips. Specifically, before filling, the raw materials need to be weighed to ensure the correctness of the raw material ratio. If the weight of any raw material exceeds a set normal threshold, the system determines that there is a quality problem with the current milk powder strip ratio, and the computer system issues a command to activate the action mechanism 7, so that the current raw materials continue to enter the raw material ratio coordination and processing module 5 through the rotating worktable 3. Furthermore, the weighing information is also stored in the information storage module.

[0047] Furthermore, if the weighing module 4 detects a quality problem with the milk powder strips, the raw material ratio needs to be readjusted through the raw material ratio coordination and processing module to proceed to the next round of raw material ratio adjustment, so as to monitor the raw material ratio in real time and ensure that the mixed raw materials meet the requirements.

[0048] The raw material proportioning and coordination module 5 is used to fill raw materials in zones according to a pre-set proportion. Specifically, different proportions of raw materials are pushed out by a pusher and mixed in a container to achieve the effect of different proportions of raw materials. Furthermore, if the proportion of raw materials does not meet the standard, the non-compliant raw materials will continue to be proportioned through the raw material proportioning and coordination module until the proportion meets the standard.

[0049] The aforementioned vision processing module primarily comprises a high-end industrial intelligent CCD industrial camera 6 and a visual image processing algorithm framework. The CCD industrial camera 6 is used for online monitoring of the milk powder strip production process, acquiring image information from each step. Furthermore, monitoring the bottling process ensures traceability at every step, guaranteeing safety, and also facilitates the detection of problems at each step, enabling timely problem identification and achieving online control to improve food safety and achieve the goal of online quality control and quality assessment visualization. Moreover, the acquired image information from each step can be used as source information for training and controlling the online monitoring device system, enhancing the real-time decision-making capabilities of the neural network.

[0050] A horizontal conveyor table 1 is connected to an airtightness testing module 2, which is used to test the airtightness of the roll film before and after packaging. To prevent damage to the roll film after it leaves the factory or during assembly by workers, the roll film undergoes an airtightness test before packaging. Specifically, uniform gas is blown onto the surface 10 of the roll film through vents 9. A container 11 filled with water is placed on the other side of the roll film surface 10. If a leak occurs in the airtight film, bubbles will immediately appear in the water 12 of the container, thus determining whether the roll film is leaking. Figure 2As shown. This device has the advantages of simple installation and low cost, and is suitable for preliminary non-inspection of the airtightness of various devices.

[0051] Furthermore, the airtightness test after roll film packaging is performed automatically using a compression method. Specifically, firstly, the outer packaging of the rolled film-packaged milk powder strip 14 is compressed using a pusher 13. The compression process is gradual to prevent damage to the outer packaging of the milk powder strip 14. Simultaneously, while the outer packaging of the milk powder strip 14 is being compressed, a CCD industrial camera 13 is used to capture the deformation of the strip-shaped outer packaging. Figure 3 As shown, further, image processing algorithms are used to process the acquired image to calculate the edge deformation process, thereby determining whether there is air leakage in the packaged film. The rate T1 of change of the edge angle of the milk powder strip 14 over time is calculated, and a standard non-leaking deformation rate ST is set. The two are compared; if ST is greater than T1, it is judged as a non-leaking state; if ST is less than or equal to T1, it is judged as a leaking state. This is because if there is air leakage in the milk powder strip packaging, under the same extrusion pressure, the angle of the edges of the milk powder strip 14 will be larger, and the deformation will be more severe. This simple airtightness testing device saves enterprises unnecessary expenses and has high applicability.

[0052] The size measurement module is used for measuring the dimensions of the roll film. Before packaging, the specific dimensions of the roll film need to be ensured; similarly, after packaging, the dimensions after packaging must also be ensured. Specifically, achieving size measurement depends on the acquisition of images by the CCD industrial camera and the design of the image processing algorithm. During the assembly line production process, various harsh environments are unavoidable, which can severely affect the quality of images acquired by the camera. Therefore, while ensuring efficient hardware operation, the design of the software algorithm is crucial.

[0053] Furthermore, the algorithm involves image processing. To adapt the system to various complex ambient light conditions, the acquired images need to be preprocessed to extract the necessary key information. First, the acquired images are converted to grayscale and thresholded. Noise from ambient light on the roll film surface is filtered out to obtain image information of the roll film surface. The image is then further split into RGB channels and converted to HSV color to obtain new image information, namely, image information for six channels: RGB and HSV. Next, the threshold for each channel is calculated, and the standard deviation (Stdi) of each channel's pixels is obtained. The difference between the standard deviation (Stdi) and the original image pixel standard deviation (Stdi) is used to obtain the Th value. The current Th value is compared with the current Threshold value. If the current Th value is greater than the current Threshold value, the next step continues. If the current Th value is less than the current Threshold value, the threshold (Threshold) is adjusted appropriately based on real-time conditions until the current Th value is greater than the current Threshold value. The Canny algorithm is used to extract the edge pixel information of the roll film, and a first-level wavelet transform is performed to filter high-frequency signals and store low-frequency signals. Current information is also stored to establish the working condition correlation of the current process. Further, the edge pixel information is statistically analyzed to calculate the current size of the roll film, and this current size information is stored. A detailed visual algorithm flowchart is shown below. Figure 4 As shown.

[0054] Furthermore, all module information will be stored in the information storage and processing module, such as... Figure 5 As shown, raw data is provided for training the data model. Specifically, by inputting the raw data, the neural network model can be trained online in real time to establish a correlation model between milk powder bar filling and final product quality, thus ensuring filling quality. Figure 6 As shown, the neural network model consists of three main parts: the input layer, the hidden layer, and the output layer.

[0055] Furthermore, the aforementioned neural network model is mainly used for online evaluation of product quality and online adjustment of process issues in the packaging of milk powder strips, enabling real-time detection of product quality problems and greatly helping to reduce enterprise losses.

[0056] The beneficial effects of this embodiment are:

[0057] (1) The online monitoring device system in this embodiment adopts a modular design, integrating multiple functional modules such as a vision processing module, an intelligent metering and weighing module, a size measurement module, an airtightness detection module, a raw material marking module, and a raw material ratio coordination and processing module. Each module has a clear function and cooperates with each other, which can cover the entire process of milk powder bar canning, thereby achieving the purpose of real-time online monitoring and process control.

[0058] (2) This embodiment uses a CCD industrial camera and visual image processing algorithm to collect image information of milk powder strip canning process in real time. Through image processing technology such as grayscale, RGB / HSV channel segmentation, and wavelet transform, key features are accurately extracted to realize real-time monitoring of production process, problem tracing and process optimization, and improve the visual control level of food safety and product quality.

[0059] (3) This embodiment designs two methods for airtightness testing before and after roll film packaging. Before packaging, a preliminary screening is performed using the "gas-water container bubbling method" to detect whether there are any leaks in the roll film. This method is simple, low-cost, and highly applicable. After packaging, the "extrusion + image deformation analysis" method is used to detect the rate of change of the deformation angle of the milk powder strip packaging using a CCD camera, thereby accurately determining whether there is any leakage and effectively improving the accuracy and reliability of the airtightness test.

[0060] (4) In this embodiment, the raw material marking module marks the raw materials with QR codes before the milk powder bars are canned. The QR codes record detailed information about the raw materials, facilitating subsequent traceability. The QR code information is read in real time by a high-end CCD camera, ensuring the controllability of the source of the raw materials and providing an effective basis for the allocation of responsibility for quality problems.

[0061] (5) All detection data generated by the modules are stored in the information storage and processing module for training the neural network model. This model can learn production data online in real time and dynamically adjust the production process according to the detection results, thereby establishing a correlation model between milk powder bar filling and final product quality, optimizing the process flow, and improving product consistency and pass rate.

[0062] The above are merely preferred embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An online monitoring system for the production process of milk powder strips, characterized in that, include: The raw material marking module is used to mark the raw materials before milk powder bars are canned, so as to obtain the marked raw materials; The metering and weighing module is used to measure the marked raw materials to obtain the metered raw materials; The metering and weighing module is also used to: measure the raw materials; if the weight of each raw material exceeds the set normal threshold, it is determined that there is a quality problem with the current milk powder bar ratio, so that the current raw materials continue to enter the raw material ratio coordination and processing module through the rotating worktable, and the raw material ratio is readjusted through the raw material ratio coordination and processing module to enter the next round of raw material ratio. The raw material proportioning and coordination processing module is used to perform partitioned filling of the metered raw materials to obtain the filled raw materials. An airtightness testing module is used to test the airtightness of the filled raw materials before and after roll film packaging. The vision processing module is used to acquire image information of all processes based on a CCD industrial camera and build a neural network model. The image information is then input into the neural network model for calculation to obtain monitoring results. It also includes: a size measurement module for measuring the size of the roll film; The size measurement module is also used to: acquire film roll image information; The image information is processed by grayscale conversion and threshold segmentation to obtain the image information of the roll film surface; The image information on the surface of the roll film is split into RGB channels and converted to HSV color to obtain new image information; Calculate the threshold of each channel in the new image information to obtain the standard deviation of pixels in each channel; The Th value is obtained based on the standard deviation of pixels in each channel and the standard deviation of pixels in the original image. A preset threshold is obtained, and the Th value is compared with the preset threshold. If the Th value is greater than the preset threshold, the edge pixel information of the roll film is extracted using the Canny algorithm and a first-level wavelet transform is performed to obtain the edge pixel information. The current size of the roll film is obtained by statistically analyzing the edge pixel information. Calculate the threshold for each channel and obtain the standard deviation of pixels in each channel, Stdi; subtract the standard deviation of pixels in the original image from the standard deviation of Stdi to obtain the Th value; compare the current Th value with the current Threshold value. If the current Th value is greater than the current Threshold value, continue to the next step; if the current Th value is less than the current Threshold value, adjust the threshold Threshold appropriately according to the real-time working conditions until the current Th value is greater than the current Threshold value; then use the Canny algorithm to extract the edge pixel information of the roll film, and perform a first-level wavelet transform to filter high-frequency signals, store low-frequency signals, and store the current information to establish the working condition correlation of the current process. The airtightness detection module includes: The pre-packaging inspection unit is used to test the airtightness of the roll film; The post-packaging testing unit is used to monitor the airtightness of the packaged raw materials. The pre-packaging inspection unit includes: a vent and a container; The operation of the pre-packaging detection unit includes: blowing uniform gas through the vent hole onto the surface of the roll film, and placing a container filled with water on the other side of the roll film surface. If air bubbles appear in the water in the container, it is determined that the roll film has leaked air. The operation of the packaging detection unit includes: using a pusher to squeeze the outer packaging of the milk powder strip after the roll film is packaged; while squeezing the outer packaging of the milk powder strip, using a CCD industrial camera to acquire the deformation of the strip shape of the milk powder strip outer packaging, generating a deformation image; using an image processing algorithm to calculate the deformation image to obtain the edge deformation process; and obtaining the roll film detection result based on the edge deformation process.

2. The system according to claim 1, characterized in that, The operation of the packaging detection unit further includes: calculating the rate of change of the edge angle over time during the edge deformation process, and setting a standard airtight deformation rate. If the standard airtight deformation rate is greater than the rate of change of the edge angle over time, the milk powder bar packaging is determined to be airtight. If the standard airtight deformation rate is less than or equal to the rate of change of the edge angle over time, the milk powder bar packaging is determined to be airtight.

Images