A label boundary automatic recognition system based on reflective sensor

Abstract

The present invention discloses a reflective sensor-based automatic label boundary recognition system, which relates to the field of printer technology. The system comprises a label boundary automatic learning module, a print job module, a real-time automatic correction module, a data recording and analysis module, and a control and user interface module. The system utilizes a reflective sensor to learn and identify the physical properties of different label paper consumables, automatically recording and saving these learned values in SPIFLASH. Thus, during a print job, surface data of the label paper consumables can be collected in real time, compared with the learned values, and an error value calculated. The position of the X- and Y-direction servo motors is then adjusted in real time using a proportional coefficient to ensure precise alignment of the inkjet landing point. This real-time automatic correction function begins with the second pass of a print job and continues until the job is completed, significantly reducing the scrap rate caused by position deviation, saving ink consumption, and lowering production costs.

Description

Technical Field

[0001] The present invention relates to the technical field of printers, and in particular to a label boundary automatic recognition system based on a reflective sensor. Background Art

[0002] With the rapid development of the logistics industry and manufacturing, the use of label paper as an information carrier is increasing. However, the traditional label paper printing method relies on manual typesetting and adjustment, which has many disadvantages: First, manual operation can easily lead to deviations in label position, which not only affects printing efficiency but also reduces label quality; second, due to problems such as position deviation, the scrap rate is high, resulting in a waste of resources; third, the traditional method consumes a lot of ink, which increases production costs; finally, because it does not conform to the concept of green and environmentally friendly production, waste disposal is difficult, which puts a burden on the environment. Summary of the Invention

[0003] The purpose of the present invention is to provide a label boundary automatic recognition system based on a reflective sensor, which is used to solve the problems existing in the traditional label printing method, improve the efficiency and accuracy of label printing, and reduce resource consumption.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] The present application provides a label boundary automatic recognition system based on a reflective sensor, including a label boundary automatic learning module, a printing operation module, a real-time automatic correction module, a data recording and analysis module, and a control and user interface module.

[0006] The label boundary automatic learning module learns the physical characteristics of different label paper consumables through a reflective sensor, identifies the boundary of each label, and automatically records and saves the learned value in SPIFLASH;

[0007] The print job module converts the image source file into the raster dot matrix image required by the printer using the RIP tool, imports the label data for printing, automatically records the printing data, displays a real-time progress bar, and records the number of labels to generate a log;

[0008] The real-time automatic correction module collects surface data of label paper consumables in real time during the printing operation, calculates errors by comparing the real-time data with the learned values, and adjusts the X- and Y-direction servo motors in real time, entering the real-time automatic correction from the second pass of the printing operation;

[0009] The data recording and analysis module sends and records printing data to the printing system in real time via RS485, displays a real-time progress bar on the interface, and records the number of labels to generate a log;

[0010] The control and user interface module includes an operation panel, through which X-direction and Y-direction learning is performed, a print job is started, and the sensitivity of the real-time automatic correction module is adjusted. The operation panel displays "array spacing" information in the X and Y directions.

[0011] Furthermore, before learning the material differences, surface flatness and typesetting errors of different label paper consumables through the reflective sensor, the method includes: installing the label paper consumables into the printer, then starting the learning program through the operation panel, and then performing X-direction learning, driving the inkjet printer to automatically move in the X direction and collect data of 6 label distances 3 times, comparing the collected array information with the actual consumables information, calculating the error, and adjusting it until the error is eliminated to zero, and then storing the learned value in SPIFLASH; based on the X-direction learning result, performing Y-direction learning, similarly collecting and comparing the array information, calculating and adjusting the error until zero error is reached, and saving the learned value.

[0012] Furthermore, identifying the boundary of each tag specifically includes:

[0013] The light intensity changes detected by the reflective sensor are converted into electrical signals, filtered and normalized, and then the boundaries of each tag are identified in the image data using an edge detection algorithm such as the Canny edge detector;

[0014] Specifically, the output electrical signal of the reflective sensor is expressed as: V(t)=a·I(t), where V(t) is the electrical signal, I(t) is the light intensity, and a is the gain coefficient of the sensor.

[0015] Furthermore, the image source file is converted into the raster dot matrix image required by the printer using the RIP tool, and the label data is imported for printing, specifically including:

[0016] Start the online tool on the computer to import pre-prepared label data or data generated by other RIP tools, and then use the RIP tool to convert the image source file into a raster dot matrix image that the printer can recognize. In the online tool, the operator needs to specify the total number of labels to be printed, and the number of rows and columns will be automatically calculated and adjusted to optimize the print layout; then the operator triggers the print command to start the print job process. The system interface will dynamically display the print progress bar, record the number of printed labels in real time, and generate a log.

[0017] Furthermore, during the printing process, the surface data of the label paper consumables is collected in real time. By comparing the real-time data with the learned value, the error is calculated and the X-axis and Y-axis servo motors are adjusted in real time. Specifically, the following steps are performed:

[0018] The reflective sensor collects surface data of the label paper consumables in real time, digitizes it through a 12-bit ADC, converts it into precise pulse data, and sends it to a 32-bit MCU. The MCU compares the real-time data with the learning value stored in SPIFLASH and calculates the error value. Based on the calculated error value, the MCU dynamically adjusts the temporary learning value stored in SRAM and transmits the updated value to the printing control system via the RS485 bus to fine-tune the position of the X and Y servo motors in real time to ensure accurate inkjet printing alignment, starting from the second pass of the print job and continuing until the job is completed.

[0019] Furthermore, the error value is calculated based on the error after the analog signal collected by the reflective sensor is converted by ADC and compared with the stored learning value. After adjusting the proportional coefficient, it is added to the old position of the servo motor to obtain the new position. The new position of the servo motor is expressed as: P new =P old +c(ADC(D analog )-L), where P old is the old position of the servo motor, ADC(D analog ) is a digital signal converted by a 12-bit ADC, that is, an analog signal collected by a reflective sensor D analog After quantization, L is the learning value stored in SPIFLASH, and c is the proportional coefficient, which is used to adjust the influence of the error on the position adjustment of the servo motor.

[0020] Furthermore, the real-time collection of surface data of the label paper consumables by the reflective sensor specifically includes:

[0021] Preprocess the collected surface data to determine the state variables of the position and velocity of the label paper consumables, and set the initial state estimate and initial covariance matrix of the Kalman filter;

[0022] Predict the system state based on the state transition model in the Kalman filter, and use the observation model and actual observation data to update the predicted state and covariance to obtain accurate state estimation;

[0023] Furthermore, the system state prediction is expressed as: in is the prior state estimate at time step k, F k is the state transition matrix, which describes how the state evolves over time, is the posterior state estimate at time step k-1, B k is the control matrix, and the control input u k Associated with state transfer, w k is the process noise;

[0024] The covariance prediction is expressed as: Among them, P k|k-1 is the prior state covariance estimate at time step k, P k-1|k-1 is the posterior state covariance estimate at time step k-1, Q k is the covariance matrix of the process noise.

[0025] The beneficial effects of the present invention are:

[0026] The label boundary automatic recognition system based on reflective sensors effectively solves the problems existing in traditional label paper printing methods and significantly improves printing efficiency and quality. The label boundary automatic learning module uses reflective sensors to learn and identify the physical characteristics of different label paper consumables, including material differences, surface flatness and typesetting errors, and automatically records and saves these learned values in SPIFLASH. In this way, the surface data of the label paper consumables can be collected in real time during the printing operation, and this real-time data is compared with the learned values to calculate the error value. The position of the X and Y servo motors is then adjusted in real time by adjusting the proportional coefficient to ensure accurate alignment of the inkjet landing point. This real-time automatic correction function starts from the second pass of the printing job and continues until the job is completed, significantly reducing the scrap rate caused by position deviation, saving ink consumption, reducing production costs, and complying with the concept of green and environmentally friendly production.

[0027] Through the print job module, the RIP tool is used to convert the image source file into the raster dot matrix image required by the printer, and the label data is imported for printing. At the same time, the printing data is automatically recorded, a real-time progress bar is displayed, and a log of the number of labels is recorded. Data export is supported, further improving the automation level and efficiency of the operation. The data recording and analysis module sends and records the printing data to the printing system in real time via RS485, which provides convenience for production statistics and supports data export, enhancing the flexibility and practicality of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0029] Figure 1 This is a schematic diagram of the structure of the automatic label boundary recognition system based on reflective sensors provided in Example 1 of the present application. DETAILED DESCRIPTION

[0030] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present application. Rather, they are merely examples of methods and systems consistent with certain aspects of the present application, as detailed in the appended claims.

[0031] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0032] The following describes in detail the specific implementation methods, features and effects of the present invention in conjunction with the accompanying drawings and preferred embodiments.

[0033] Example 1

[0034] See also Figure 1 This embodiment provides a label boundary automatic recognition system based on a reflective sensor, which is used to solve the problems existing in the traditional label printing method, improve the efficiency and accuracy of label printing, and reduce resource consumption.

[0035] The label boundary automatic recognition system based on reflective sensor provided by the present invention includes:

[0036] The label boundary automatic learning module uses a reflective sensor to learn the physical characteristics of different label paper consumables, including material differences, surface flatness, typesetting errors and other factors, to identify the boundary of each label. By automatically recording and saving the learned values in SPIFLASH, the accuracy of inkjet placement is ensured.

[0037] The print job module uses the RIP tool (Raster Image Processor) to convert the image source file into the raster dot matrix image required by the printer, and imports the label data for printing. It automatically records the printing data, displays a real-time progress bar, and records the number of labels to generate a log, and supports data export;

[0038] The real-time automatic correction module collects surface data of label paper consumables in real time during the printing operation, calculates errors by comparing the real-time data with the learned values, and adjusts the X and Y servo motors in real time to ensure the accuracy of the inkjet landing point. The real-time automatic correction function starts from the second pass of the printing operation and has 10 levels of sensitivity adjustment.

[0039] The data recording and analysis module sends and records printing data to the printing system in real time via RS485. The interface displays a real-time progress bar and records the number of labels generated. It is equipped with production statistics and supports data export.

[0040] The control and user interface module includes an operation panel, which is used to learn the X and Y directions, start a print job, and adjust the sensitivity of the real-time automatic correction module. The operation panel displays the "array spacing" information in the X and Y directions, provides error correction and saves learning values.

[0041] Specifically, the system uses a highly sensitive reflective sensor that can quickly identify the boundaries of label consumables in real time. The system is not limited to the consumables themselves and can be widely applied to various types of label paper and printers. The real-time automatic correction function ensures the accuracy of inkjet placement during the printing process to the greatest extent, reducing consumables and ink consumption and promoting green and environmentally friendly production. Through data recording and analysis, the system can send and record print data to the printing system in real time via RS485 and supports data export.

[0042] This embodiment uses boundary difference as the basis for identification, which is not limited to the situation of the consumables themselves. It can be widely used in various types of label papers and printers, has strong adaptability and is easy to integrate. During printing, due to the influence of factors such as the surface flatness of the consumables themselves, typesetting errors, base color block uniformity, label base thickness, and printing mechanism motion errors, the initially learned data or the data learned in the previous PASS deviates from the real-time data of the current sensor. This system makes full use of this real-time deviation, enables real-time automatic correction function, and cooperates with 10 levels of sensitivity adjustment to maximize the accuracy of the inkjet landing point during the printing process, ensure automated operations according to quality and quantity, reduce the consumption of label paper consumables, ink, etc., and promote green and environmentally friendly production.

[0043] Furthermore, before learning the material differences, surface flatness and typesetting errors of different label paper consumables through the reflective sensor, the method includes: installing the label paper consumables into the printer, then starting the learning program through the operation panel, and then performing X-direction learning, driving the inkjet printer to automatically move in the X direction and collect data of 6 label distances 3 times, comparing the collected array information with the actual consumables information, calculating the error, and adjusting it until the error is eliminated to zero, and then storing the learned value in SPIFLASH; based on the X-direction learning result, performing Y-direction learning, similarly collecting and comparing the array information, calculating and adjusting the error until zero error is reached, and saving the learned value.

[0044] Specifically, first install the label paper consumables to be printed on the printer; click the learning button in the operation panel to enter the X-direction learning. The inkjet carriage automatically moves back and forth 6 labels in the X direction for a total of 3 times by default (the number of learning labels and the number of times can be adjusted), and the returned X-direction array information is displayed in the X-direction "Array Spacing" column of the operation panel. Check the X-direction array information of the actual label consumables, fill in the corresponding "Error" column with error = learning value - actual value, click learning again, until error = learning value - actual value = 0, click save, and the learning value is automatically saved in SPIFLASH; return to the parent directory. Under normal circumstances, learning can be completed in 2 to 3 times;

[0045] Click the learning button in the operation panel to enter the Y-direction learning. Depending on the learning value in the X-direction, the X-direction servo motor drives the spray car to automatically move to the middle position of the first label in the X-direction of the consumables. Under the action of the Y-direction servo motor, the consumables automatically move back and forth in the Y direction for a total of 3 times by default (the number and number of learning labels can be adjusted), and the returned Y-direction array information is displayed in the Y-direction "Array Spacing" column of the operation panel. Check the Y-direction array information of the actual label consumables, fill in the corresponding "Error" column with error = learning value - actual value, click learning again, until error = learning value - actual value = 0, click save, and the learning value is automatically saved in SPIFLASH; return to the parent directory. Under normal circumstances, learning can be completed in 2 to 3 times.

[0046] Furthermore, identifying the boundary of each tag specifically includes:

[0047] The light intensity changes detected by the reflective sensor are converted into electrical signals, filtered and normalized, and then the boundaries of each tag are identified in the image data using an edge detection algorithm such as the Canny edge detector;

[0048] Specifically, the output electrical signal of the reflective sensor is expressed as: V(t)=a·I(t), where V(t) is the electrical signal, I(t) is the light intensity, and a is the gain coefficient of the sensor.

[0049] Furthermore, the image source file is converted into a raster dot matrix image required by the printer using a RIP tool (Raster Image Processor), and the label data is imported for printing, specifically including:

[0050] Start the online tool on the computer to import pre-prepared label data or data generated by other RIP tools, and then use the RIP tool to convert the image source file into a raster dot matrix image that the printer can recognize. In the online tool, the operator needs to specify the total number of labels to be printed, and the number of rows and columns will be automatically calculated and adjusted to optimize the print layout; then the operator triggers the print command to start the print job process. The system interface will dynamically display the print progress bar, record the number of printed labels in real time, and generate a log.

[0051] Specifically, open the online tool on the computer, import the pre-prepared label data or label data generated by other RIP tools, fill in the number of labels to be printed in the job volume (the system automatically rounds up the number of rows and columns), click Start Printing, enter the printing job process, the interface displays a real-time progress bar, and records the number of labels generated in the log, has prepared production statistics, and supports exporting data and setting parameters for use by other machines.

[0052] RIP Tool: Raster Image Processor (Raster Image Processor), refers to image processing software used for printing or copying. Its function is to convert image source files into raster dot images required by the printer.

[0053] Furthermore, during the printing operation, the surface data of the label paper consumables is collected in real time, and the error is calculated by comparing the real-time data with the learning value, and the X-axis and Y-axis servo motors are adjusted in real time. Specifically, the surface data of the label paper consumables is collected in real time according to the reflective sensor, and digitally quantized by the 12-bit ADC, converted into precise pulse data and sent to the 32-bit MCU, wherein the MCU compares the real-time data with the learning value stored in the SPIFLASH to calculate the error value. According to the calculated error value, the MCU dynamically adjusts the temporary learning value stored in the SRAM, and transmits the updated value to the printing control system via the RS485 bus to fine-tune the position of the X-axis and Y-axis servo motors in real time to ensure accurate alignment of the inkjet printing. This process starts from the second PASS of the printing operation and continues until the operation is completed.

[0054] Among them, SPIFLASH is a non-volatile memory that uses a serial peripheral interface (SPI) for communication. This type of memory is commonly used in embedded systems to store firmware, configuration parameters, calibration data, and other information that needs to remain unchanged after the system is powered off. Specifically, SPIFLASH is used to store the learning values of parameters such as material differences, surface flatness, and typesetting errors of label paper consumables obtained through reflective sensor learning. These learning values are read when the system starts or executes a print job, and are used to compare with the real-time collected data to calculate errors and adjust the position of the servo motor in real time to ensure accurate alignment of inkjet printing. SPIFLASH is due to its fast reading and writing capabilities, miniaturization, and low power consumption.

[0055] Specifically, due to the influence of factors such as the surface flatness of the consumables themselves, typesetting errors, uniformity of the base color blocks, thickness of the label base, and movement errors of the printing mechanism, there is a deviation between the initially learned data or the data learned in the previous PASS and the real-time data of the current sensor. If this is not processed and the pre-printing learning values are continued to be used step by step, the printing quality will be acceptable in the initial stage. As the printing operation continues, the deviation will become larger and larger, and the product will have to be treated as scrap.

[0056] This system fully considers the harmfulness of this error and starts the real-time automatic correction function at the beginning of the printing job. To be more precise, the real-time automatic correction function starts from the second PASS of the printing job. Among them, PASS in the field of digital inkjet printing, the printing screen is divided into several small areas, and the number of times a unit area is covered by inkjet during printing is called the PASS number. Generally, for specific consumables, the higher the PASS number, the better the printing quality, but the speed is correspondingly reduced. Usually, printers have 4PASS, 6PASS and 8PASS printing methods.

[0057] The first pass uses the learning value in SPIFLASH to determine the inkjet landing point. At the same time, the actual data returned by the reflective sensor in real time is digitally quantized by the 12-bit ADC, and the 12-bit precision pulse data is sent to the 32-bit MCU. The core component MCU compares the data with the learning value in SPIFLASH and calls the learning function module to store the error = learning value - actual value in the MCU's SRAM unit. At the same time, the refreshed temporary learning value is transmitted to the printing control system in real time via the RS485 bus. During the second pass printing, the X-axis servo and Y-axis servo are fine-tuned to ensure the accurate inkjet landing point of the second pass.

[0058] The second pass uses the temporary learning value of the first pass to determine the inkjet landing point. At the same time, the actual data returned by the reflective sensor in real time is digitally quantized by the 12-bit ADC, and the 12-bit precision pulse data is sent to the 32-bit MCU. The core component MCU compares the data with the first pass learning value and calls the learning function module to store the error = learning value - actual value in the MCU's SRAM unit. At the same time, the refreshed temporary learning value is transmitted to the printing control system in real time via the RS485 bus. During the third pass printing, the X-axis servo and Y-axis servo are fine-tuned to ensure that the inkjet landing point of the third pass is accurate.

[0059] As the print job progresses, the learning module continuously refreshes the temporary learning value of the SRAM unit at each pass, and the real-time correction module fine-tunes the X and Y servo motors at each pass. This repetitive process can maximize the accuracy of the inkjet landing point at each pass during the printing process. The system's real-time correction function has 10 levels of sensitivity adjustment. During the initial printing phase, you can observe the print quality and adjust it to a satisfactory level in real time. Once the adjustment is stopped, subsequent prints will maintain this effect until the entire print task is completed, and the real-time correction sensitivity parameters will be automatically saved in SPIFLASH. This ensures automated operations that meet quality and quantity to the greatest extent possible, reduces the consumption of label paper consumables, ink, etc., improves the cost-effectiveness of the machine, and promotes green and environmentally friendly production. Specifically, there are 10 levels of sensitivity adjustment, which can be adjusted to a satisfactory level in real time based on the print quality, and the real-time correction sensitivity parameters are automatically saved in SPIFLASH.

[0060] Furthermore, the error value is calculated based on the error after the analog signal collected by the reflective sensor is converted by ADC and compared with the stored learning value. After adjusting the proportional coefficient, it is added to the old position of the servo motor to obtain the new position. The new position of the servo motor is expressed as: P new =P old +c(ADC(D analog )-L), where P old is the old position of the servo motor, ADC(D analog ) is a digital signal converted by a 12-bit ADC, that is, an analog signal collected by a reflective sensor D analog After quantization, L is the learning value stored in SPIFLASH, and c is the proportional coefficient, which is used to adjust the influence of the error on the position adjustment of the servo motor.

[0061] Specifically, through an advanced feedback control system, the new position of the servo motor is precisely calculated and adjusted to achieve highly accurate alignment for inkjet printing. This process involves converting the analog signal collected by the reflective sensor into a digital signal using a 12-bit ADC. This signal is then compared with the learned value stored in SPIFLASH to calculate the error. The calculated error value is adjusted using a proportional coefficient c to determine its impact on the servo motor position. Finally, it is added to the old position of the servo motor to determine the new position, ensuring the accuracy of the inkjet placement during printing, significantly improving print quality and efficiency.

[0062] Furthermore, the real-time collection of surface data of the label paper consumables by the reflective sensor specifically includes:

[0063] Preprocess the collected surface data to determine the state variables of the position and velocity of the label paper consumables, and set the initial state estimate and initial covariance matrix of the Kalman filter;

[0064] Predict the system state based on the state transition model in the Kalman filter, and use the observation model and actual observation data to update the predicted state and covariance to obtain a more accurate state estimate;

[0065] Furthermore, the system state prediction is expressed as: in is the prior state estimate at time step k, F k is the state transition matrix, which describes how the state evolves over time, is the posterior state estimate at time step k-1, B k is the control matrix, and the control input u k Associated with state transfer, w k is the process noise;

[0066] The covariance prediction is expressed as: Among them, P k|k-1 is the prior state covariance estimate at time step k, P k-1|k-1 is the posterior state covariance estimate at time step k-1, Q k is the covariance matrix of the process noise.

[0067] Specifically, in the label boundary automatic recognition system based on reflective sensors, the process of real-time collection of label paper consumables surface data first involves preprocessing the raw data collected by the sensor to eliminate noise and interference, and then determining the key state variables, namely the position and speed of the label paper consumables. Next, the initial state estimate is set for the Kalman filter, which is usually based on prior knowledge or assumptions at system startup, as well as the initial covariance matrix, which represents the quantification of the uncertainty of these initial estimates. These steps provide a starting point for the Kalman filter, enabling it to accurately track the dynamic changes of the label paper consumables in subsequent prediction and update cycles by fusing the prediction model and real-time observation data, thereby providing accurate feedback for the system's automatic correction and ensuring high accuracy in the inkjet printing process.

[0068] Specifically, the reflective sensor-based automatic label printing boundary recognition system significantly improves label printing efficiency and accuracy through high-precision boundary recognition and automatic correction. In the future, we will continue to optimize system performance and provide high-quality label printing solutions for more industries.

[0069] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A label boundary automatic recognition system based on a reflective sensor, characterized by: It includes label boundary automatic learning module, printing operation module, real-time automatic correction module, data recording and analysis module and control and user interface module. The label boundary automatic learning module learns the physical characteristics of different label paper consumables through a reflective sensor, identifies the boundary of each label, and automatically records and saves the learned value in SPIFLASH; The print job module converts the image source file into the raster dot matrix image required by the printer using the RIP tool, imports the label data for printing, automatically records the printing data, displays a real-time progress bar, and records the number of labels to generate a log; The real-time automatic correction module collects surface data of label paper consumables in real time during the printing operation, calculates errors by comparing the real-time data with the learned values, and adjusts the X- and Y-direction servo motors in real time, entering the real-time automatic correction from the second pass of the printing operation; The data recording and analysis module sends and records printing data to the printing system in real time via RS485, displays a real-time progress bar on the interface, and records the number of labels to generate a log; The control and user interface module includes an operation panel, which starts a print job and adjusts the sensitivity of the real-time automatic correction module by performing X- and Y-direction learning. The operation panel displays "array spacing" information in the X and Y directions.

2. The automatic label boundary recognition system based on a reflective sensor according to claim 1, characterized in that: Before learning the material differences, surface flatness, and typesetting errors of different label paper consumables through the reflective sensor, the method includes: installing the label paper consumables into the printer, then starting the learning program through the operation panel, and then performing X-direction learning, driving the inkjet printer to automatically move in the X direction and collect data of 6 label distances 3 times, comparing the collected array information with the actual consumables information, calculating the error, and adjusting it until the error is eliminated to zero, and then storing the learned value in SPIFLASH; based on the X-direction learning result, performing Y-direction learning, similarly collecting and comparing the array information, calculating and adjusting the error until the error is zero, and saving the learned value.

3. The automatic label boundary recognition system based on a reflective sensor according to claim 1, characterized in that: Identifying the boundary of each label specifically includes: The light intensity changes detected by the reflective sensor are converted into electrical signals, filtered and normalized, and then the boundary of each tag is identified in the image data using the Canny edge detector algorithm; Specifically, the output electrical signal of the reflective sensor is expressed as: V(t)=a·I(t), where V(t) is the electrical signal, I(t) is the light intensity, and a is the gain coefficient of the sensor.

4. The automatic label boundary recognition system based on a reflective sensor according to claim 1, characterized in that: Use the RIP tool to convert the image source file into the raster dot matrix image required by the printer, and import the label data for printing, including: Start the online tool on the computer to import pre-prepared label data or data generated by other RIP tools, and then use the RIP tool to convert the image source file into a raster dot matrix image that the printer can recognize. In the online tool, the operator needs to specify the total number of labels to be printed, and the number of rows and columns will be automatically calculated and adjusted to optimize the print layout; then the operator triggers the print command to start the print job process. The system interface will dynamically display the print progress bar, record the number of printed labels in real time, and generate a log.

5. The automatic label boundary recognition system based on a reflective sensor according to claim 1, characterized in that: During the printing process, the surface data of the label paper consumables is collected in real time. By comparing the real-time data with the learned value, the error is calculated and the X and Y servo motors are adjusted in real time. Specifically, The reflective sensor collects surface data of the label paper consumables in real time, digitizes it through a 12-bit ADC, converts it into precise pulse data, and sends it to a 32-bit MCU. The MCU compares the real-time data with the learning value stored in SPIFLASH and calculates the error value. Based on the calculated error value, the MCU dynamically adjusts the temporary learning value stored in SRAM and transmits the updated value to the print control system via the RS485 bus to fine-tune the position of the X and Y servo motors in real time to ensure accurate inkjet printing alignment, starting from the second pass of the print job and continuing until the job is completed.

6. The automatic label boundary recognition system based on a reflective sensor according to claim 5, characterized in that: The error value is calculated based on the error after the analog signal collected by the reflective sensor is converted by ADC and compared with the stored learning value. After adjustment by the proportional coefficient, it is added to the old position of the servo motor to obtain the new position. The new position of the servo motor is expressed as: P new =P old +c(ADC(D analog )-L) where P old is the old position of the servo motor, ADC(D analog ) is a digital signal converted by a 12-bit ADC, that is, an analog signal collected by a reflective sensor D analog After quantization, L is the learning value stored in SPIFLASH, and c is the proportional coefficient, which is used to adjust the influence of the error on the position adjustment of the servo motor.

7. The automatic label boundary recognition system based on a reflective sensor according to claim 4, characterized in that: The real-time collection of surface data of label paper consumables based on the reflective sensor specifically includes: Preprocess the collected surface data to determine the state variables of the position and velocity of the label paper consumables, and set the initial state estimate and initial covariance matrix of the Kalman filter; The system state is predicted based on the state transition model in the Kalman filter, and the predicted state and covariance are updated using the observation model and actual observation data to obtain accurate state estimation.

8. The automatic label boundary recognition system based on a reflective sensor according to claim 7, characterized in that: The prediction of the system state is expressed as: in is the prior state estimate at time step k, F k is the state transition matrix, which describes how the state evolves over time, is the posterior state estimate at time step k-1, B k is the control matrix, and the control input u k Associated with state transfer, w k is the process noise; The covariance prediction is expressed as: Among them, P k|k-1 is the prior state covariance estimate at time step k, P k-1|k-1 is the posterior state covariance estimate at time step k-1, Q k is the covariance matrix of the process noise.

Images