A mass flow adaptive measurement method and system for shoe rubber compounding

Abstract

The present application relates to the technical field of mass flow measurement, and particularly relates to a mass flow adaptive measurement method and system for shoe glue proportioning, comprising: obtaining multiple types of conveying flow materials for shoe glue proportioning, performing charge signal collection and preprocessing on the powder flow materials by using a mass flow sensor set to obtain multiple preprocessing signals, performing phase difference analysis on the multiple preprocessing signals to obtain signal phase differences, calculating a preliminary powder flow mass flow based on the signal phase differences, a physical distance and a sampling frequency, performing liquid mass flow measurement on the liquid flow materials to obtain a preliminary liquid flow mass flow, and completing the mass flow adaptive measurement for shoe glue proportioning based on the preliminary powder flow mass flow and the preliminary liquid flow mass flow. Through real-time mass flow accurate detection, the present application realizes mass flow adjustment according to the component proportioning of shoe glue, so as to improve the control accuracy of shoe glue proportioning and ensure production continuity and product quality consistency.

Description

Technical Field

[0001] This invention relates to the field of mass flow measurement technology, and in particular to an adaptive mass flow measurement method and system for shoe adhesive formulation. Background Technology

[0002] As a key adhesive material in the shoe manufacturing process, the precision of its formulation directly affects the bonding strength, durability, and overall quality stability of the shoes. The production process often involves the precise delivery and mixing of various materials, such as powdered fillers (e.g., magnesium oxide) and liquid base materials (e.g., neoprene rubber). Inaccurate material quality control can lead to deviations in the actual formulation from the process settings, resulting in problems such as substandard adhesive viscosity and inconsistent curing characteristics. This severely impacts product qualification rates and production efficiency.

[0003] In existing technologies, the detection of material mass flow rate mostly relies on fixed types of mass flow sensors, such as turbine flow meters for liquids or differential pressure flow meters for gases.

[0004] However, in the context of shoe adhesive production, where multiphase materials coexist, existing methods have significant limitations: First, they struggle to simultaneously adapt to materials with significantly different physical states, such as powder and liquid. Powdered materials are prone to static electricity, adsorption, and blockage, making traditional contact sensors less suitable. Second, the detection process is often independent of the actual adhesive state, failing to form a closed-loop feedback with real-time adhesive viscosity and other process parameters, thus hindering adaptive adjustments based on final product performance. Third, when adhesive viscosity deviates, there is a lack of rapid and accurate detection methods to pinpoint abnormal materials and mass flow rates, requiring subsequent adjustments based on manual experience, resulting in low efficiency and difficulty in guaranteeing accuracy. Therefore, a method is needed that can accurately detect real-time mass flow rates and adjust them according to the shoe adhesive's component ratio to improve the control precision of the adhesive formulation, ensuring production continuity and product quality consistency. Summary of the Invention

[0005] This invention provides an adaptive mass flow rate measurement method and a computer-readable storage medium for shoe adhesive formulation. Its main purpose is to improve the control accuracy of shoe adhesive formulation and ensure production continuity and product quality consistency by accurately detecting the mass flow rate in real time and adjusting the mass flow rate according to the composition ratio of the shoe adhesive.

[0006] To achieve the above objectives, the present invention provides an adaptive mass flow rate measurement method for shoe adhesive formulation, comprising: Obtain various types of conveying materials for shoe adhesive formulation, wherein the conveying materials are located in a pre-constructed fluid conveying pipeline, and the various types of conveying materials include powder materials and liquid materials; A pre-built mass flow sensor set is used to perform charge signal acquisition on powdered material to obtain multiple charge signals. The mass flow sensor set includes multiple mass flow sensors. Multiple charge signals are preprocessed to obtain multiple preprocessed signals, including signal filtering and signal peak finding. Phase difference analysis is performed on multiple preprocessed signals to obtain the signal phase difference; The physical spacing and sampling frequency of multiple preprocessed signals are obtained. Based on the signal phase difference, physical spacing and sampling frequency, the preliminary powder flow mass flow rate is calculated using a pre-constructed calculation formula. Based on the preliminary powder flow mass flow rate, the powder flow mass flow rate measurement for shoe adhesive formulation is completed. Liquid mass flow rate is measured for the liquid material to obtain a preliminary liquid mass flow rate. Based on the preliminary liquid mass flow rate, the liquid mass flow rate for shoe adhesive formulation is measured.

[0007] Optionally, the process of using a pre-built set of mass flow sensors to acquire charge signals from the powder flow material yields multiple charge signals, including: The initial charge signal of the powder flow material is acquired by using a mass flow sensor set, resulting in multiple initial charge signals; Calculate the amplitude characteristic value of each initial charge signal among multiple initial charge signals to obtain multiple amplitude characteristic values; A comprehensive amplitude feature value is calculated based on multiple amplitude feature values. Based on the comprehensive amplitude feature value, a pre-constructed gain coefficient adjustment algorithm is used to calculate the gain adjustment coefficient. Gain control is performed on multiple initial charge signals based on the gain adjustment coefficient to obtain multiple charge signals.

[0008] Optionally, the preprocessing of multiple charge signals to obtain multiple preprocessed signals includes: For each of the multiple charge signals, perform the following operation: A low-frequency filtering operation is performed on the charge signal to obtain a high-frequency signal; Adaptive LMS filtering is performed on the high-frequency signal to obtain the filtered signal; Obtain multiple amplitude values ​​of the filtered signal; Amplitude retention operations are performed on multiple amplitudes based on pre-constructed upper and lower amplitude thresholds to obtain multiple retained amplitudes; A preprocessed signal is constructed based on multiple retained amplitude values; The preprocessed signals are summarized to obtain multiple preprocessed signals.

[0009] Optionally, performing phase difference analysis on multiple preprocessed signals to obtain the signal phase difference includes: Multiple preprocessed signals are fused to obtain upstream and downstream signals; The time-domain phase difference is calculated based on the upstream and downstream signals using a pre-constructed formula for calculating the time-domain phase difference. Perform a Fast Fourier Transform on the upstream and downstream signals to obtain the upstream and downstream frequency domain signals; Calculate the frequency domain phase difference based on the upstream and downstream frequency domain signals; The signal phase difference is calculated based on the time-domain phase difference and the frequency-domain phase difference.

[0010] Optionally, the step of performing liquid mass flow rate measurement on the liquid flow material to obtain a preliminary liquid flow rate includes: Perform time-series-based image acquisition on the liquid flow material to obtain multiple continuous material images; Perform image preprocessing operations on multiple consecutive material images to obtain multiple processed images; Perform pairwise combination operations on multiple processed images to obtain multiple image combinations. Each image combination includes a processed image and adjacent processed images. The adjacent processed images are processed images that are adjacent to the processed image and lag behind it. Preliminary liquid flow mass flow rate calculations are performed based on pixel displacement analysis using a combination of multiple images, resulting in multiple preliminary liquid flow mass flow rates.

[0011] Optionally, the preliminary liquid flow mass flow rate calculation based on pixel displacement analysis using multiple image combinations yields multiple preliminary liquid flow mass flow rates, including: For each of the multiple image combinations, perform the following operation: Perform liquid flow material region recognition on the processed image and adjacent processed images to obtain processed material region images and adjacent material region images; Pixel displacement analysis is performed on the image of the processed material area and the image of the adjacent material area to obtain multiple pixel flow displacement vectors; The average displacement vector is obtained by averaging the flow displacement vectors of multiple pixels. Obtain the time difference between the processed image and adjacent processed images, and calculate the average pixel velocity based on the time difference and the average displacement vector; Calculate the initial liquid flow mass flow rate based on the average pixel velocity; By summing the initial liquid flow mass flow rates, multiple initial liquid flow mass flow rates are obtained.

[0012] Optionally, the step of performing pixel displacement analysis on the processed material region image and adjacent material region images to obtain multiple pixel flow displacement vectors includes: Based on the material area image and adjacent material area images, a marker recognition operation is performed to obtain the coordinates of multiple markers and multiple adjacent markers; Based on multiple marker coordinates and multiple adjacent marker coordinates, multiple material image regions and multiple adjacent image regions are extracted from the processed image and adjacent processed images, respectively. Among them, the material image regions correspond one-to-one with the marker coordinates, and the adjacent image regions correspond one-to-one with the adjacent marker coordinates. Extract material image regions one by one from the material image regions to obtain the target material region, and perform the following operations on the target material region: Identify the adjacent image regions corresponding to the target material region in multiple adjacent image regions to obtain the target adjacent region; Obtain the maximum adjacent material region based on the target material region and the target adjacent region; The center coordinates of the largest adjacent material region and the target material region are obtained respectively. The maximum center coordinates and the target center coordinates are obtained. The pixel flow displacement vector is calculated based on the maximum center coordinates and the target center coordinates. By summing the pixel flow displacement vectors, we obtain multiple pixel flow displacement vectors corresponding to multiple marker coordinates.

[0013] Optionally, obtaining the maximum adjacent material region based on the target material region and the target adjacent region includes: Obtain the grayscale values ​​of multiple target pixels in the target material region, and obtain multiple adjacent material regions from the target adjacent region based on the target material region; For each of multiple adjacent material regions, perform the following operation: Obtain the gray values ​​of multiple adjacent pixels in the adjacent material region, and calculate the correlation coefficient based on the gray values ​​of multiple adjacent pixels and multiple target pixels using a pre-constructed formula for calculating the correlation coefficient. Summarize the correlation coefficients to obtain multiple correlation coefficients, and extract the maximum value from the multiple correlation coefficients to obtain the maximum correlation coefficient; Identify the adjacent material region corresponding to the largest correlation coefficient among multiple adjacent material regions to obtain the largest adjacent material region.

[0014] Optionally, the formula for calculating the correlation coefficient is as follows: ; in, Represents the correlation coefficient. Represents the grayscale value of multiple target pixels. grayscale value of each target pixel Represents the grayscale value of multiple target pixels. The index of the grayscale value of the target pixel This represents the average grayscale value of multiple target pixels. Represents the gray value of a plurality of adjacent pixels. grayscale values ​​of adjacent pixels This represents the average grayscale value of multiple adjacent pixels. This represents the total number of grayscale values ​​for multiple target pixels.

[0015] To achieve the above objectives, the present invention also provides an adaptive mass flow rate measurement system for shoe adhesive formulation, comprising: The material conveying module is used to acquire various types of conveying materials for shoe adhesive formulation, wherein the conveying materials are located in a pre-constructed fluid conveying pipeline, and the various types of conveying materials include powder materials and liquid materials. The signal acquisition module is used to perform charge signal acquisition on powdered material using a pre-built mass flow sensor set to obtain multiple charge signals. The mass flow sensor set includes multiple mass flow sensors. The powder mass flow rate measurement module is used to preprocess multiple charge signals to obtain multiple preprocessed signals. The preprocessing includes signal filtering and signal peak finding. Phase difference analysis is performed on the multiple preprocessed signals to obtain the signal phase difference. The physical spacing and sampling frequency of the multiple preprocessed signals are obtained. Based on the signal phase difference, physical spacing and sampling frequency, the preliminary powder flow rate is calculated using a pre-constructed calculation formula. Based on the preliminary powder flow rate, the powder flow rate measurement for shoe adhesive formulation is completed. The liquid mass flow rate measurement module is used to perform liquid mass flow rate measurement on liquid materials to obtain a preliminary liquid mass flow rate. Based on the preliminary liquid mass flow rate, the liquid mass flow rate measurement for shoe adhesive formulation is completed.

[0016] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the above-described adaptive mass flow rate measurement method for shoe adhesive ratio.

[0017] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned adaptive mass flow rate measurement method for shoe adhesive ratio.

[0018] To address the problems described in the background art, this invention obtains multiple types of conveying materials for shoe adhesive formulation. These materials are situated within a pre-constructed fluid conveying pipeline. The multiple types of conveying materials include powder flow materials and liquid flow materials. A pre-constructed mass flow sensor set is used to acquire charge signals from the powder flow materials, resulting in multiple charge signals. These charge signals are then pre-processed to obtain multiple pre-processed signals, including signal filtering and peak finding. Phase difference analysis is performed on the pre-processed signals to obtain the signal phase difference. The physical spacing and sampling frequency of the pre-processed signals are then obtained. Based on the signal phase difference, physical spacing, and sampling frequency, a preliminary powder flow mass flow rate is calculated using a pre-constructed formula. The powder flow mass flow rate for shoe adhesive formulation is then measured based on this preliminary powder flow mass flow rate. Similarly, liquid flow mass flow rate measurement is performed on the liquid flow materials to obtain a preliminary liquid flow mass flow rate. Finally, the liquid flow mass flow rate for shoe adhesive formulation is measured based on this preliminary liquid flow mass flow rate. This invention selects different mass flow rate detection methods for different materials based on their physical form, adapting to materials with significantly different physical forms, such as powder and liquid, to achieve adaptive detection of material mass flow rate. If the conveyed material is a powder, a mass flow sensor is used to collect the charge signals generated by friction. Preprocessing multiple charge signals effectively filters out noise interference, providing high-quality signals for subsequent analysis. Phase difference analysis is then performed on the preprocessed signals, and combined with the sensor's physical spacing and sampling frequency, the mass flow rate of the powder is accurately calculated. This method effectively solves the problem of direct measurement of powder materials using traditional flowmeters due to their tendency to adhere and generate dust. If the conveyed material is a liquid, a time-series-based image acquisition and analysis method is used for mass flow rate measurement. By acquiring continuous material images, identifying liquid material regions, and performing pixel displacement analysis, the liquid mass flow rate is finally calculated, achieving non-contact, high-precision mass flow rate detection of liquid materials. Based on the measured material mass flow rate, adaptive detection of material mass flow rate during shoe adhesive mixing is achieved. Finally, as can be seen in the embodiments of the present invention, the present invention also achieves mass flow rate adjustment by summarizing the mass flow rates of each material and based on the component ratio of the shoe adhesive, thereby controlling the shoe adhesive ratio and ensuring production continuity and product quality consistency. Therefore, the present invention can improve the control accuracy of the shoe adhesive ratio and ensure production continuity and product quality consistency by accurately detecting the mass flow rate in real time and adjusting the mass flow rate according to the component ratio of the shoe adhesive. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating an adaptive mass flow measurement method for shoe adhesive ratio according to an embodiment of the present invention. Figure 2This is a functional block diagram of an adaptive mass flow rate measurement system for shoe adhesive ratio provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device for implementing the adaptive mass flow rate measurement method for shoe adhesive ratio according to an embodiment of the present invention. Figure 4 This is a schematic diagram of the image coordinate system for a continuous material image used in an embodiment of the present invention to implement the adaptive measurement method for mass flow rate of shoe adhesive ratio.

[0020] Explanation of reference numerals in the attached figures: 1. Electronic equipment; 10. Processor; 11. Memory; 12. Bus; 501. Feed port; 502. Discharge port.

[0021] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0023] This application provides an adaptive mass flow rate measurement method for shoe adhesive formulation. The executing entity of this adaptive mass flow rate measurement method for shoe adhesive formulation includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the adaptive mass flow rate measurement method for shoe adhesive formulation can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0024] Reference Figure 1 The diagram shown is a flowchart illustrating an adaptive mass flow rate measurement method for shoe adhesive ratio according to an embodiment of the present invention. In this embodiment, the adaptive mass flow rate measurement method for shoe adhesive ratio includes: S1. Obtain various types of conveying materials for shoe adhesive formulation, wherein the conveying materials are located in a pre-constructed fluid conveying pipeline, and the various types of conveying materials include powder materials and liquid materials.

[0025] It should be noted that the shoe adhesive ratio refers to the proportion of multiple materials used in the production of shoe adhesive, and multiple materials refer to multiple materials used in the production of shoe adhesive. For example, there is a two-component shoe adhesive formulation, which includes multiple materials such as isophorone diisocyanate, hexamethylene diisocyanate, polyester diol, chloroprene rubber, phenolic resin, dimethylolpropionic acid, triethylamine, ethylenediamine, magnesium oxide, zinc oxide, acetone, deionized water, HDI trimer-modified polypropylene glycol monomethyl ether, and dibutyltin dilaurate. The ratio of these materials is isophorone diisocyanate: hexamethylene diisocyanate: polyester diol: chloroprene rubber: phenolic resin: dimethylolpropionic acid: triethylamine: ethylenediamine: magnesium oxide: zinc oxide: acetone: deionized water: HDI trimer-modified polypropylene glycol monomethyl ether: dibutyltin dilaurate = 95:40:200:30:15:8:6:12:8:15:90:381:198:2. In layman's terms, 1100 grams of shoe glue contains 95 grams of isophorone diisocyanate, along with 40 grams of hexamethylene diisocyanate, 200 grams of polyester diol, 30 grams of chloroprene rubber, 15 grams of phenolic resin, 8 grams of dimethylolpropionic acid, 6 grams of triethylamine, 12 grams of ethylenediamine, 8 grams of magnesium oxide, 15 grams of zinc oxide, 90 grams of acetone, 381 grams of deionized water, 198 grams of HDI trimer-modified polypropylene glycol monomethyl ether, and 2 grams of dibutyltin dilaurate.

[0026] It should be explained that the fluid transport pipeline refers to a pipeline used for transporting materials, and the transported flowing material is a material used in the production of shoe adhesives that is located in the fluid transport pipeline. The powdered material refers to a powdered material, such as magnesium oxide or zinc oxide. The liquid material refers to a liquid material, such as chloroprene rubber or phenolic resin. It is understood that the term "powdered material" is a characterization of powdered materials among multiple materials used in the production of shoe adhesives, and is not limited to a specific material. Similarly, the term "liquid material" is also a characterization of liquid materials, and is not limited to a specific material.

[0027] S2. Use a pre-built mass flow sensor set to perform charge signal acquisition on the powder flow material to obtain multiple charge signals. The mass flow sensor set includes multiple mass flow sensors.

[0028] Understandably, a mass flow sensor refers to a sensor used to acquire charge signals from powdered materials. For example, a charge sensor (mass flow sensor) is used to acquire charge signals from conveying flowing materials to obtain charge signals.

[0029] It should be understood that, due to the characteristics of powdered materials during transportation, such as powder adhesion, dust generation, and flammability and explosiveness, conventional gas or liquid flow meters cannot be used to measure the mass flow rate. Therefore, this invention utilizes a mass flow sensor to calculate the mass flow rate by using the static electricity generated by the friction of the powdered material during pipeline transportation and the fluctuation of the charge generated by this static electricity. The charge signal refers to the signal of the fluctuation of charge caused by the static electricity generated by the friction of the powdered material. The charge quantity refers to the amount of charge carried by the powdered material.

[0030] Importantly, the mass flow sensor set refers to a collection of multiple mass flow sensors. The number of mass flow sensors is even, and they are symmetrically distributed near the inlet and outlet of the fluid delivery pipeline.

[0031] Furthermore, the pre-built mass flow sensor set is used to perform charge signal acquisition on the powder flow material to obtain multiple charge signals, including: The initial charge signal of the powder flow material is acquired by using a mass flow sensor set, resulting in multiple initial charge signals; Calculate the amplitude characteristic value of each initial charge signal among multiple initial charge signals to obtain multiple amplitude characteristic values; A comprehensive amplitude feature value is calculated based on multiple amplitude feature values. Based on the comprehensive amplitude feature value, a pre-constructed gain coefficient adjustment algorithm is used to calculate the gain adjustment coefficient. Gain control is performed on multiple initial charge signals based on the gain adjustment coefficient to obtain multiple charge signals.

[0032] It is understood that the initial charge signal refers to the initial charge signal of the powder flow material collected by the mass flow sensor.

[0033] It should be explained that the initial charge signal is also the corrected original charge signal. Before using the mass flow sensor set to collect the initial charge signal of the powder flow material, it is also necessary to collect multiple influencing factors that affect the accuracy of the initial charge signal, such as the temperature, humidity and type of powder material at the location of the mass flow sensor set. Based on these multiple influencing factors, charge response correction coefficients are obtained from a pre-constructed charge response correction table. Based on these charge response correction coefficients, the original charge signal of the powder flow material collected by the mass flow sensor set is corrected to obtain the corrected original charge signal.

[0034] Importantly, the charge response correction table is a table that constructs a relationship between the charge response correction coefficient and different influencing factors based on historical data. It is used to record the charge response correction coefficient under different influencing factors such as different temperatures and different humidity levels, so as to reduce the impact of differences in influencing factors such as temperature, humidity and material type on the charge capacity of powder flow materials.

[0035] Specifically, constructing the charge response correction table involves: setting a standard operating condition; collecting charge signals under the standard operating condition and calculating their amplitude characteristic values ​​to obtain the standard amplitude; collecting charge signals under different influencing factors and calculating their amplitude characteristic values ​​to obtain the influence amplitude; dividing the standard amplitude by the influence amplitude to obtain the charge response correction coefficient; and summarizing the charge response correction coefficients under various influencing operating conditions constructed from multiple combinations of influencing factors (e.g., different combinations of influencing factors such as temperature: 25 degrees Celsius and humidity: relative humidity of 70%RH, etc., constitute one influencing operating condition) to obtain the charge response correction table. The standard operating condition can be arbitrarily selected from different combinations of influencing factors. It should be noted that the mass flow rates under all the various influencing operating conditions and the standard operating condition must be set to the same value. Only under the same mass flow rate can the charge response correction coefficient characterize the influence of multiple influencing factors on the charge capacity of the powder flow material. Then, each amplitude of the original charge signal is multiplied by the charge response correction coefficient to obtain the corrected charge signal.

[0036] It should be explained that the charge response correction table and gain tuning table are not constructed exhaustively for all combinations of temperature, humidity, and material type. Instead, they are constructed by selecting representative operating conditions and calibrating these representative conditions. Specifically, the powder flow material is first classified according to its type. For the same type of powder flow material, multiple temperatures and humidity levels are selected using methods such as Latin hypercube sampling. Each combination of temperature and humidity is considered a representative operating condition. Multiple combinations of temperatures and humidity levels are then used to construct multiple representative operating conditions for the powder flow material. Under these multiple representative operating conditions, when the mass flow rate of the powder flow material is equal, the original charge signal corresponding to each representative operating condition is collected. Based on the amplitude difference between the original charge signal and the reference charge signal under the standard operating condition, the charge response correction coefficient corresponding to each representative operating condition is calculated, thereby establishing the charge response correction table. For actual operating conditions that are not directly calibrated, multiple calibrated charge response correction coefficients and corresponding representative operating conditions and materials are extracted from the charge response correction table based on the actual temperature, actual humidity, and current material type. Curve fitting is then performed based on these calibrated charge response correction coefficients and corresponding representative operating conditions and materials to obtain the target charge response correction coefficient for the current operating condition. This avoids the need for item-by-item experimental calibration of all environmental factor combinations. The curve fitting can be achieved using existing curve fitting techniques such as least squares fitting, which will not be elaborated upon here.

[0037] In detail, the initial construction method of the gain tuning table is as follows: When the equipment is initially installed or historical data is lacking, a powder flow material is selected, and a calibrated representative operating condition is selected as the initial operating condition for table construction. Under the initial table construction condition, the mass flow rate of the powder flow material is kept stable, the original charge signal is collected, and the amplitude characteristic value of the original charge signal is calculated. Then, the amplitude characteristic value of the original charge signal is compared with the preset signal amplitude to obtain the amplitude difference. The preset signal amplitude is the average value of the amplitude characteristic values ​​of the charge signal collected multiple times under standard operating conditions.

[0038] In more detail, using existing technologies such as Latin hypercube, multiple proportional coefficients and multiple integral coefficients are selected. Each proportional coefficient and integral coefficient forms a gain combination. The original charge signal is amplified according to these gain combinations, and the amplitude characteristic value of the amplified charge signal is recorded. The set of proportional coefficients and integral coefficients with the smallest difference between the amplitude characteristic value of the gain-controlled charge signal and the preset signal amplitude is used as the initial gain parameter set corresponding to the initial operating condition. The initial material, initial operating condition, proportional coefficients, and integral coefficients are recorded in a gain tuning table. Subsequently, during subsequent production, when a new type of powder material, temperature, or humidity is acquired, the recorded proportional coefficients and integral coefficients, along with their corresponding representative operating conditions, are extracted from the gain tuning table based on the new powder material type, temperature, and humidity. Curve fitting is then performed based on the recorded proportional coefficients and integral coefficients and their corresponding representative operating conditions to obtain the proportional coefficients and integral coefficients corresponding to the current operating condition. The corresponding proportional coefficients and integral coefficients are then used to amplify the charge signal. Therefore, even in the initial operation phase where historical data is lacking, initial gain parameters can be established first, and proportional coefficients and integral coefficients under different operating conditions can be gradually obtained during subsequent operations.

[0039] It should be noted that the amplitude feature value is the root mean square of multiple amplitudes of the initial charge signal. The multiple amplitudes are obtained by discretizing the horizontal axis (i.e., time) of the initial charge signal to obtain multiple time coordinates, and obtaining the value of each time coordinate on the vertical axis of the initial charge signal to obtain multiple amplitudes. The root mean square is a prior art, and will not be elaborated here. The comprehensive amplitude feature value refers to the weighted average of multiple amplitude feature values. The weight of each amplitude feature value is obtained by first obtaining the signal-to-noise ratio (SNR) of the amplitude feature value in the initial charge signal. Then, multiple amplitude feature values ​​correspond to multiple SNRs of multiple initial charge signals. Then, Max-Min normalization is used to normalize the multiple SNRs of multiple initial charge signals to obtain multiple normalized values. The normalized value corresponding to the amplitude feature value is the weight of the amplitude feature value. Max-Min normalization is a prior art, and the method of obtaining the SNR is also a prior art, and will not be elaborated here.

[0040] It should be understood that the gain coefficient adjustment algorithm is a PI control algorithm. The PI control algorithm is a technique that combines proportional control and integral control (integral control integrates the error through integral gain and accumulates the integral result as part of the control output, while proportional control converts the error into the control output through proportional gain) to control the output and reduce the error.

[0041] Furthermore, in order to adjust the error between the amplitude of the initial charge signal and the preset amplitude, this invention first calculates the difference between the amplitude of the initial charge signal and the preset signal amplitude, uses this difference as the input of the PI control algorithm, and uses the PI control algorithm to calculate the gain adjustment coefficient, which is used to adjust the error between the amplitude of the initial charge signal and the preset signal amplitude. Then, the amplitudes of multiple initial charge signals are multiplied by the gain adjustment coefficient to obtain multiple charge signals, thereby realizing the gain control of multiple initial charge signals based on the gain adjustment coefficient, so that the multiple charge signals collected under different operating conditions have a consistent signal amplitude, improving the stability and reliability of subsequent signal processing.

[0042] Optionally, the preset signal amplitude is a signal amplitude pre-set based on historical experience data. This amplitude, determined by the optimal signal-to-noise ratio (SNR) of multiple collected charge signals based on historical experience, ensures that the multiple charge signals are at their optimal SNR. At the optimal SNR, noise interference in the charge signals is minimized, thus improving the quality of the charge signals.

[0043] Understandably, the parameters (proportional coefficient and integral coefficient) of the PI control algorithm need to be tuned according to specific operating conditions. This can be achieved by pre-setting different influencing operating conditions, collecting charge signals under different influencing conditions, and setting the calibration target as the amplitude of the charge signal under different influencing conditions approaching the preset signal amplitude, while avoiding overshoot or oscillation during the gain adjustment process. Multiple sets of candidate proportional coefficients and candidate integral coefficients are tested, and a set of proportional coefficients and integral coefficients that meet the calibration target is selected from these sets. A correspondence is established between this influencing operating condition and the selected proportional coefficient and integral coefficient, resulting in a gain tuning table. Then, when using the gain adjustment algorithm, the gain can be adjusted by using the proportional coefficient and integral coefficient corresponding to the actual operating condition in the gain tuning table.

[0044] S3. Perform preprocessing on multiple charge signals to obtain multiple preprocessed signals, including signal filtering and signal peak finding.

[0045] Furthermore, the preprocessing of multiple charge signals to obtain multiple preprocessed signals includes: For each of the multiple charge signals, perform the following operation: A low-frequency filtering operation is performed on the charge signal to obtain a high-frequency signal; Adaptive LMS filtering is performed on the high-frequency signal to obtain the filtered signal; Obtain multiple amplitude values ​​of the filtered signal; Amplitude retention operations are performed on multiple amplitudes based on pre-constructed upper and lower amplitude thresholds to obtain multiple retained amplitudes; A preprocessed signal is constructed based on multiple retained amplitude values; The preprocessed signals are summarized to obtain multiple preprocessed signals.

[0046] It should be understood that because there are low-frequency interference signals (e.g., power frequency interference) in the charge signal, a high-pass filter (e.g., IIR high-pass digital filtering algorithm) is needed to perform low-frequency filtering on the charge signal to remove the low-frequency interference signals and obtain the high-frequency signal.

[0047] It should be explained that the high-frequency signal mentioned is only the charge signal after filtering out low-frequency interference signals. It still includes high-frequency interference signals (e.g., electromagnetic pulses from motor start-up and shutdown, high-frequency harmonics from the frequency converter, and random noise from material particle collisions). The signal required by this invention is only the high-frequency signal related to the powder flow material. Therefore, adaptive LMS filtering needs to be performed on the high-frequency signal to obtain the filtered signal. The filtered signal is the signal generated by friction during the actual powder flow material transport process. The LMS adaptive filter is existing technology. By passing the high-frequency signal into an existing LMS adaptive filter, the interference signals in the high-frequency signal can be reduced according to the built-in algorithm of a conventional LMS adaptive filter. This invention will not elaborate on this further.

[0048] It is understood that obtaining multiple amplitudes of the filtered signal refers to obtaining multiple amplitudes of multiple sampling points based on the sampling frequency of the filtered signal.

[0049] Importantly, the filtered signal includes effective amplitude and interference amplitude. The effective amplitude refers to the amplitude of the charge signal generated by friction between powder materials. The interference amplitude refers to the peak value caused by accidental violent collisions between the powder material and the pipeline (e.g., the signal generated by the impact of the powder material with the pipeline during equipment startup and shutdown) or by instantaneous electromagnetic pulses from the equipment. Therefore, the material mass flow rate calculated using a filtered signal containing interference amplitude is inaccurate. This invention performs amplitude retention operations on multiple amplitudes based on pre-constructed upper and lower amplitude thresholds to obtain multiple retained amplitudes (effective amplitudes). The upper and lower amplitude thresholds include an upper amplitude limit and a lower amplitude limit, both calculated using a 3x standard deviation technique based on multiple amplitudes. The 3x standard deviation technique is prior art and will not be elaborated upon here. The retained amplitude refers to the amplitude among the multiple amplitudes that is less than or equal to the upper amplitude limit and greater than or equal to the lower amplitude limit. The interference amplitude is the amplitude among the multiple amplitudes that is greater than the upper amplitude limit or less than the lower amplitude limit.

[0050] It is clear that the construction of a preprocessed signal based on multiple retained amplitudes refers to arranging multiple retained amplitudes according to the sampling time order to obtain a sequence of retained amplitudes, and obtaining a curve of a signal through spline fitting (e.g., B-spline fitting), and the curve of the signal is denoted as the preprocessed signal.

[0051] It should be noted that due to the presence of interference amplitude, the waveform of the filtered signal has interference spikes. Therefore, the waveform of the preprocessed signal after removing the interference amplitude is the actual waveform of the charge signal generated by the friction of the powder flow material, thus providing a reliable basis for subsequent signal processing.

[0052] S4. Perform phase difference analysis on multiple preprocessed signals to obtain the signal phase difference.

[0053] Furthermore, the step of performing phase difference analysis on multiple preprocessed signals to obtain the signal phase difference includes: Multiple preprocessed signals are fused to obtain upstream and downstream signals; The time-domain phase difference is calculated based on the upstream and downstream signals using a pre-constructed formula for calculating the time-domain phase difference. Perform a Fast Fourier Transform on the upstream and downstream signals to obtain the upstream and downstream frequency domain signals; Calculate the frequency domain phase difference based on the upstream and downstream frequency domain signals; The signal phase difference is calculated based on the time-domain phase difference and the frequency-domain phase difference.

[0054] It should be noted that the signal fusion of multiple preprocessed signals refers to fusing multiple preprocessed signals obtained from multiple mass flow sensors installed at the discharge port into a downstream signal, and fusing multiple preprocessed signals obtained from multiple mass flow sensors installed at the inlet into an upstream signal.

[0055] Specifically, the process of fusing multiple preprocessed signals obtained from multiple mass flow sensors near the discharge port into a downstream signal involves calculating the standard deviation of each preprocessed signal to obtain multiple preprocessed signal standard deviations. The standard deviation of a preprocessed signal represents the quality of the preprocessed signal; the smaller the standard deviation, the better the quality of the preprocessed signal. Therefore, the multiple preprocessed signal standard deviations are recorded as multiple signal weights, and a weighted average is performed on the multiple signal weights and the multiple preprocessed signals to obtain the downstream signal.

[0056] It is understood that the process of fusing multiple preprocessed signals obtained from multiple mass flow sensors near the feed inlet into an upstream signal is the same as the process of fusing multiple preprocessed signals obtained from multiple mass flow sensors near the discharge outlet into a downstream signal, and will not be described in detail here.

[0057] It should be explained that calculating the time-domain phase difference using the pre-constructed formula for calculating the time-domain phase difference involves substituting multiple amplitude values ​​of the upstream signal and multiple amplitude values ​​of the downstream signal into the formula for calculating the cross-correlation function, calculating multiple cross-correlation values ​​based on the pre-constructed time-domain delay range, determining the time-domain delay corresponding to the maximum value among the multiple cross-correlation values, and then substituting the time-domain delay and sampling frequency into the formula for calculating the time-domain phase difference to calculate the time-domain phase difference. The number of amplitude values ​​of the upstream signal is equal to the number of amplitude values ​​of the downstream signal. The formula for calculating the cross-correlation function is shown below:

[0058] in, Indicates the cross-correlation value. This indicates the number of multiple amplitude values ​​of the upstream signal. The first of multiple amplitude values ​​of the upstream signal Each amplitude, The first of multiple amplitude values ​​of the upstream signal Index of each amplitude value Represents multiple amplitude values ​​of the downstream signal. Each amplitude value. This indicates time-domain delay.

[0059] Specifically, multiple cross-correlation values ​​can be calculated based on the range of the time-domain delay. The larger the cross-correlation value, the higher the similarity between the upstream and downstream signals; that is, at a certain time delay (time-domain delay), the waveforms of the upstream and downstream signals are more similar. The formula for calculating the time-domain phase difference is as follows:

[0060] in, Represents the phase difference in the time domain. Represents pi (π). Indicates the frequency of the upstream signal. This represents the time-domain delay corresponding to the maximum value among multiple cross-correlation values. This represents the sampling period, which is the reciprocal of the sampling frequency.

[0061] It should be explained that the time-domain delay refers to the difference in similarity between the upstream and downstream signals in their waveforms. For example, if the upstream and downstream signals match in waveform after 1 second, then 1 second is recorded as the time-domain delay. Since it is impossible to find a definite time-domain delay between the actual upstream and downstream signals to make them completely identical in waveform, a time-domain delay range needs to be preset to find the maximum cross-correlation value, that is, the maximum similarity between the upstream and downstream signals in waveform. The time-domain delay range is a range set manually based on the waveforms of the upstream and downstream signals.

[0062] In detail, the calculation of signal phase difference in the time domain is easily affected by on-site electromagnetic noise and material flow disturbances, resulting in inaccurate time domain phase difference results. Frequency domain analysis can extract the phase characteristics of the signal at different frequencies, effectively filtering noise interference and improving the accuracy of signal phase difference calculation. Therefore, this invention performs Fast Fourier Transform on the upstream and downstream signals. Through Fast Fourier Transform, the upstream and downstream signals in the time domain are converted into upstream and downstream frequency domain signals containing amplitude and phase information at different frequencies, respectively. The frequency domain phase difference is calculated based on the upstream and downstream frequency domain signals, and then combined with the time domain phase difference to calculate a more accurate signal phase difference.

[0063] It should be noted that the calculation of frequency domain phase difference based on upstream and downstream frequency domain signals refers to the calculation of the cross-spectral function of the upstream and downstream frequency domain signals, and the calculation of frequency domain phase difference based on the cross-spectral function. The cross-spectral function is existing technology and will not be described in detail here.

[0064] It should be explained that the time-domain phase difference represents the time difference between the upstream and downstream signals in the time domain, while the frequency-domain phase difference represents the time difference between the upstream and downstream signals in the frequency domain.

[0065] It should be understood that the signal phase difference is a weighted average of the frequency domain phase difference and the time domain phase difference. The weight of the frequency domain phase difference is the normalized value of the average signal-to-noise ratio (SNR) of the upstream frequency domain signal and the downstream frequency domain signal, and the time domain phase difference is the normalized value of the average SNR of the upstream signal and the downstream signal. Using Max-Min normalization to normalize the average SNR of the upstream and downstream frequency domain signals is a prior art technique, and will not be elaborated upon here.

[0066] It is clear that the signal phase difference is the weighted average of the time difference between the upstream and downstream signals in the time and frequency domains, representing the time difference in the transport of powdered material in the pipeline from the inlet to the outlet.

[0067] S5. Obtain the physical spacing and sampling frequency of multiple preprocessed signals. Based on the signal phase difference, physical spacing and sampling frequency, calculate the preliminary powder flow mass flow using the pre-constructed calculation formula. Based on the preliminary powder flow mass flow, complete the powder flow mass flow measurement for shoe adhesive formulation.

[0068] It should be noted that the physical spacing refers to the distance between multiple mass flow sensors corresponding to multiple preprocessed signals.

[0069] For example, there are a first preprocessed signal, a second preprocessed signal, a third preprocessed signal, and a fourth preprocessed signal, and there are a first mass flow sensor, a second mass flow sensor, a third mass flow sensor, and a fourth mass flow sensor. The first preprocessed signal is a charge signal collected and preprocessed by the first mass flow sensor, and so on, the second preprocessed signal is a charge signal collected and preprocessed by the second mass flow sensor, the third preprocessed signal is a charge signal collected and preprocessed by the third mass flow sensor, and the fourth preprocessed signal is a charge signal collected and preprocessed by the fourth mass flow sensor. Assuming the pipeline is approximately fitted to a circle, the first and second mass flow sensors are located side by side at the inlet (which can be approximated as the centroids of the first and second mass flow sensors being located on the same circular cross-section at the pipeline inlet, in which case the distance between the first and second mass flow sensors is 0). Similarly, the third and fourth mass flow sensors are located side by side at the outlet. The line connecting the first and third mass flow sensors is perpendicular to the line connecting the first and second mass flow sensors. Therefore, the physical distance is the distance between the first and third mass flow sensors, or the distance between the second and fourth mass flow sensors.

[0070] It should be understood that the sampling frequency refers to the sampling frequency of the mass flow sensor. For example, if the mass flow sensor collects charge signals 100 times per second, the sampling frequency is 100 Hz.

[0071] Understandably, multiple mass flow sensors have the same sampling frequency, thus enabling signal fusion of the multiple charge signals. The preliminary material mass flow rate refers to the mass flow rate of the powdered material calculated based on the signal phase difference, physical spacing, and sampling frequency.

[0072] Importantly, the formula for calculating the initial powder flow mass flow rate is as follows:

[0073] in, This indicates the initial material mass flow rate. Indicates the initial material flow rate. Indicates the sampling frequency. Indicates physical spacing. Indicates the signal phase difference. Indicates the density of the powdered material. This indicates the cross-sectional area of ​​the powder.

[0074] It is understood that the density of the powder flow material is the density of the powder flow material, and the detection of the density of the powder flow material is an existing technology, including but not limited to the existing technology of bulk density detection, true density detection, gas displacement method, impregnation method, or real-time detection by online density sensors, etc., which will not be elaborated here. The cross-sectional area of ​​the powder is the cross-sectional area of ​​the outlet of the fluid conveying pipeline in which the powder flow material is located.

[0075] It should be explained that the preliminary material flow rate refers to the flow rate of the powder flow material calculated based on the sampling frequency, physical spacing and signal phase difference. The preliminary material flow rate is the average flow rate of the powder flow material calculated by dividing the charge signal measured by the mass flow sensor set. It is used to multiply the powder cross-sectional area and the density of the powder flow material to obtain the mass flow rate of the powder flow material (preliminary powder flow mass flow rate).

[0076] Importantly, the measurement of powder flow mass flow rate for shoe adhesive formulation based on preliminary powder flow mass flow rate refers to predicting the powder flow mass flow rate based on the preliminary powder flow mass flow rate.

[0077] Specifically, since the preliminary powder flow mass flow rate is obtained by preprocessing the charge signal collected by the mass flow sensor set, and the charge signal has a phase jump problem, the calculated preliminary material mass flow rate is not the actual mass flow rate of the powder flow. Therefore, this invention uses Kalman filtering to predict the actual mass flow rate of the powder flow (powder flow mass flow rate) based on the preliminary material mass flow rate. Kalman filtering is prior art, and will not be described in detail here.

[0078] In detail, the specific process of predicting the actual powder flow mass flow rate of the powder flow material using Kalman filtering based on the preliminary material mass flow rate is as follows: Kalman filtering predicts the powder flow mass flow rate at the current moment based on the previous estimated powder flow mass flow rate. The predicted powder flow mass flow rate at the current moment is compared with the preliminary powder flow mass flow rate to obtain the difference. The Kalman filter is corrected based on the difference. The powder flow mass flow rate at the current moment is estimated based on the corrected Kalman filter to obtain the optimal estimated value of the powder flow mass flow rate at the current moment (powder flow mass flow rate).

[0079] S6. Perform liquid mass flow rate measurement on the liquid flow material to obtain the preliminary liquid flow rate, and complete the liquid flow rate measurement for shoe adhesive formulation based on the preliminary liquid flow rate.

[0080] It is understood that the preliminary liquid flow mass flow rate refers to the preliminary mass flow rate of the liquid material. The process of measuring the liquid flow mass flow rate for shoe adhesive formulation based on the preliminary liquid flow mass flow rate is the same as the process of measuring the powder flow mass flow rate for shoe adhesive formulation based on the preliminary powder flow mass flow rate, and will not be described again here.

[0081] Furthermore, the step of performing liquid mass flow rate measurement on the liquid flow material to obtain the preliminary liquid flow mass flow rate includes: Perform time-series-based image acquisition on the liquid flow material to obtain multiple continuous material images; Perform image preprocessing operations on multiple consecutive material images to obtain multiple processed images; Perform pairwise combination operations on multiple processed images to obtain multiple image combinations. Each image combination includes a processed image and adjacent processed images. The adjacent processed images are processed images that are adjacent to the processed image and lag behind it. Preliminary liquid flow mass flow rate calculations are performed based on pixel displacement analysis using a combination of multiple images, resulting in multiple preliminary liquid flow mass flow rates.

[0082] It should be noted that the image acquisition operation refers to the operation of using a high-definition camera to capture images of the liquid flow material inside the pipe through a transparent window. The multiple consecutive material images refer to multiple images of the liquid flow material acquired at fixed sampling intervals and then arranged in a temporal sequence. The sampling interval refers to the time interval between two image acquisitions; for example, if the time interval between two image acquisitions is 1 second, then the sampling interval is 1 second. The temporal arrangement refers to arranging the liquid flow material images acquired multiple times in the order of their acquisition time. It should be understood that the image coordinate system of the continuous material images (e.g., ...) Figure 4 The graph (shown) is a coordinate system with the direction of liquid material transport as the horizontal axis, the direction from the inlet to the outlet as the positive direction of the horizontal axis, and the direction perpendicular to the direction of liquid material transport as the vertical axis.

[0083] It should be explained that the image preprocessing operation on multiple consecutive material images refers to performing grayscale conversion, median filtering, and Gaussian filtering operations on each of the multiple consecutive material images to obtain multiple processed images. Grayscale conversion, median filtering, and Gaussian filtering are all existing technologies, and will not be described in detail here.

[0084] It should be understood that the multiple continuous material images are all images of multiple liquid flow materials that have passed image quality detection. To avoid blurring of the continuous material images due to liquid flow material adhering to the inside of the transparent window, after obtaining multiple initial liquid flow material images, this invention also uses existing techniques such as the Laplace variance method to calculate the sharpness of the multiple initial liquid flow material images. When the image sharpness is less than a preset sharpness threshold, it is determined that the multiple initial liquid flow material images do not meet the pixel displacement analysis conditions. A cleaning component (such as an automatic brush similar to a windshield wiper) set at the transparent window is then controlled to perform a cleaning operation on the transparent window, thereby re-acquiring multiple liquid flow material images. These re-acquired images are used as the multiple initial liquid flow materials, and the process of calculating the sharpness of the multiple initial liquid flow material images using the Laplace variance method is repeated until the image sharpness is greater than or equal to the preset sharpness threshold, thus obtaining multiple continuous material images. It should be noted that the sharpness threshold is the sharpness of a qualified material image. The qualified material image refers to an image that, through the transparent window, can clearly identify markers and the flow of liquid flow material during historical production processes. The clarity of images of qualified materials can be calculated using existing techniques such as the Laplace variance method, which will not be elaborated upon here.

[0085] Furthermore, the transparent window comprises multiple enclosed transparent observation windows spaced at intervals along the liquid material conveying direction on the side wall of the liquid material conveying pipeline, such as multiple double-valve-stem straight-through sight glasses. During normal operation, the two valve stems of the double-valve-stem straight-through sight glasses are open, allowing material to continuously pass through the main flow channel of the sight glass body. The image acquisition device can observe the liquid material within the pipeline through the glass window. When the glass window needs to be replaced, the two valve stems are operated to close the corresponding isolation structure, thereby isolating the area where the glass window is located from the liquid material in the main flow channel. Since the main flow channel remains open, the liquid material can continue to be conveyed from the inlet to the outlet. Therefore, the effective flow cross-sectional area of ​​the liquid material conveying pipeline is not changed, the predetermined conveying path of the liquid material is not disrupted, and the feeding process and flow state of the liquid material are not interfered with. Simultaneously, multiple double-valve-stem straight-through sight glasses can be installed. When one double-valve-stem straight-through sight glass is replaced, image acquisition is performed through the remaining double-valve-stem straight-through sight glasses to continuously monitor the mass flow rate of the liquid material. Furthermore, the lens of the through-view mirror is far from the actual liquid surface, making it less susceptible to contamination by splashing liquid. The liquid flow is slow and has high viscosity, further reducing splashing. Additionally, a coating on the lens reduces the adhesion of liquid flow to the inner surface of the transparent window, minimizing obstruction of the image acquisition unit's field of view. This coating can be a polytetrafluoroethylene (PTFE) coating, a hydrophobic or oleophobic coating, or other transparent, solvent-resistant, and non-stick coating. When the transparent window lacks an anti-adhesion coating, image acquisition switching between multiple dual-valve through-view mirrors ensures at least one transparent window meeting clarity requirements is used for liquid flow image acquisition. When the transparent window has an anti-adhesion coating, the adhesion of liquid flow to the inner surface of the transparent window is further reduced, improving the image acquisition stability of a single dual-valve through-view mirror. Therefore, the combination of multiple dual-valve through-view mirrors ensures continuous image acquisition, while the anti-adhesion coating reduces the probability of blurred transparent windows; both can be used individually or in combination.

[0086] It is understood that the image combination is the result of performing a pairwise combination operation on multiple processed images. The pairwise combination refers to the operation of sliding extraction in multiple continuous material images, using two consecutive material images as the sliding window size and one consecutive material image as the sliding step size, so that each extracted image combination includes two consecutive material images.

[0087] For example, if there exists {first processed image, second processed image, third processed image, fourth processed image}, then a pairwise combination operation is performed on the multiple processed images to obtain multiple image combinations. The multiple image combinations are respectively the first image combination {first processed image, second processed image}, the second image combination {second processed image, third processed image}, and the third image combination {third processed image, fourth processed image}. In the first image combination, the first processed image is the processed image, the second processed image is the adjacent processed image, and so on. The remaining image combinations will not be described in detail here.

[0088] Furthermore, the preliminary liquid flow mass flow rate calculation based on pixel displacement analysis using multiple image combinations yields multiple preliminary liquid flow mass flow rates, including: For each of the multiple image combinations, perform the following operation: Perform liquid flow material region recognition on the processed image and adjacent processed images to obtain processed material region images and adjacent material region images; Pixel displacement analysis is performed on the image of the processed material area and the image of the adjacent material area to obtain multiple pixel flow displacement vectors; The average displacement vector is obtained by averaging the flow displacement vectors of multiple pixels. Obtain the time difference between the processed image and adjacent processed images, and calculate the average pixel velocity based on the time difference and the average displacement vector; Calculate the initial liquid flow mass flow rate based on the average pixel velocity; By summing the initial liquid flow mass flow rates, multiple initial liquid flow mass flow rates are obtained.

[0089] Specifically, the process of identifying liquid flow material regions in the processed image and adjacent processed images involves using the Otsu method to perform region segmentation on both the processed image and adjacent processed images, resulting in processed material region images and adjacent material region images. The processed material region image corresponds to the image of the liquid flow material in the processed image, and the adjacent material region image corresponds to the image of the liquid flow material in the adjacent processed image. The Otsu method is existing technology and will not be described in detail here.

[0090] Furthermore, the pixel displacement analysis performed on the processed material region image and adjacent material region images yields multiple pixel flow displacement vectors, including: Based on the material area image and adjacent material area images, a marker recognition operation is performed to obtain the coordinates of multiple markers and multiple adjacent markers; Based on multiple marker coordinates and multiple adjacent marker coordinates, multiple material image regions and multiple adjacent image regions are extracted from the processed image and adjacent processed images, respectively. Among them, the material image regions correspond one-to-one with the marker coordinates, and the adjacent image regions correspond one-to-one with the adjacent marker coordinates. Extract material image regions one by one from the material image regions to obtain the target material region, and perform the following operations on the target material region: Identify the adjacent image regions corresponding to the target material region in multiple adjacent image regions to obtain the target adjacent region; Obtain the maximum adjacent material region based on the target material region and the target adjacent region; The center coordinates of the largest adjacent material region and the target material region are obtained respectively. The maximum center coordinates and the target center coordinates are obtained. The pixel flow displacement vector is calculated based on the maximum center coordinates and the target center coordinates. By summing the pixel flow displacement vectors, we obtain multiple pixel flow displacement vectors corresponding to multiple marker coordinates.

[0091] It should be noted that the marker recognition operation based on the material area image and adjacent material area images refers to using FAST corner detection to identify multiple markers in the material area image and multiple adjacent markers in adjacent material areas. The coordinates of multiple markers are obtained based on the pixel coordinates of the multiple markers and multiple adjacent markers in the image coordinate system of the material area image, and the coordinates of multiple adjacent markers are obtained based on the pixel coordinates of the multiple adjacent markers in the image coordinate system of the adjacent material areas. The markers are substances added to the liquid flow material that differ from the liquid flow material and can be detected by FAST corner detection. Examples of markers include magnesium carbonate, silica, or titanium dioxide. FAST corner detection is existing technology and will not be elaborated upon here. Specifically, the added markers are all substances that do not affect the production of shoe adhesive, or are materials used in shoe adhesive production. Because the amount of material added (mass flow rate of the liquid material) needs to be controlled, the flow rate of the liquid material cannot be too fast; otherwise, even a small system error (pipe vibration, etc.) will affect the accuracy of the amount of material added and disrupt the shoe adhesive formulation. Therefore, two consecutive material images acquired at a suitable sampling frequency can basically characterize the displacement of the marker at a fixed time interval, that is, the displacement of the liquid flow material.

[0092] It should be noted that the marker can be a material with a density similar to that of the liquid material, so that the marker will not sink or float in the liquid material due to density differences, thus failing to approximate the flow of the liquid material. Simultaneously, the size of the marker needs to be controlled; it needs to be small enough to flow with the liquid material, yet large enough to be identifiable in the processed image. Furthermore, surface modification can be used to prevent the marker from agglomerating or adhering to the wall surface.

[0093] Specifically, the material image region is a certain area extracted from the processed image, centered on the coordinates of the marker. The adjacent image region is a certain area extracted from adjacent processed images, centered on the coordinates of adjacent markers. The adjacent image region is larger than the material image region.

[0094] In detail, confirming the adjacent image regions corresponding to the target material region in multiple adjacent image regions refers to identifying multiple markers in multiple adjacent image regions based on the markers corresponding to the target material region, comparing the markers in the target material region with the multiple markers, finding the markers that are identical to the markers in the target material region, and determining their corresponding adjacent image regions. Image recognition is existing technology, and will not be elaborated upon here.

[0095] Furthermore, obtaining the maximum adjacent material region based on the target material region and the target adjacent region includes: Obtain the grayscale values ​​of multiple target pixels in the target material region, and obtain multiple adjacent material regions from the target adjacent region based on the target material region; For each of multiple adjacent material regions, perform the following operation: Obtain the gray values ​​of multiple adjacent pixels in the adjacent material region, and calculate the correlation coefficient based on the gray values ​​of multiple adjacent pixels and multiple target pixels using a pre-constructed formula for calculating the correlation coefficient. Summarize the correlation coefficients to obtain multiple correlation coefficients, and extract the maximum value from the multiple correlation coefficients to obtain the maximum correlation coefficient; Identify the adjacent material region corresponding to the largest correlation coefficient among multiple adjacent material regions to obtain the largest adjacent material region.

[0096] Understandably, the grayscale values ​​of multiple target pixels are the grayscale values ​​of multiple pixels in the target material area.

[0097] It should be explained that the process of obtaining multiple adjacent material regions from the target adjacent region based on the target material region refers to using the range of the target material region as a sliding window and n pixels as the sliding step size to traverse the target adjacent region in order to extract multiple adjacent material regions from the target adjacent region. The range of the target material region is the same as the range of the adjacent material regions.

[0098] For example, assuming the target material area is 2 pixels × 2 pixels and the sliding step is 1 pixel, and the target adjacent area is 3 pixels × 3 pixels, then the first adjacent material area is extracted as the first row to the second row and the first column to the second column of the target adjacent area, the second adjacent material area is extracted as the first row to the second row and the second column to the third column of the target adjacent area, the third target adjacent area is extracted as the second row to the third row and the first column to the second column, and the fourth target adjacent area is extracted as the second row to the third row and the second column to the third column.

[0099] It should be understood that the multiple adjacent pixel grayscale values ​​refer to the grayscale values ​​of multiple pixels in adjacent material regions. The correlation coefficient is a value calculated using the correlation coefficient calculation formula, representing the similarity between the adjacent material region and the target material region. The larger the correlation coefficient, the greater the similarity between the adjacent material region and the target material region, and the greater the probability that the adjacent material region is the moved target material region. Therefore, this invention extracts the maximum value from multiple correlation coefficients and confirms the adjacent material region corresponding to the largest correlation coefficient among multiple adjacent material regions as the largest adjacent material region.

[0100] Furthermore, the formula for calculating the correlation coefficient is as follows: ; in, Represents the correlation coefficient. Represents the grayscale value of multiple target pixels. grayscale value of each target pixel Represents the grayscale value of multiple target pixels. The index of the grayscale value of the target pixel This represents the average grayscale value of multiple target pixels. Represents the gray value of a plurality of adjacent pixels. grayscale values ​​of adjacent pixels This represents the average grayscale value of multiple adjacent pixels. This represents the total number of grayscale values ​​for multiple target pixels.

[0101] Importantly, obtaining the center coordinates of the maximum adjacent material region and the target material region involves calculating the average of multiple pixel coordinates in the maximum adjacent material region as the maximum center coordinate, and calculating the average of multiple pixel coordinates in the target material region as the target center coordinate. Since the horizontal axis of the image coordinate system represents the direction of liquid flow, the flow velocity of the liquid flow can be calculated based on the change in the horizontal axis and the time difference. Therefore, calculating the pixel flow displacement vector based on the maximum center coordinate and the target center coordinate involves calculating the difference between the horizontal coordinate of the maximum center coordinate and the horizontal coordinate of the target center coordinate, and constructing a vector from the horizontal coordinates of the maximum center coordinate and the target center coordinate based on this difference to obtain the pixel flow displacement vector.

[0102] It should be understood that the average displacement vector refers to the average value of the displacement vectors of multiple pixels, and the time difference refers to the sampling interval. The calculation of the average pixel velocity based on the time difference and the average displacement vector means dividing the average displacement vector by the time difference to obtain the average pixel velocity. Since the average pixel velocity is the velocity calculated based on the sampling interval using the average displacement vector (the number of pixels that move the marker in the image coordinate system), it is the velocity in the image coordinate system, i.e., the velocity of the liquid flow material in the image. Therefore, it is necessary to adjust the ratio according to the unit pixel size to amplify the velocity of the liquid flow material in the image to the actual flow rate of the liquid flow material in reality. Furthermore, the calculation of the preliminary liquid flow mass flow rate based on the average pixel velocity means multiplying the average pixel velocity by the unit pixel size to obtain the preliminary liquid flow rate, and then calculating the preliminary liquid flow mass flow rate using a pre-constructed preliminary liquid flow mass flow rate calculation formula based on the preliminary liquid flow rate. Here, the unit pixel size refers to the actual physical size occupied by one pixel. The preliminary liquid flow mass flow rate calculation formula is as follows:

[0103] in, This indicates the initial liquid flow rate. Indicates the initial liquid flow rate. Indicates the density of the liquid flow material. This represents the cross-sectional area of ​​the liquid.

[0104] Specifically, the density of the liquid flow material refers to the density of the liquid flow material. The method for detecting the density of the liquid flow material is the same as the method for detecting the density of the powder flow material, and will not be repeated here. The cross-sectional area of ​​the liquid represents the cross-sectional area of ​​the outlet of the fluid conveying pipeline in which the liquid flow material is located.

[0105] Furthermore, the step of measuring the liquid flow mass flow rate for shoe adhesive formulation based on the initial liquid flow mass flow rate further includes: The system aggregates the mass flow rates of powder and liquid streams, and dynamically adjusts the material delivery ratio based on these rates to control the shoe adhesive formulation. Specifically, the addition amounts of multiple materials are calculated in real time using the powder and liquid mass flow rates. Simultaneously, component analysis instruments (e.g., Fourier transform infrared spectrometers) are used to analyze the produced shoe adhesive, obtaining multiple shoe adhesive components. These components are compared with the shoe adhesive formulation to calculate the deviation between the actual proportions of the materials and the actual proportions. Based on these deviations, corresponding mass flow rate adjustment commands are generated. If the actual proportion of a material is greater than the shoe adhesive formulation, the mass flow rate of that material is reduced; if it is less, it is increased; and if it is equal, no adjustment is needed. This dynamic flow rate adjustment ensures that the actual proportion of the produced shoe adhesive closely approximates the formulation, guaranteeing continuous shoe adhesive production and consistent product quality.

[0106] It should be noted that the outlets of the fluid conveying pipes corresponding to different materials are all connected to the shoe glue production machine. The shoe glue production machine will stir and blend the various materials. Therefore, when the mass flow rate of the fluid conveying pipe corresponding to a certain material is reduced, the mass of that material added to the shoe glue production machine per unit time (e.g., 1 second) will be reduced. When the mass flow rate of the fluid conveying pipe corresponding to a certain material is increased, the mass of that material added to the shoe glue production machine per unit time (e.g., 1 second) will be increased. Thus, the present invention controls the shoe glue ratio by controlling the mass flow rate of different materials.

[0107] To address the problems described in the background art, this invention obtains multiple types of conveying materials for shoe adhesive formulation. These materials are situated within a pre-constructed fluid conveying pipeline. The multiple types of conveying materials include powder flow materials and liquid flow materials. A pre-constructed mass flow sensor set is used to acquire charge signals from the powder flow materials, resulting in multiple charge signals. These charge signals are then pre-processed to obtain multiple pre-processed signals, including signal filtering and peak finding. Phase difference analysis is performed on the pre-processed signals to obtain the signal phase difference. The physical spacing and sampling frequency of the pre-processed signals are then obtained. Based on the signal phase difference, physical spacing, and sampling frequency, a preliminary powder flow mass flow rate is calculated using a pre-constructed formula. The powder flow mass flow rate for shoe adhesive formulation is then measured based on this preliminary powder flow mass flow rate. Similarly, liquid flow mass flow rate measurement is performed on the liquid flow materials to obtain a preliminary liquid flow mass flow rate. Finally, the liquid flow mass flow rate for shoe adhesive formulation is measured based on this preliminary liquid flow mass flow rate. This invention selects different mass flow rate detection methods for different materials based on their physical form, adapting to materials with significantly different physical forms, such as powder and liquid, to achieve adaptive detection of material mass flow rate. If the conveyed material is a powder, a mass flow sensor is used to collect the charge signals generated by friction. Preprocessing multiple charge signals effectively filters out noise interference, providing high-quality signals for subsequent analysis. Phase difference analysis is then performed on the preprocessed signals, and combined with the sensor's physical spacing and sampling frequency, the mass flow rate of the powder is accurately calculated. This method effectively solves the problem of direct measurement of powder materials using traditional flowmeters due to their tendency to adhere and generate dust. If the conveyed material is a liquid, a time-series-based image acquisition and analysis method is used for mass flow rate measurement. By acquiring continuous material images, identifying liquid material regions, and performing pixel displacement analysis, the liquid mass flow rate is finally calculated, achieving non-contact, high-precision mass flow rate detection of liquid materials. Based on the measured material mass flow rate, adaptive detection of material mass flow rate during shoe adhesive mixing is achieved. Finally, as can be seen in the embodiments of the present invention, the present invention also achieves mass flow rate adjustment by summarizing the mass flow rates of each material and based on the component ratio of the shoe adhesive, thereby controlling the shoe adhesive ratio and ensuring production continuity and product quality consistency. Therefore, the present invention can improve the control accuracy of the shoe adhesive ratio and ensure production continuity and product quality consistency by accurately detecting the mass flow rate in real time and adjusting the mass flow rate according to the component ratio of the shoe adhesive.

[0108] like Figure 2 The diagram shown is a functional block diagram of an adaptive mass flow rate measurement system for shoe adhesive ratio provided in an embodiment of the present invention.

[0109] The adaptive mass flow rate measurement system 100 for shoe adhesive formulation described in this invention can be installed in an electronic device. Depending on the functions implemented, the adaptive mass flow rate measurement system 100 for shoe adhesive formulation may include a material conveying module 101, a signal acquisition module 102, a powder mass flow rate measurement module 103, and a liquid mass flow rate measurement module 104. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0110] The material conveying module 101 is used to acquire multiple types of conveying materials for shoe adhesive formulation, wherein the conveying materials are located in a pre-constructed fluid conveying pipeline, and the multiple types of conveying materials include powder materials and liquid materials. The signal acquisition module 102 is used to perform charge signal acquisition on the powder flow material using a pre-constructed mass flow sensor set to obtain multiple charge signals, wherein the mass flow sensor set includes multiple mass flow sensors. The powder mass flow rate measurement module 103 is used to perform preprocessing on multiple charge signals to obtain multiple preprocessed signals. The preprocessing includes signal filtering and signal peak finding. Phase difference analysis is performed on the multiple preprocessed signals to obtain the signal phase difference. The physical spacing and sampling frequency of the multiple preprocessed signals are obtained. Based on the signal phase difference, physical spacing and sampling frequency, the preliminary powder flow rate is calculated using a pre-constructed calculation formula. Based on the preliminary powder flow rate, the powder flow rate measurement for shoe adhesive formulation is completed. The liquid mass flow rate measurement module 104 is used to perform liquid mass flow rate measurement on the liquid flow material to obtain a preliminary liquid flow rate, and to complete the liquid flow rate measurement for shoe adhesive formulation based on the preliminary liquid flow rate.

[0111] In detail, the modules in the adaptive mass flow rate measurement system 100 for shoe adhesive ratio described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The method used is the same as the adaptive measurement method for mass flow rate of shoe adhesive ratio described in the previous section, and can produce the same technical effect, so it will not be repeated here.

[0112] like Figure 3 The diagram shown is a schematic representation of an electronic device for implementing an adaptive mass flow rate measurement method for shoe adhesive ratio, according to an embodiment of the present invention.

[0113] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a mass flow rate adaptive measurement method program for shoe adhesive ratio.

[0114] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as code for a mass flow adaptive measurement method program for shoe adhesive ratios, but also to temporarily store data that has been output or will be output.

[0115] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device via various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a mass flow rate adaptive measurement method program for shoe adhesive ratios) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0116] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0117] Figure 3 Only electronic devices with components are shown; those skilled in the art will understand that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0118] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0119] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0120] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0121] The adaptive measurement method program for shoe adhesive ratio, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following: Obtain various types of conveying materials for shoe adhesive formulation, wherein the conveying materials are located in a pre-constructed fluid conveying pipeline, and the various types of conveying materials include powder materials and liquid materials; A pre-built mass flow sensor set is used to perform charge signal acquisition on powdered material to obtain multiple charge signals. The mass flow sensor set includes multiple mass flow sensors. Multiple charge signals are preprocessed to obtain multiple preprocessed signals, including signal filtering and signal peak finding. Phase difference analysis is performed on multiple preprocessed signals to obtain the signal phase difference; The physical spacing and sampling frequency of multiple preprocessed signals are obtained. Based on the signal phase difference, physical spacing and sampling frequency, the preliminary powder flow mass flow rate is calculated using a pre-constructed calculation formula. Based on the preliminary powder flow mass flow rate, the powder flow mass flow rate measurement for shoe adhesive formulation is completed. Liquid mass flow rate is measured for the liquid material to obtain a preliminary liquid mass flow rate. Based on the preliminary liquid mass flow rate, the liquid mass flow rate for shoe adhesive formulation is measured.

[0122] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 4 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0123] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0124] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: Obtain various types of conveying materials for shoe adhesive formulation, wherein the conveying materials are located in a pre-constructed fluid conveying pipeline, and the various types of conveying materials include powder materials and liquid materials; A pre-built mass flow sensor set is used to perform charge signal acquisition on powdered material to obtain multiple charge signals. The mass flow sensor set includes multiple mass flow sensors. Multiple charge signals are preprocessed to obtain multiple preprocessed signals, including signal filtering and signal peak finding. Phase difference analysis is performed on multiple preprocessed signals to obtain the signal phase difference; The physical spacing and sampling frequency of multiple preprocessed signals are obtained. Based on the signal phase difference, physical spacing and sampling frequency, the preliminary powder flow mass flow rate is calculated using a pre-constructed calculation formula. Based on the preliminary powder flow mass flow rate, the powder flow mass flow rate measurement for shoe adhesive formulation is completed. Liquid mass flow rate is measured for the liquid material to obtain a preliminary liquid mass flow rate. Based on the preliminary liquid mass flow rate, the liquid mass flow rate for shoe adhesive formulation is measured.

[0125] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0126] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0127] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0128] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An adaptive mass flow rate measurement method for shoe adhesive formulation, characterized in that, The method includes: Obtain various types of conveying materials for shoe adhesive formulation, wherein the conveying materials are located in a pre-constructed fluid conveying pipeline, and the various types of conveying materials include powder materials and liquid materials; A pre-built mass flow sensor set is used to perform charge signal acquisition on powdered material to obtain multiple charge signals. The mass flow sensor set includes multiple mass flow sensors. Multiple charge signals are preprocessed to obtain multiple preprocessed signals, including signal filtering and signal peak finding. Phase difference analysis is performed on multiple preprocessed signals to obtain the signal phase difference; The physical spacing and sampling frequency of multiple preprocessed signals are obtained. Based on the signal phase difference, physical spacing and sampling frequency, the preliminary powder flow mass flow rate is calculated using a pre-constructed calculation formula. Based on the preliminary powder flow mass flow rate, the powder flow mass flow rate measurement for shoe adhesive formulation is completed. Liquid mass flow rate is measured for the liquid material to obtain a preliminary liquid mass flow rate. Based on the preliminary liquid mass flow rate, the liquid mass flow rate for shoe adhesive formulation is measured.

2. The adaptive mass flow rate measurement method for shoe adhesive formulation as described in claim 1, characterized in that, The process involves using a pre-built mass flow sensor set to acquire charge signals from the powder flow material, resulting in multiple charge signals, including: The initial charge signal of the powder flow material is acquired by using a mass flow sensor set, resulting in multiple initial charge signals; Calculate the amplitude characteristic value of each initial charge signal among multiple initial charge signals to obtain multiple amplitude characteristic values; A comprehensive amplitude feature value is calculated based on multiple amplitude feature values. Based on the comprehensive amplitude feature value, a pre-constructed gain coefficient adjustment algorithm is used to calculate the gain adjustment coefficient. Gain control is performed on multiple initial charge signals based on the gain adjustment coefficient to obtain multiple charge signals.

3. The adaptive mass flow rate measurement method for shoe adhesive ratio as described in claim 2, characterized in that, The preprocessing of multiple charge signals yields multiple preprocessed signals, including: For each of the multiple charge signals, perform the following operation: A low-frequency filtering operation is performed on the charge signal to obtain a high-frequency signal; Adaptive LMS filtering is performed on the high-frequency signal to obtain the filtered signal; Obtain multiple amplitude values ​​of the filtered signal; Amplitude retention operations are performed on multiple amplitudes based on pre-constructed upper and lower amplitude thresholds to obtain multiple retained amplitudes; A preprocessed signal is constructed based on multiple retained amplitude values; The preprocessed signals are summarized to obtain multiple preprocessed signals.

4. The adaptive mass flow rate measurement method for shoe adhesive formulation as described in claim 3, characterized in that, The step of performing phase difference analysis on multiple preprocessed signals to obtain the signal phase difference includes: Multiple preprocessed signals are fused to obtain upstream and downstream signals; The time-domain phase difference is calculated based on the upstream and downstream signals using a pre-constructed formula for calculating the time-domain phase difference. Perform a Fast Fourier Transform on the upstream and downstream signals to obtain the upstream and downstream frequency domain signals; Calculate the frequency domain phase difference based on the upstream and downstream frequency domain signals; The signal phase difference is calculated based on the time-domain phase difference and the frequency-domain phase difference.

5. The adaptive mass flow rate measurement method for shoe adhesive formulation as described in claim 4, characterized in that, The process of performing liquid mass flow rate measurement on the liquid flow material to obtain a preliminary liquid flow rate includes: Perform time-series-based image acquisition on the liquid flow material to obtain multiple continuous material images; Perform image preprocessing operations on multiple consecutive material images to obtain multiple processed images; Perform pairwise combination operations on multiple processed images to obtain multiple image combinations. Each image combination includes a processed image and adjacent processed images. The adjacent processed images are processed images that are adjacent to the processed image and lag behind it. Preliminary liquid flow mass flow rate calculations are performed based on pixel displacement analysis using a combination of multiple images, resulting in multiple preliminary liquid flow mass flow rates.

6. The adaptive mass flow rate measurement method for shoe adhesive formulation as described in claim 5, characterized in that, The preliminary liquid flow mass flow rate calculation based on pixel displacement analysis using multiple image combinations yields multiple preliminary liquid flow mass flow rates, including: For each of the multiple image combinations, perform the following operation: Perform liquid flow material region recognition on the processed image and adjacent processed images to obtain processed material region images and adjacent material region images; Pixel displacement analysis is performed on the image of the processed material area and the image of the adjacent material area to obtain multiple pixel flow displacement vectors; The average displacement vector is obtained by averaging the flow displacement vectors of multiple pixels. Obtain the time difference between the processed image and adjacent processed images, and calculate the average pixel velocity based on the time difference and the average displacement vector; Calculate the initial liquid flow mass flow rate based on the average pixel velocity; By summing the initial liquid flow mass flow rates, multiple initial liquid flow mass flow rates are obtained.

7. The adaptive mass flow rate measurement method for shoe adhesive formulation as described in claim 6, characterized in that, The pixel displacement analysis performed on the processed material area image and adjacent material area images yields multiple pixel flow displacement vectors, including: Based on the material area image and adjacent material area images, a marker recognition operation is performed to obtain the coordinates of multiple markers and multiple adjacent markers; Based on multiple marker coordinates and multiple adjacent marker coordinates, multiple material image regions and multiple adjacent image regions are extracted from the processed image and adjacent processed images, respectively. Among them, the material image regions correspond one-to-one with the marker coordinates, and the adjacent image regions correspond one-to-one with the adjacent marker coordinates. Extract material image regions one by one from the material image regions to obtain the target material region, and perform the following operations on the target material region: Identify the adjacent image regions corresponding to the target material region in multiple adjacent image regions to obtain the target adjacent region; Obtain the maximum adjacent material region based on the target material region and the target adjacent region; The center coordinates of the largest adjacent material region and the target material region are obtained respectively. The maximum center coordinates and the target center coordinates are obtained. The pixel flow displacement vector is calculated based on the maximum center coordinates and the target center coordinates. By summing the pixel flow displacement vectors, we obtain multiple pixel flow displacement vectors corresponding to multiple marker coordinates.

8. The adaptive mass flow rate measurement method for shoe adhesive formulation as described in claim 7, characterized in that, The process of obtaining the maximum adjacent material region based on the target material region and the target adjacent region includes: Obtain the grayscale values ​​of multiple target pixels in the target material region, and obtain multiple adjacent material regions from the target adjacent region based on the target material region; For each of multiple adjacent material regions, perform the following operation: Obtain the gray values ​​of multiple adjacent pixels in the adjacent material region, and calculate the correlation coefficient based on the gray values ​​of multiple adjacent pixels and multiple target pixels using a pre-constructed formula for calculating the correlation coefficient. Summarize the correlation coefficients to obtain multiple correlation coefficients, and extract the maximum value from the multiple correlation coefficients to obtain the maximum correlation coefficient; Identify the adjacent material region corresponding to the largest correlation coefficient among multiple adjacent material regions to obtain the largest adjacent material region.

9. The adaptive mass flow rate measurement method for shoe adhesive formulation as described in claim 8, characterized in that, The formula for calculating the correlation coefficient is as follows: ； in, Represents the correlation coefficient. Represents the grayscale value of multiple target pixels. grayscale value of each target pixel Represents the grayscale value of multiple target pixels. The index of the grayscale value of each target pixel. This represents the average grayscale value of multiple target pixels. Represents the gray value of a plurality of adjacent pixels. grayscale values ​​of adjacent pixels This represents the average grayscale value of multiple adjacent pixels. This represents the total number of grayscale values ​​for multiple target pixels.

10. A mass flow rate adaptive measurement system for shoe adhesive formulation, characterized in that, The system includes: The material conveying module is used to acquire various types of conveying materials for shoe adhesive formulation, wherein the conveying materials are located in a pre-constructed fluid conveying pipeline, and the various types of conveying materials include powder materials and liquid materials. The signal acquisition module is used to perform charge signal acquisition on powdered material using a pre-built mass flow sensor set to obtain multiple charge signals. The mass flow sensor set includes multiple mass flow sensors. The powder mass flow rate measurement module is used to preprocess multiple charge signals to obtain multiple preprocessed signals. The preprocessing includes signal filtering and signal peak finding. Phase difference analysis is performed on the multiple preprocessed signals to obtain the signal phase difference. The physical spacing and sampling frequency of the multiple preprocessed signals are obtained. Based on the signal phase difference, physical spacing and sampling frequency, the preliminary powder flow rate is calculated using a pre-constructed calculation formula. Based on the preliminary powder flow rate, the powder flow rate measurement for shoe adhesive formulation is completed. The liquid mass flow rate measurement module is used to perform liquid mass flow rate measurement on liquid materials to obtain a preliminary liquid mass flow rate. Based on the preliminary liquid mass flow rate, the liquid mass flow rate measurement for shoe adhesive formulation is completed.

Images