Calcium carbonate master batch wind shear forming detection method and system

Abstract

The invention discloses a calcium carbonate master batch wind shear forming detection method and system, relates to the technical field of wind shear forming detection, and is used for solving the problems that due to the particularity of the shape of a granular product, part of products are arranged outside a groove, the detection quality precision is reduced, and the detection efficiency is reduced. The slot double image ratio, the slot non-filling rate, the granular product density distribution flatness and the granular product filling duration are collected and substituted into logistic regression calculation to obtain a slot initial error rate, the slot initial error rate is compared with a preset error threshold value, the maximum value of the slot initial error rate in the pre-scanning mechanism is positioned and marked as a default error slot, and the slot double image ratio, the slot non-filling rate, the granular product density distribution flatness and the granular product filling duration are obtained. And according to the subsequent error rate of the subsequent to-be-detected slot positions and the X-ray uniformity coefficient corresponding to each slot position, fuzzy logic is substituted for fuzzy reasoning to obtain a detection sequence result of the subsequent to-be-detected slot positions, so that the detection quality precision is improved, and the detection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind shearing and forming detection, and more specifically, to a method and system for detecting wind shearing and forming of a calcium carbonate masterbatch. Background Art

[0002] Calcium carbonate masterbatch wind shearing molding is a common process in plastic processing and a key step in the preparation of highly filled calcium carbonate masterbatch. It extrude the molten masterbatch from the extruder and use high-speed airflow, i.e. wind shearing, to quickly cool, mold and separate it to finally form a granular product. However, before the calcium carbonate masterbatch wind shearing molding, the calcium carbonate component of the masterbatch is analyzed in detail. However, when the molten masterbatch undergoes the wind shearing operation, the high-speed operation of the wind shearing machine and the unevenness of the wind shearing result in differences in the content of calcium carbonate components contained in the molded granular products.

[0003] The prior art has the following deficiencies: At present, an X-ray fluorescence analysis method is usually used as a component detection method. However, in its implementation process, since the granular product is spherical, if it still relies on manual placement of the product on the inspection table, it still takes too much time and increases the risk of manual operation. If a corresponding number of detection slots are set, some products will be placed outside the slot due to the particularity of the shape of the granular product, which not only makes it impossible to detect the product outside the slot, but also causes the possibility of ghosting during detection, resulting in a decrease in detection quality accuracy and reduced detection efficiency. Therefore, a calcium carbonate masterbatch wind cutting molding detection method and system are proposed.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a method and system for detecting wind-cutting molding of calcium carbonate masterbatch, which solves the problems raised in the above-mentioned background technology by using different product inspection methods.

[0006] To achieve the above object, the present invention provides the following technical solution, a calcium carbonate masterbatch wind-cut molding detection method, comprising S1: substituting the board to be inspected into a pre-scanning mechanism, collecting slot feature information and granular product feature information, and obtaining the slot ghosting ratio, slot unfilled rate, granular product density distribution flatness and granular product filling time through data processing; S2: Obtain the slot ghosting ratio, slot unfilling rate, granular product density distribution flatness, and granular product filling time, perform normalization, and substitute them into logistic regression calculation to obtain the slot initial error rate; S3: Obtain the initial error rate of the slot and compare it with the preset error threshold. According to the comparison result, count the initial error rate of the slot corresponding to the error threshold, locate the maximum value of the initial error rate of the slot in the pre-scanning mechanism, mark the current slot as the default error slot, and mark the remaining slots as subsequent slots to be inspected; S4: Obtain subsequent slots to be inspected, and collect subsequent error rates of the subsequent slots to be inspected and X-ray uniformity coefficients corresponding to each slot in the remaining inspection batches; S5: Obtain the subsequent error rate of the slots to be inspected and the X-ray uniformity coefficient corresponding to each slot, and use fuzzy logic to determine the inspection sequence results of the slots to be inspected.

[0007] In a preferred embodiment, the pre-scanning mechanism refers to scanning row by row and column by column in a preset order, which is divided into point scanning and surface scanning in the X-ray fluorescence analysis method; The slot feature information includes the slot ghosting ratio and the slot unfilling rate; the granular product feature information includes the granular product density distribution flatness and the granular product filling time; Use laser to scan the surface of each slot to determine whether the slot has abnormal height coverage, calculate the ratio of abnormal height coverage to slot surface area, and get the slot ghosting ratio ; Where i is the i-th slot; The unfilled area of ​​the slots with less than expected filling saturation is obtained by laser scanning the slot depth, and the ratio of the unfilled area to the slot depression area is calculated to obtain the slot unfilled rate. ; Through laser detection, the height change of the density distribution of the granular product in the slot is detected, and the local density deviation of the granular product in the slot is analyzed based on the height change to obtain the flatness of the density distribution of the granular product. ; The sensor records the stabilization time after the particles enter the slot, and the filling time of the granular product is obtained by subtracting the time when the granular product starts to enter the slot from the time when the granular product is completely stationary in the slot. .

[0008] In a preferred embodiment, the slot ghosting ratio, slot unfilling rate, granular product density distribution flatness and granular product filling time are normalized and substituted into the logistic regression calculation formula to express as follows: ; In the formula, is the result of logistic regression calculation, that is, the initial error rate of the slot, e is the natural base, and y is the linear combination term of the logistic regression model. Specifically, y can be set as: ; In the formula, is the bias term, , , as well as They are the regression coefficients of slot ghosting ratio, slot unfilling rate, granular product density distribution flatness and granular product filling time.

[0009] In a preferred embodiment, after obtaining the initial slot error rate, the initial slot error rate is compared and analyzed with the continuously iterated error threshold; If the initial error rate of the slot is greater than or equal to the error threshold, the current slot is marked as an error slot and a concern signal is generated; If the initial error rate of the slot is less than the error threshold, the current slot is marked as a regular slot and an end signal is generated; Scan the current slot marked as a regular slot in all remaining batches using point scanning for this slot.

[0010] In a preferred embodiment, the current slots marked as error slots are counted and located, the corresponding slot initial error rates are obtained, the slot initial error rates are sorted in descending order according to the numerical values, the slot corresponding to the maximum value of the slot initial error rate is set as the default error slot, and the remaining current slots marked as error slots are marked as subsequent slots to be inspected.

[0011] In a preferred embodiment, the default error slot is locked, and the slot is scanned using point scanning in all remaining batches.

[0012] In a preferred embodiment, the subsequent error rate of the subsequent slots to be inspected is obtained by calculating the ratio of the number of false detections after surface scanning in the remaining inspection batches to the total number of scans; In each surface scan, an X-ray sensor is used to collect numerical data of the ray intensity distribution, and the standard deviation of the ray intensity in the slot is calculated by the ratio of the average ray intensity in the slot to obtain the X-ray uniformity coefficient corresponding to each slot.

[0013] In a preferred embodiment, the subsequent error rate of the slots to be inspected and the X-ray uniformity coefficient corresponding to each slot are defined as input variables and divided into different fuzzy sets respectively; The subsequent slot inspection sequence results are defined as output variables and divided into fuzzy sets; Formulate fuzzy rules to describe the influence of the subsequent error rate of the slots to be inspected and the X-ray uniformity coefficient corresponding to each slot on the inspection sequence results of the slots to be inspected; Perform fuzzy reasoning based on fuzzy rules to determine the subsequent inspection sequence plan for the slots to be inspected.

[0014] The calcium carbonate masterbatch wind cutting molding detection system includes a data acquisition module, a data processing module, a slot analysis module and a detection sequence module; The data acquisition module is used to substitute the board to be inspected into the pre-scanning mechanism, collect slot feature information and granular product feature information, and obtain the slot ghosting ratio, slot unfilled rate, granular product density distribution flatness and granular product filling time through data processing, and send them to the data processing module; The data processing module is used to obtain the slot ghosting ratio, slot unfilling rate, granular product density distribution flatness and granular product filling time, perform normalization processing, and substitute into the logistic regression calculation to obtain the slot initial error rate, and send it to the slot analysis module; The slot analysis module is used to obtain the initial error rate of the slot and compare it with the preset error threshold. According to the comparison result, the initial error rate of the slot corresponding to the error threshold is counted, and the maximum value of the initial error rate of the slot in the pre-scan mechanism is located, and the current slot is marked as the default error slot, and the remaining slots are marked as subsequent slots to be inspected, and sent to the detection sequence module; The detection sequence module is used to obtain the subsequent slots to be inspected. In the remaining detection batches, the subsequent error rates of the subsequent slots to be inspected and the X-ray uniformity coefficients corresponding to each slot are collected, and the fuzzy logic is used to determine the detection sequence results of the subsequent slots to be inspected.

[0015] Technical effects and advantages of the present invention: 1. The present invention substitutes the board to be inspected into a pre-scanning mechanism, collects slot feature information and granular product feature information, obtains the slot ghost ratio, slot unfilled rate, granular product density distribution flatness and granular product filling time through data processing, performs normalization processing, substitutes the information into a logistic regression calculation to obtain the slot initial error rate, and compares it with a preset error threshold. According to the comparison result, the maximum value of the slot initial error rate in the pre-scanning mechanism is located, the current slot is marked as a default error slot, and the corresponding remaining slots that are greater than or equal to the error threshold are marked as subsequent slots to be inspected, so as to timely discover detection ghosts, mark the slots of key concern, improve the detection quality accuracy, and increase the detection efficiency.

[0016] 2. The present invention obtains subsequent slots to be inspected, collects subsequent error rates of subsequent slots to be inspected and X-ray uniformity coefficients corresponding to each slot in the remaining inspection batches, substitutes them into fuzzy logic for fuzzy reasoning, and obtains the inspection sequence results of subsequent slots to be inspected, avoids repeated inspections, assigns priorities to inspections, improves the quality of inspection data, and reduces memory redundancy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the wind shearing molding detection method of the calcium carbonate masterbatch of the present invention.

[0018] Figure 2 The present invention is a flow chart of the method for detecting the wind-cutting molding of the calcium carbonate masterbatch.

[0019] Figure 3 It is a module schematic diagram of the wind-cutting molding detection system of the calcium carbonate masterbatch of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] The present disclosure is based on an existing X-ray fluorescence analysis method, using a test plate with multiple grooves, and placing a number of granular products corresponding to the groove holes. Specifically, when placing, the placement height must be guaranteed and no new acceleration is added to the granular products (i.e., free-falling). The test plate is placed in a pre-scanning mechanism (i.e., sequential laser scanning). The initial error rate of the slot is determined by substituting the slot feature information and the granular product feature information into a logistic regression calculation, and the slots with the most errors in the pre-scanning mechanism are counted and located, and these slots are marked as default error slots. By default, in this round (this round includes multiple batches), the default error slots are point scanned, and in the remaining batches, according to the subsequent error rate of the default error slot and the X-ray uniformity coefficient corresponding to each slot, the fuzzy logic is substituted to determine the scanning mechanism result; Example 1: Please refer to Figure 1 to Figure 2 , calcium carbonate masterbatch wind cutting molding detection method, the specific operation process is as follows: S1: Substitute the board to be inspected into the pre-scanning mechanism, collect slot feature information and granular product feature information, and obtain the slot ghosting ratio, slot unfilled rate, granular product density distribution flatness and granular product filling time through data processing; Among them, the board to be inspected is substituted into the pre-scanning mechanism. The pre-scanning mechanism refers to scanning column by column or row by row in a preset order (similar to the scanning method of a printer), that is, sequential scanning. In the X-ray fluorescence analysis method, it is usually divided into point scanning and surface scanning. Point scanning is that the X-ray is focused on a single position of the sample, with a small emission range and a long time consumption. Surface scanning is like sequential scanning, and the scanning order and scanning path are controlled by software to maintain consistency, etc., which will not be elaborated here; Specifically, the X-ray fluorescence analysis method uses high voltage to excite the anode material (such as tungsten, molybdenum or rhodium) to produce continuous X-rays and characteristic X-rays, and limits the wavelength range and direction through filters or collimators. Among them, the X-ray source is mainly continuous emission, and the emission intensity is controlled by the voltage and current of the ray tube; The working principle of X-ray fluorescence analysis is to use the characteristic fluorescence of specific elements when the sample is irradiated by high-energy X-rays, so as to conduct qualitative and quantitative analysis. Specifically, high-energy X-rays excite the atoms in the sample, so that the inner electrons are knocked out and holes are generated. When the holes are filled by outer electrons, fluorescent X-rays with characteristic energy are released. The calcium element in the granular product formed by air cutting of calcium carbonate masterbatch will release specific energy. and Spectral lines, specifically, when the L layer electrons jump to the K layer, the released X-rays form Spectral line, when the M layer electron jumps to the K layer, the released X-ray forms Spectrum, usually, and The energy values ​​are 3.69 and 4.01 Based on the relationship between fluorescence intensity and content, the mass fraction of calcium was calculated using the calibration curve. The specific formula is: ; In the formula, is the mass fraction of calcium, is the fluorescence intensity, It is the calibration factor and needs to be measured based on the standard sample; According to the mass fraction of calcium, the variance among particles was compared to evaluate the overall uniformity; It should be noted that the above content is the specific implementation method of the X-ray fluorescence analysis method and how to measure and detect the composition uniformity of the granular product formed by wind-cutting the calcium carbonate masterbatch, which will not be elaborated here; Among them, the slot feature information includes the slot ghosting ratio and the slot unfilling rate; the granular product feature information includes the granular product density distribution flatness and the granular product filling time; The slot ghosting ratio refers to the abnormal detection results caused by overlapping, tilting or incorrect slot placement of granular products during placement. The acquisition logic is to use laser to scan the surface of each slot to determine whether the slot has abnormal height coverage, and calculate the ratio of the abnormal height coverage to the slot surface area to obtain the slot ghosting ratio. ; Where i is the i-th slot; It should be noted that the slot surface area refers to the slot mouth surface area, and its calculation formula conforms to the circle area calculation formula. The slot surface area is obtained by substituting the diameter of the granular product as a parameter; Among them, the detection of abnormal height is usually carried out by obtaining surface height data through laser scanning technology, and judging whether there is abnormal change on the surface of a certain slot through an algorithm. Specifically, if the height of certain areas of the slot surface is significantly higher or lower than the normal value, it may indicate that an overlapping effect occurs around the slot. Specifically, the setting of the normal value of the abnormal height is determined by the experimenter according to the size and size of the granular product, which will not be elaborated here. The slot unfill rate refers to the percentage of granular products missing from the slot or not completely covering the bottom of the slot, resulting in a weakened or invalid detection signal. The acquisition logic is to scan the slot depth with a laser to obtain the unfilled area in the slot with a filling saturation less than the expected one, and calculate the ratio of the unfilled area to the slot depression area to obtain the slot unfill rate. ; It should be noted that the groove depression area refers to the area of ​​the groove depression, which is usually 0.5 times the surface area of ​​the granular product. The specific setting of the groove depression area is set by the experimenter according to the surface area and size of the granular product, and will not be repeated here; Specifically, the setting of the expected filling saturation is defined by the experimenter according to the optimal groove filling saturation required by the X-ray fluorescence analysis method and other operating methods, and is not limited here; The flatness of the density distribution of granular products refers to whether the density distribution of granular products in the slot is uniform. Uneven density will lead to local ghosting or unfilled areas. Specifically, it is not a measurement of the uniformity of the composition of granular products. Its acquisition logic is to detect the height change of the density distribution of granular products in the slot through laser detection, and analyze the local density deviation of the granular products in the slot according to the height change to obtain the flatness of the density distribution of granular products. ; Specifically, the formula for analyzing the local density deviation of particles in the slot is: ; In the formula, It is the density distribution flatness of granular products. is the average height of the granular product in the slot, N is the total number of slots, is the height of the granular product in the ith slot in the slot; Specifically, the setting of the measuring points and the spacing of the measuring points are obtained by the experimenters based on the historical surface area height difference of the granular product and the flatness of the density distribution of the granular product, which will not be elaborated here; The filling time of granular products refers to the time required for evaluating the granular products from being put in to being stationary. Usually, after the granular products are detected to be put into the inspection plate, an extrusion plate is hung above the inspection plate to quickly fill the granular products into the slots of the inspection plate. If the filling time is too long, it means that the granular products are not inserted into the slots but scattered in other positions of the inspection plate. The current acquisition logic is to record the stabilization time after the particles enter the slots through the sensor, and subtract the time when the granular products start to enter the slots from the time when the granular products are completely stationary in the slots to obtain the granular product filling time. ; S2: Obtain the slot ghosting ratio, slot unfilling rate, granular product density distribution flatness, and granular product filling time, perform normalization, and substitute them into logistic regression calculation to obtain the slot initial error rate; The slot ghosting ratio, slot unfilling rate, granular product density distribution flatness and granular product filling time are normalized, and all input variables are converted to the same range to ensure that each input contributes to the model in a balanced manner. Specifically, the normalization method is to normalize the [0,1] interval, and the specific formula is expressed as:

[0022] In the formula, is the slot ghosting ratio, is the normalized slot ghosting ratio, is the minimum value of the slot ghosting ratio, is the maximum value of the slot ghosting ratio; Among them, the slot unfilling rate, the flatness of the granular product density distribution and the granular product filling time are also normalized using the above formula, which will not be described in detail here; After normalization, the values ​​of the slot ghosting ratio, slot unfilled rate, granular product density distribution flatness, and granular product filling time are all within the range of [0, 1]. The system can make comparisons and decisions on a unified scale, thereby improving the accuracy and efficiency of the logistic regression model. Substituting the slot ghosting ratio, slot unfilling rate, granular product density distribution flatness and granular product filling time into the logistic regression calculation, the specific formula is expressed as follows: ; In the formula, is the result of logistic regression calculation, that is, the initial error rate of the slot, e is the natural base, and y is the linear combination term of the logistic regression model. Specifically, y can be set as: ; In the formula, is the bias term, , , as well as They are the regression coefficients of the slot ghosting ratio, slot unfilling ratio, granular product density distribution flatness, and granular product filling time; Among them, the percentage of slot ghosting, the slot unfilled rate, the flatness of the granular product density distribution, and the granular product filling time are all data manifestations that directly express the initial error rate of each slot; It can be seen from the formula that the higher the slot ghosting ratio, slot unfilled rate and granular product filling time, the lower the integration degree between the granular product and the slot, and the higher the initial slot error rate. Conversely, the higher the flatness of the granular product density distribution, the higher the integration degree between the granular product and the slot, and the lower the initial slot error rate. S3: Obtain the initial error rate of the slot and compare it with the preset error threshold. According to the comparison result, count the initial error rate of the slot corresponding to the error threshold, locate the maximum value of the initial error rate of the slot in the pre-scanning mechanism, mark the current slot as the default error slot, and mark the remaining slots as subsequent slots to be inspected; The logic of obtaining the error threshold is to collect a distribution sample set of the historical granular product test result database, divide the data set into a training set and a test set, set the evaluation index and clustering algorithm, and in each round of cross-validation, train the model on the training set and evaluate the model performance on the test set. Then, adjust the error threshold according to the performance of the validation set. Therefore, the error threshold is constantly updated. In the present invention, clustering algorithm is a kind of unsupervised learning algorithm, which is used to divide the granular product detection results in the data set into groups or clusters with similarities; a common one is K-means clustering, which divides the granular products in the data set into K clusters, so that the distance between each granular product and the center point (center of mass) of the cluster to which it belongs is minimized, and finally the integration degree of the granular product and the slot is measured by the Euclidean distance, so as to set the error threshold; After obtaining the initial slot error rate, compare and analyze the initial slot error rate with the continuously iterated error threshold; If the initial error rate of the slot is greater than or equal to the error threshold, the current slot is marked as an error slot and a concern signal is generated; If the initial error rate of the slot is less than the error threshold, the current slot is marked as a regular slot and an end signal is generated; Further, the current slot marked as a regular slot is scanned in all remaining batches, and the slot is scanned using point scanning; Specifically, count and locate the current slots marked as error slots, obtain the corresponding initial error rates of the slots, sort the initial error rates of the slots in descending order according to the numerical values, set the slot corresponding to the maximum value of the initial error rate of the slot as the default error slot, and mark the remaining current slots marked as error slots as subsequent slots to be inspected; It should be noted that the default error slot refers to the slot with the highest error rate in the pre-scan mechanism, so this slot needs to be focused on in the remaining inspection batches; Specifically, the default error slot is locked, and in all remaining batches, the slot is scanned using point scanning; The use methods and purposes of point scanning and surface scanning have been described in this embodiment and will not be repeated here. The present invention substitutes the to-be-inspected board into a pre-scanning mechanism, collects slot feature information and granular product feature information, obtains the slot ghost ratio, slot unfilled rate, granular product density distribution flatness and granular product filling time through data processing, performs normalization processing, substitutes into logistic regression calculation to obtain the slot initial error rate, and compares it with a preset error threshold. According to the comparison result, the maximum value of the slot initial error rate in the pre-scanning mechanism is located, the current slot is marked as a default error slot, and the corresponding remaining slots that are greater than or equal to the error threshold are marked as subsequent slots to be inspected, so as to timely discover detection ghosts, mark the slots of key concern, improve the detection quality accuracy, and increase the detection efficiency.

[0023] Example 2: Example 1 focuses on the example of substituting the board to be inspected into the pre-scanning mechanism, collecting slot feature information and granular product feature information, and obtaining the slot ghosting ratio, slot unfilled rate, granular product density distribution flatness and granular product filling time through data processing, performing normalization processing, substituting into the logistic regression calculation to obtain the slot initial error rate, and comparing it with the preset error threshold. According to the comparison result, the maximum value of the slot initial error rate in the pre-scanning mechanism is located, the current slot is marked as the default error slot, and the corresponding remaining slots greater than or equal to the error threshold are marked as subsequent slots to be inspected. The operation strategy; however, in Example 1, only the default error slot is analyzed to make a judgment. However, in actual applications, if the total amount of detection deviation of the subsequent slots to be inspected is too large, it will result in obtaining more vacant or distorted data, which makes the system memory redundant and further reduces the detection efficiency; in view of the above problems, Example 2 is further refined; S4: Obtain subsequent slots to be inspected, and collect subsequent error rates of the subsequent slots to be inspected and X-ray uniformity coefficients corresponding to each slot in the remaining inspection batches; Specifically, the remaining test batches refer to all test batches included in the current round of testing after the pre-scanning mechanism is performed. The experimenter can understand that the number of test batches included in one round can be obtained based on the number of granular products and the number of granular products that the test plate can accommodate at one time. The pre-scanning mechanism can be set. The experimenter can set the first round as the pre-scanning mechanism, or the first few rounds as the pre-scanning mechanism, etc., which is not limited here; The subsequent error rate of the subsequent slot to be inspected refers to the subsequent error rate indicating whether there is an error probability for the subsequent slot to be inspected after the surface scan in the remaining inspection batch. The acquisition logic is to calculate the ratio of the number of error detections after the surface scan in the remaining inspection batch to the total number of scans to obtain the subsequent error rate of the subsequent slot to be inspected; Specifically, the subsequent error rate can set the number of error detections according to different batches. Multiple scans can be set in one batch detection. The specific number of scans is not limited, but is set according to the test results obtained by the experimenter, and will not be elaborated here; The X-ray uniformity coefficient corresponding to each slot refers to a parameter that measures the uniformity of the X-ray intensity distribution in the sample area, reflecting the energy distribution state when the X-ray beam covers the slot to be inspected. Its acquisition logic is to use the X-ray sensor to collect the numerical data of the ray intensity distribution in each surface scan, and calculate the ratio of the standard deviation of the ray intensity in the slot to the average value of the ray intensity in the slot to obtain the X-ray uniformity coefficient corresponding to each slot; Specifically, the calculation formula for obtaining the X-ray uniformity coefficient corresponding to each slot is as follows: ; In the formula, is the X-ray uniformity coefficient corresponding to each slot, is the ray intensity of the i-th slot, is the average value of the ray intensity; S5: Obtain the subsequent error rate of the slots to be inspected and the X-ray uniformity coefficient corresponding to each slot, and use fuzzy logic to determine the inspection sequence results of the slots to be inspected; For example, "Frequently", "Seldom", and "Moderately" are for the subsequent error rates of the subsequent slots to be inspected, and "High", "Low", and "Medium" are for the X-ray uniformity coefficients corresponding to each slot; Formulate a set of fuzzy rules to describe the impact of different input variables on output variables. The definition of rules can be based on professional knowledge or obtained through data analysis and experiments. For example: The subsequent error rate of the subsequent slots to be inspected is marked as X, the X-ray uniformity coefficient corresponding to each slot is marked as U, and the subsequent inspection sequence results of the slots to be inspected are marked as C_results; Then we can define: Rule 1: IF (X is Frequently) AND (U is Low) THEN (C_results is Low) Rule 2: IF (U is Seldom) AND (U is High) THEN (C_results is High) ... Perform fuzzy reasoning based on fuzzy rules to determine the subsequent slot inspection sequence plan; It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although the present embodiment takes three fuzzy sets as an example, in fact, the subsequent error rates of the subsequent slots to be inspected and the X-ray uniformity coefficients corresponding to each slot can be divided into more than three sets to facilitate better accurate adjustment according to different error rates. Further, for the subsequent error rate of the slots to be inspected and the judgment of the X-ray uniformity coefficient corresponding to each slot, a threshold can be set according to the actual situation for judgment. For example, when the subsequent error rate of the slots to be inspected exceeds 65%, it is marked as "Frequently", and when the X-ray uniformity coefficient corresponding to each slot is higher than 72%, it is marked as "High", etc., which will not be elaborated here; For example, according to the subsequent slot inspection sequence results of each slot, the sequence is sorted according to the result value, and the results with the statistical result of "Low" are substituted into the preset stop inspection threshold, and it is analyzed whether to stop the inspection in the future to save resources, and an alarm is issued to the visual end, etc. The subsequent steps and methods are not described in detail here; The present invention obtains subsequent slots to be inspected, collects subsequent error rates of subsequent slots to be inspected and X-ray uniformity coefficients corresponding to each slot in the remaining inspection batches, substitutes them into fuzzy logic for fuzzy reasoning, and obtains the inspection sequence results of subsequent slots to be inspected, avoids repeated inspections, assigns priorities to inspections, improves the quality of inspection data, and reduces memory redundancy. Example

[0024] See also Figure 3 , the calcium carbonate masterbatch wind cutting molding detection system includes a data acquisition module, a data processing module, a slot analysis module and a detection sequence module; The data acquisition module is used to substitute the board to be inspected into the pre-scanning mechanism, collect slot feature information and granular product feature information, and obtain the slot ghosting ratio, slot unfilled rate, granular product density distribution flatness and granular product filling time through data processing, and send them to the data processing module; The data processing module is used to obtain the slot ghosting ratio, slot unfilling rate, granular product density distribution flatness and granular product filling time, perform normalization processing, and substitute into the logistic regression calculation to obtain the slot initial error rate, and send it to the slot analysis module; The slot analysis module is used to obtain the initial error rate of the slot and compare it with the preset error threshold. According to the comparison result, the initial error rate of the slot corresponding to the error threshold is counted, and the maximum value of the initial error rate of the slot in the pre-scan mechanism is located, and the current slot is marked as the default error slot, and the remaining slots are marked as subsequent slots to be inspected, and sent to the detection sequence module; The detection sequence module is used to obtain the subsequent slots to be inspected. In the remaining detection batches, the subsequent error rates of the subsequent slots to be inspected and the X-ray uniformity coefficients corresponding to each slot are collected, and the fuzzy logic is used to determine the detection sequence results of the subsequent slots to be inspected.

[0025] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0026] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0027] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0028] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0029] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0030] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0031] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0032] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0033] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0034] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Calcium carbonate masterbatch wind cutting molding detection method, characterized in that: The method comprises: S1: substituting the board to be inspected into a pre-scanning mechanism, collecting slot feature information and granular product feature information, and obtaining the slot ghosting ratio, slot unfilled rate, granular product density distribution flatness, and granular product filling time through data processing; S2: Obtain the slot ghosting ratio, slot unfilling rate, granular product density distribution flatness, and granular product filling time, perform normalization, and substitute them into logistic regression calculation to obtain the slot initial error rate; S3: Obtain the initial error rate of the slot and compare it with the preset error threshold. According to the comparison result, count the initial error rate of the slot corresponding to the error threshold, locate the maximum value of the initial error rate of the slot in the pre-scanning mechanism, mark the current slot as the default error slot, and mark the remaining slots as subsequent slots to be inspected; S4: Obtain subsequent slots to be inspected, and collect subsequent error rates of the subsequent slots to be inspected and X-ray uniformity coefficients corresponding to each slot in the remaining inspection batches; S5: Obtain the subsequent error rate of the slots to be inspected and the X-ray uniformity coefficient corresponding to each slot, and use fuzzy logic to determine the inspection sequence results of the slots to be inspected.

2. The calcium carbonate masterbatch wind shearing molding detection method according to claim 1, characterized in that: The pre-scan mechanism refers to scanning row by row in a preset order. In the X-ray fluorescence analysis method, it is divided into point scanning and surface scanning; The slot feature information includes the slot ghosting ratio and the slot unfilling rate; the granular product feature information includes the granular product density distribution flatness and the granular product filling time; Use laser to scan the surface of each slot to determine whether the slot has abnormal height coverage, calculate the ratio of abnormal height coverage to slot surface area, and get the slot ghosting ratio ; Where i is the i-th slot; The unfilled area of ​​the slots with less than expected filling saturation is obtained by laser scanning the slot depth, and the ratio of the unfilled area to the slot depression area is calculated to obtain the slot unfilled rate. ; Through laser detection, the height change of the density distribution of the granular product in the slot is detected, and the local density deviation of the granular product in the slot is analyzed based on the height change to obtain the flatness of the density distribution of the granular product. ; The sensor records the stabilization time after the particles enter the slot, and the filling time of the granular product is obtained by subtracting the time when the granular product starts to enter the slot from the time when the granular product is completely stationary in the slot. .

3. The calcium carbonate masterbatch wind shearing molding detection method according to claim 2, characterized in that: The slot ghosting ratio, slot unfilling rate, granular product density distribution flatness, and granular product filling time are normalized and substituted into the logistic regression calculation formula to express the specific expression as follows: ； In the formula, is the result of logistic regression calculation, that is, the initial error rate of the slot, e is the natural base, and y is the linear combination term of the logistic regression model. The specific setting of y is: ； In the formula, is the bias term, , , as well as They are the regression coefficients of slot ghosting ratio, slot unfilling rate, granular product density distribution flatness and granular product filling time.

4. The calcium carbonate masterbatch wind shear molding detection method according to claim 3, characterized in that: After obtaining the initial slot error rate, compare and analyze the initial slot error rate with the continuously iterated error threshold; If the initial error rate of the slot is greater than or equal to the error threshold, the current slot is marked as an error slot and a concern signal is generated; If the initial error rate of the slot is less than the error threshold, the current slot is marked as a regular slot and an end signal is generated; Scan the current slot marked as a regular slot in all remaining batches using point scanning for this slot.

5. The calcium carbonate masterbatch wind shearing molding detection method according to claim 4, characterized in that: Count and locate the current slots marked as error slots, obtain the corresponding slot initial error rates, sort the slot initial error rates in descending order according to their numerical values, set the slot corresponding to the maximum value of the slot initial error rate as the default error slot, and mark the remaining current slots marked as error slots as subsequent slots to be inspected.

6. The calcium carbonate masterbatch wind shearing molding detection method according to claim 5, characterized in that: The default error slot is locked and in all remaining batches, this slot is scanned using point scanning.

7. The calcium carbonate masterbatch wind shearing molding detection method according to claim 5, characterized in that: The subsequent error rate of the subsequent slots to be inspected is obtained by calculating the ratio of the number of false detections after surface scanning in the remaining inspection batches to the total number of scans; In each surface scan, an X-ray sensor is used to collect numerical data of the ray intensity distribution, and the standard deviation of the ray intensity in the slot is calculated by the ratio of the average ray intensity in the slot to obtain the X-ray uniformity coefficient corresponding to each slot.

8. The calcium carbonate masterbatch wind shearing molding detection method according to claim 7, characterized in that: The subsequent error rates of the slots to be inspected and the X-ray uniformity coefficients corresponding to each slot are defined as input variables and divided into different fuzzy sets respectively; The subsequent slot inspection sequence results are defined as output variables and divided into fuzzy sets; Formulate fuzzy rules to describe the influence of the subsequent error rate of the slots to be inspected and the X-ray uniformity coefficient corresponding to each slot on the inspection sequence results of the slots to be inspected; Perform fuzzy reasoning based on fuzzy rules to determine the subsequent inspection sequence plan for the slots to be inspected.

9. A calcium carbonate masterbatch wind shearing molding detection system, used to implement the calcium carbonate masterbatch wind shearing molding detection method according to any one of claims 1 to 8, characterized in that: It includes a data acquisition module, a data processing module, a slot analysis module and a detection sequence module; The data acquisition module is used to substitute the board to be inspected into the pre-scanning mechanism, collect slot feature information and granular product feature information, and obtain the slot ghosting ratio, slot unfilled rate, granular product density distribution flatness and granular product filling time through data processing, and send them to the data processing module; The data processing module is used to obtain the slot ghosting ratio, slot unfilling rate, granular product density distribution flatness and granular product filling time, perform normalization processing, and substitute into the logistic regression calculation to obtain the slot initial error rate, and send it to the slot analysis module; The slot analysis module is used to obtain the initial error rate of the slot and compare it with the preset error threshold. According to the comparison result, the initial error rate of the slot corresponding to the error threshold is counted, and the maximum value of the initial error rate of the slot in the pre-scan mechanism is located, and the current slot is marked as the default error slot, and the remaining slots are marked as subsequent slots to be inspected, and sent to the detection sequence module; The detection sequence module is used to obtain the subsequent slots to be inspected. In the remaining detection batches, the subsequent error rates of the subsequent slots to be inspected and the X-ray uniformity coefficients corresponding to each slot are collected, and the fuzzy logic is used to determine the detection sequence results of the subsequent slots to be inspected.

Images