Blow-molded product wall thickness online control method based on image recognition

Abstract

The invention provides a blow molding product wall thickness on-line control method based on image recognition, and relates to the technical field of on-line control, and the method comprises the following steps: formulating type process parameters, calculating wall thickness adjustment parameters according to the adjusted melt extrusion amount and die orifice shape, adjusting the type process parameters to obtain molding control parameters, and controlling the molding control parameters to be in a closed state. And acquiring the thickness of the target blow molding product in the forming process to obtain time sequence thickness data. And whether the time sequence thickness data reach a preset target thickness threshold value or not is judged, if yes, the current forming control parameters are maintained, and if not, the wall thickness adjusting parameters are optimized. And performing feature extraction on the time sequence thickness data to obtain wall thickness deviation features, analyzing a linkage relationship between the wall thickness deviation features and the type process parameters to obtain associated correction parameters, and optimizing the wall thickness adjustment parameters to obtain wall thickness correction parameters. The directional correction capability of local deviation can be enhanced, the wall thickness control precision and stability are improved, and the method is suitable for products with different shapes and functions.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of online control technology, and in particular to a blow molding product wall thickness online control method based on image recognition. BACKGROUND

[0002] Blow molding is an important plastic processing method and is widely used in plastic product production. With the continuous improvement of the quality requirements of plastic products, the accurate control of the wall thickness of blow molding products has become one of the key technologies.

[0003] Early machines use two-stage oil pressure to control the core shaft gap, which can only achieve two simple effects of thick or thin, and cannot meet the needs of modern high-precision production. Later, although modern embryo wall thickness control systems are equipped with servo oil pressure systems and computers to form multi-stage control, improving product quality, there are still some problems. For example, it is difficult to accurately adjust the process parameters according to the wall thickness deviation. At the same time, when facing local wall thickness deviation, the traditional control method often has difficulty in accurate correction, resulting in unstable product quality.

[0004] Some automatic transverse thickness control systems based on fuzzy control algorithm, such as automatic air ring, although they have improved the transverse thickness uniformity of the film to some extent, but for highly nonlinear, strongly coupled, time-varying and control uncertainty systems, their precise mathematical model is almost impossible to establish, and the control effect still needs to be improved. In addition, some existing wall thickness control methods also have shortcomings in processing real-time data and dynamic adjustment, and cannot respond to wall thickness changes in the blow molding process in a timely and accurate manner.

[0005] In recent years, with the development of image recognition technology, its application in the field of industrial detection has become more and more widespread. Image recognition technology has the advantages of non-contact, high precision, and strong real-time performance, which can provide more effective means for blow molding product wall thickness online control. However, at present, the application of image recognition technology in blow molding product wall thickness online control is still relatively rare, and a mature technical system has not yet been formed.

[0006] In view of the problems existing in the prior art, the present application provides a blow molding product wall thickness online control method based on image recognition. SUMMARY

[0007] The present application provides a blow molding product wall thickness online control method based on image recognition, which solves the problems of unclear correlation between process parameters and wall thickness deviation and difficulty in accurately correcting local wall thickness deviation in the prior art.

[0008] The present application provides a blow molding product wall thickness online control method based on image recognition, which includes: Collecting raw material characteristic data, combining target blow molding shape to formulate type process parameters, calculating wall thickness adjustment parameters according to adjusting melt extrusion amount and die opening shape through wall thickness regulation method.

[0009] Adjusting type process parameters according to wall thickness adjustment parameters to obtain molding control parameters, collecting image data of target blow molding product in the molding process, and processing image data using dynamic partition calibration method to obtain time sequence thickness data.

[0010] Judging whether the time sequence thickness data reaches a preset target thickness threshold, if yes, maintaining the current molding control parameters, otherwise optimizing the wall thickness adjustment parameters.

[0011] Obtaining wall thickness deviation features by feature extraction on the time sequence thickness data, obtaining correlation correction parameters according to sequence pattern mining method by analyzing the linkage relationship between the wall thickness deviation features and the type process parameters, and optimizing the wall thickness adjustment parameters to obtain wall thickness correction parameters.

[0012] The application provides a blow molding product wall thickness online control method based on image recognition, and the step of formulating type process parameters comprises: According to the product use, the performance index is determined, the shape parameters of the target blow molding product are obtained, and the raw material characteristic data is obtained by analyzing the basic performance and processing adaptability of the raw material.

[0013] According to the single weight and production speed of the target product, the theoretical extrusion amount is calculated, the initial screw rotation speed is calculated combined with the screw diameter and pitch, and the die head temperature of different functional sections is set according to the use function.

[0014] According to the raw material characteristic data, the blow molding pressure and cooling water temperature are set, the initial gap of the die opening is calculated according to the target wall thickness and blow ratio of the product, and the type process parameters are obtained by combining the historical optimal parameters of similar products.

[0015] The application provides a blow molding product wall thickness online control method based on image recognition, and the step of calculating wall thickness adjustment parameters comprises: According to the initial screw rotation speed, the melt volume extrusion amount in the current production is calculated.

[0016] Collecting the average gap of the die opening, the die opening gap distribution and the die opening outlet diameter as the key parameters of the die opening.

[0017] According to the preset target thickness threshold, the target demand extrusion amount and the target demand gap of the die opening shape are calculated.

[0018] According to the target demand extrusion amount, the raw material is extruded, and the local wall thickness deviation area is corrected combined with the target demand gap to obtain a die opening gap distribution adjustment scheme.

[0019] Detecting the head pressure data in the blow molding process, combining the initial screw rotation speed to calculate the real-time melt viscosity, when exceeding the preset reference viscosity, adjusting the target demand extrusion amount and the target demand gap to obtain the wall thickness adjustment parameter.

[0020] The application provides a blow molding product wall thickness online control method based on image recognition, and the step of adjusting the molding control parameter comprises: According to the corresponding association of the wall thickness adjustment parameter and the type process parameter, a parameter mapping table is constructed, and the influence amplitude of the unit change of the type process parameter on the wall thickness is determined to form a sensitivity coefficient table.

[0021] The wall thickness adjustment parameter is converted into an adjustment value of the process parameter based on the parameter mapping table and the sensitivity coefficient table.

[0022] According to the influence of directness and response speed, each parameter in the wall thickness adjustment parameter is sorted, and the adjustment rate is set according to the single-step maximum adjustment amount.

[0023] The adjustment value is superimposed on the type process parameter, and the molding control parameter is generated according to the equipment safety and the process feasible range.

[0024] The application provides a blow molding product wall thickness online control method based on image recognition, and the step of obtaining the time sequence thickness data comprises: Based on the blow molding product moving speed and the minimum detection accuracy, the sampling frequency is calculated, and the detection area is divided according to the blow molding product structure and the circumferential direction.

[0025] According to the sampling frequency and the detection area, image data is collected and preprocessed to obtain preprocessed thickness data.

[0026] Taking the pulse of the main encoder of the production line as the reference time, the preprocessed thickness data collected by different sensors is calibrated, the data segment is divided according to the molding cycle for intermittent production, and the abnormal value is removed and the continuity is checked to obtain the time sequence thickness data.

[0027] The application provides a blow molding product wall thickness online control method based on image recognition, and the step of extracting the wall thickness deviation feature comprises: According to the preset target wall thickness threshold as the reference, the absolute deviation and the relative deviation of each sampling point are calculated to define the deviation, and the time sequence thickness data is sliced to form a regionalized sub-data set according to the detection area.

[0028] From the time sequence point of view, the trend feature, the fluctuation feature and the burst feature of the wall thickness deviation are analyzed to obtain the dynamic change law.

[0029] From the spatial distribution point of view of the blow molding product, the position characteristics of the wall thickness deviation are analyzed, and the local defects and the regional differences are identified.

[0030] Integrate the dynamic change rule and the local defect and the regional difference to form the wall thickness deviation characteristics.

[0031] The application provides a blow molding product wall thickness online control method based on image recognition, and the step of obtaining the dynamic change rule comprises: Calculate the average deviation and cumulative deviation in the preset period, and obtain the trend characteristics by linear regression fitting the deviation change curve over time.

[0032] Obtain the fluctuation characteristics by calculating the standard deviation and range of the regionalized sub-data set, and performing Fourier transform to extract the fluctuation frequency and corresponding amplitude.

[0033] Extract the deviation peak value and duration exceeding the preset target wall thickness threshold as the deviation time, and calculate the deviation change amount of adjacent data points as the burstiness characteristics.

[0034] Integrate the trend characteristics, fluctuation characteristics and burstiness characteristics to obtain the dynamic change rule.

[0035] The application provides a blow molding product wall thickness online control method based on image recognition, and the step of obtaining the associated correction parameter comprises: Divide the type process parameters and wall thickness deviation characteristics into discrete states according to the normal range, and sequence encode the adjustment action and burstiness characteristics to form the associated sequence pair.

[0036] Mine the frequent patterns in the associated sequence pair by using the PrefixSpan algorithm.

[0037] Convert the frequent patterns into process parameter correction rules, including trigger conditions, associated process parameters, correction actions and confidence.

[0038] Calculate the correction coefficient based on the statistical relationship between the process parameter change amount and the deviation change amount in the frequent patterns.

[0039] When multiple process parameter correction rules are triggered at the same time, select the process parameter correction rule with the maximum correction coefficient as the associated correction parameter.

[0040] The application provides a blow molding product wall thickness online control method based on image recognition, and the step of obtaining the frequent patterns comprises: Traverse all associated sequence pairs, extract all prefix patterns, calculate the support degree, and extract the prefix patterns exceeding the preset minimum support degree to form the initial frequent sequences.

[0041] Generate a projection database for each initial frequent sequence, and combine all suffix items of the current initial frequent sequence to form candidate item patterns.

[0042] For each candidate item pattern, count the number of occurrences in the projection database, and screen out the frequent item patterns.

[0043] Continue to build the projection database for each frequent item pattern, recursively extend the prefix pattern, and generate long sequence frequent patterns.

[0044] Remove short patterns that do not meet the preset length in the long sequence frequent patterns, and sort them by length to form frequent patterns from short to long.

[0045] The present application provides an image recognition-based online control method for blow molding product wall thickness, and the optimization of the wall thickness correction parameter includes: According to the mapping relationship between the associated correction parameter and the wall thickness adjustment parameter, a correction mapping table is constructed, and a plurality of adjustment amounts are sorted according to the influence weight of the associated correction parameter on the wall thickness.

[0046] According to the associated correction parameter and the correction coefficient, each level of adjustment amount is adjusted to obtain a plurality of adjustment parameters.

[0047] Determine whether the wall thickness adjusted by the multi-level adjustment parameter reaches the preset target thickness threshold, if yes, the current multi-level adjustment parameter is taken as the wall thickness correction parameter, otherwise the correction coefficient is recalculated.

[0048] The image recognition-based online control method for blow molding product wall thickness provided by the present application realizes real-time monitoring of wall thickness changes and adjustment of process parameters according to real-time data, ensures wall thickness uniformity, and solves the defects of traditional blow molding product wall thickness control methods, which usually rely on experience parameter setting and are difficult to adjust in real time, resulting in poor wall thickness uniformity and high scrap rate. Through dynamic partition calibration method and real-time melt viscosity detection, the wall thickness adjustment parameter is adjusted in real time, improving the real-time performance of wall thickness control. Through partition detection and feature extraction, independent detection and adjustment are carried out for different functional sections and local areas, ensuring the wall thickness uniformity of complex shape products, solving the defects of traditional methods that are difficult to accurately control the wall thickness of complex shape blow molding products, resulting in local wall thickness deviation. Through real-time monitoring and adjustment, wall thickness uniformity is ensured, scrap rate is reduced, and product quality is improved. And using partition detection and feature extraction, the wall thickness uniformity of complex shape products is ensured, and products of different shapes and functions are adapted. The automatic extraction and continuous optimization of process knowledge are realized, which significantly improves the intelligentization and automation level of the blow molding process, and has important industrial application value and popularization prospect. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0050] Figure 1 is one of the flow schematic diagrams of the image recognition-based blow molding product wall thickness online control method provided by the embodiments of the present application; Figure 2 is another one of the flow schematic diagrams of the image recognition-based blow molding product wall thickness online control method provided by the embodiments of the present application; Figure 3 is a third one of the flow schematic diagrams of the image recognition-based blow molding product wall thickness online control method provided by the embodiments of the present application; Figure 4 is a fourth one of the flow schematic diagrams of the image recognition-based blow molding product wall thickness online control method provided by the embodiments of the present application; Figure 5 is a correction mapping table of the image recognition-based blow molding product wall thickness online control method provided by the embodiments of the present application. DETAILED DESCRIPTION

[0051] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0052] The present application is described below with reference to the drawings. Figures 1-5 A kind of image recognition-based blow molding product wall thickness online control method is described.

[0053] As shown in Figure 1 , the image recognition-based blow molding product wall thickness online control method provided by the embodiments of the present application comprises: Collecting raw material characteristic data, combining target blow molding product shape to formulate type process parameters, calculating wall thickness adjustment parameters according to the adjustment of melt extrusion amount and die shape by wall thickness control method.

[0054] The step of formulating type process parameters comprises: According to the use of the product, the performance index is determined, the shape parameters of the target blow molding product are obtained, and the raw material characteristic data is obtained by analyzing the basic performance and processing adaptability of the raw material.

[0055] Basic performance detection: the melt flow rate can be detected by a melt flow rate instrument, and the fluidity of the material under standard temperature and load is recorded.

[0056] The gel permeation chromatography is used to analyze the molecular weight distribution, the weight average molecular weight and the molecular weight distribution index (PDI) are obtained, and the material with PDI≤3 is preferentially selected to ensure the processing stability.

[0057] The melting temperature and crystallinity of the material are determined by a differential scanning calorimeter to determine the processing temperature range. The processing temperature should be higher than the melting temperature.

[0058] Processing adaptability detection: for hygroscopic materials, the water content is detected by Karl Fischer moisture meter, and the water content is required to be ≤0.02% to avoid bubbles during processing. The viscosity curve of the melt at different shear rates and temperatures is determined by a rotational rheometer to determine the correlation between viscosity, temperature and shear rate.

[0059] According to the single weight and production speed of the target product, the theoretical extrusion amount is calculated, and the initial screw speed is calculated combined with the screw diameter and pitch. According to the use function, the head temperature of different functional segments is set by segmentation.

[0060] According to the material characteristic data, the blow molding pressure and cooling water temperature are set, and the initial gap of the die is calculated according to the target wall thickness and blow ratio of the product, and is corrected to obtain the type process parameters combined with the historical optimal parameters of similar products.

[0061] As shown in Figure 2 The steps of calculating the wall thickness adjustment parameter include: According to the initial screw speed, the melt volume extrusion amount in the current production is calculated, which is expressed by the formula:

[0062] In the formula, is the initial screw speed, is the displacement per revolution of the screw, is the melt flow efficiency coefficient, is the melt volume extrusion amount.

[0063] The average gap of the die, the die gap distribution and the die outlet diameter are collected as the key parameters of the die.

[0064] According to the preset target thickness threshold, the target demand extrusion amount and the target demand gap of the die shape are calculated, which are expressed by the formula:

[0065]

[0066] In the formula, is the target demand extrusion amount, is the target demand gap, is the preset target thickness threshold, is the flow rate of the material at the die, is the die diameter, is the initial gap, is the correction coefficient, is the current extrusion amount.

[0067] According to the target requirement extrusion amount, the raw material is extruded, and the local wall thickness deviation area is corrected according to the target requirement gap to obtain a die gap distribution adjustment scheme.

[0068] The head pressure data in the blow molding process is detected, the real-time melt viscosity is calculated in combination with the initial screw rotation speed, when the preset reference viscosity is exceeded, the target requirement extrusion amount and the target requirement gap are adjusted to obtain a wall thickness adjustment parameter.

[0069] According to the wall thickness adjustment parameter, a molding control parameter is obtained by adjusting the type process parameter, image data of the target blow molding product in the molding process is collected, and the image data is processed by using a dynamic partition calibration method to obtain time sequence thickness data.

[0070] The step of adjusting the molding control parameter comprises: According to the corresponding association between the wall thickness adjustment parameter and the type process parameter, a parameter mapping table is constructed, and the influence amplitude of the unit change of the type process parameter on the wall thickness is determined to form a sensitivity coefficient table.

[0071] Based on the parameter mapping table and the sensitivity coefficient table, the wall thickness adjustment parameter is converted into an adjustment value of the process parameter.

[0072] Screw speed adjustment: the screw speed adjustment amount is calculated according to the melt extrusion amount adjustment amount and the screw displacement.

[0073] Die total opening adjustment: the die total opening adjustment amount is calculated according to the die average gap adjustment amount and the die mechanical transmission ratio.

[0074] Partition process parameter adjustment amount calculation: local die gap adjustment: the stroke adjustment amount of each motor is calculated according to the deviation area in the circumferential direction and the displacement-gap conversion coefficient of the corresponding area servo motor.

[0075] Head partition temperature adjustment: according to the material viscosity-temperature curve, the temperature reduction amount is calculated for the area that needs to be thickened.

[0076] According to the influence directness and response speed, each parameter in the wall thickness adjustment parameter is sorted, and the adjustment rate is set according to the single-step maximum adjustment amount.

[0077] The adjustment value is superimposed with the type process parameter, and the molding control parameter is generated according to the equipment safety and process feasible range.

[0078] The molding control parameter is converted into a device recognizable instruction format to realize automatic adjustment: instruction format conversion: the molding control parameter is converted into a digital signal according to the device communication protocol: Screw rotation speed → frequency command of frequency converter. Die gap → pulse number of servo motor. Temperature → set value of PID controller.

[0079] Synchronous issuance and state feedback: instructions are issued in order according to adjustment priority, and actual values of parameters are collected in real time through sensors (such as encoder feedback actual rotation speed, displacement sensor feedback actual die gap).

[0080] If the deviation between the actual value and the target value exceeds ±2% (such as target rotation speed 40r / s, actual 39r / s), trigger secondary fine adjustment until the deviation is ≤±1%.

[0081] As shown in Figure 3 the step of obtaining time-series thickness data includes: Based on the moving speed of the blow molded product and the minimum detection accuracy, the sampling frequency is calculated, and the detection area is divided according to the structure and circumferential direction of the blow molded product.

[0082] According to the structure of the blow molded product, the detection area is divided into sections, such as the mouth section, body section and bottom section, and independent detection thresholds are set for each section.

[0083] For the circumferential direction: the detection points are divided according to the angle, and the thickness distribution of the full circumferential direction is recorded.

[0084] According to the sampling frequency and the detection area, image data is collected and preprocessed to obtain preprocessed thickness data. According to the sampling frequency, the collection frequency of the image sensor (such as a high-speed industrial camera) is bound with the pulse signal of the main encoder of the production line to ensure that each frame of image corresponds to a fixed displacement of the blow molded product, avoiding sampling misplacement caused by speed fluctuations. For structure partitioning of the mouth section, body section and bottom section, multiple sensors are used for cooperative collection: a macro lens is used for the mouth area, a wide-angle lens is used for the body area, and a side-view camera is added for the bottom area to capture corner details.

[0085] The circumferential direction is divided into 36 detection points at intervals of 10°, and each detection point corresponds to an independent image ROI (region of interest), ensuring that the full circumferential thickness data has no dead angle.

[0086] Combining the transmission type laser thickness measurement and infrared thermal imaging, laser thickness images and temperature distribution images of each detection area are collected synchronously, each frame of image is attached with a time stamp and encoder position information, and image data is formed.

[0087] The step of filtering noise from the image data includes: for laser images, adaptive median filtering is used to eliminate salt and pepper noise caused by dust and bubbles; for infrared images, Gaussian filtering is used to smooth temperature fluctuation noise and retain real temperature gradient features. For low-contrast areas such as the bottom corner, a limited contrast adaptive histogram equalization algorithm is used to enhance local details, ensuring that the wall thickness boundary is clear and identifiable, and contrast enhancement is performed.

[0088] Based on the preset gray-thickness calibration curve (obtained by standard thickness block calibration), the gray value of the laser image is converted into the actual wall thickness value to obtain the pretreatment thickness data.

[0089] With the main encoder pulse of the production line as the reference time, the pretreatment thickness data collected by different sensors is calibrated, the data segments are divided according to the forming cycle for intermittent production, and the abnormal value is removed and the continuity is checked to obtain the time sequence thickness data.

[0090] Remove abnormal values: when the thickness value of a certain point exceeds the theoretical range (such as the target wall thickness 1.2mm, the measured value 3.0mm or 0.1mm), mark it as invalid value and record the abnormal reason (such as sensor shielding, image blur).

[0091] Continuity check: if the thickness change rate of the continuous 5 points exceeds 50% (such as from 1.2mm to 0.5mm), trigger the sensor state self-check (such as laser power, camera focal length).

[0092] Determine whether the time sequence thickness data reaches the preset target thickness threshold, yes, maintain the current forming control parameter, otherwise optimize the wall thickness adjustment parameter.

[0093] Obtain the wall thickness deviation feature by feature extraction of the time sequence thickness data, analyze the linkage relationship between the wall thickness deviation feature and the type process parameter according to the sequence pattern mining method to obtain the associated correction parameter, and optimize the wall thickness adjustment parameter to obtain the wall thickness correction parameter.

[0094] The steps of extracting the wall thickness deviation feature include: According to the preset target wall thickness threshold as the reference, calculate the absolute deviation and relative deviation of each sampling point, define the deviation, and slice the time sequence thickness data to form a regionalized sub-data set according to the detection area.

[0095] From the time sequence point of view, analyze the trend feature, fluctuation feature and burst feature of the wall thickness deviation to obtain the dynamic change law.

[0096] The steps of obtaining the dynamic change law include: Calculate the average deviation and cumulative deviation in the preset period, and fit the deviation-time curve by linear regression to obtain the trend feature.

[0097] The formula for calculating the average error is:

[0098] In the formula, is the average error, is the number of data points, is the error value of the th data point, is the independent variable.

[0099] The formula for calculating the cumulative deviation is expressed as:

[0100] In the formula, is the cumulative deviation, is the absolute value of the error of the th data point.

[0101] The formula for fitting the deviation curve with time by linear regression is expressed as:

[0102] In the formula, is the deviation change of the control input, is the slope, is the time, is the intercept.

[0103] The volatility feature is obtained by calculating the standard deviation and range of the regionalized sub-data set, and performing Fourier transform to extract the fluctuation frequency and corresponding amplitude.

[0104] The formula for calculating the standard deviation is expressed as:

[0105] In the formula, is the standard deviation.

[0106] The formula for calculating the range is expressed as:

[0107] In the formula, is the range, is the maximum value in , and is the minimum value in .

[0108] The deviation peak value and duration exceeding the preset target wall thickness threshold are extracted as the deviation time, and the deviation change of adjacent data points is calculated as the burstiness feature.

[0109] The formula for calculating the deviation change is expressed as:

[0110] In the formula, is the deviation change.

[0111] The trend feature, volatility feature and burstiness feature are integrated to obtain the dynamic change rule.

[0112] From the perspective of spatial distribution of blow molding products, the position characteristics of wall thickness deviation are analyzed, and local defects and regional differences are identified.

[0113] Regional deviation distribution characteristics: Regional average deviation: Calculate the average deviation of each detection area and compare the deviation degree of different areas.

[0114] Deviation proportion: Calculate the proportion of the number of points exceeding the tolerance in a certain area (e.g., the corner area exceeds the tolerance by 30%, indicating that the molding is unstable in this area).

[0115] Circumferential direction deviation distribution: For the same axial position, draw the relationship curve between the circumferential angle (0°-360°) and the deviation value, extract the angle corresponding to the maximum deviation, and identify the axial position of the deviation mutation (e.g., the gradient is large at the connection between the bottle mouth and the bottle body, which may be due to unreasonable design of the mold mouth transition).

[0116] Spatial correlation characteristics: Use clustering algorithms (such as K-means) to cluster the full-space deviation points, identify continuous over-thickness areas (e.g., "100-150mm axial range on the right side of the bottle body continuously over-thick"), extract the area, center coordinates and other features of this area, and determine whether it is a systematic defect.

[0117] Integrate dynamic change rules and local defects and regional differences to form wall thickness deviation characteristics.

[0118] As shown in Figure 4 , the steps of obtaining the associated correction parameters include: Divide the type process parameters and wall thickness deviation characteristics into discrete states according to the normal range, and sequence code the adjustment actions and sudden characteristics to form associated sequence pairs.

[0119] Use the PrefixSpan algorithm to mine frequent patterns in the associated sequence pairs.

[0120] Convert the frequent patterns into process parameter correction rules, including trigger conditions, associated process parameters, correction actions and confidence.

[0121] Based on the statistical relationship between the process parameter change amount and the deviation change amount in the frequent patterns, calculate the correction coefficient, which is expressed as:

[0122] In the formula, is the correction coefficient of the th process parameter, is the normalized change amount of the parameter when the th associated rule is triggered, is the wall thickness deviation change amount corresponding to the th trigger, is the Pearson correlation coefficient between the parameter and the deviation.

[0123] wherein the formula expression is:

[0124] wherein, is the change of the parameter at the time the correlation rule is triggered, is the arithmetic mean of the change of the process parameter in all correlation rule triggering events, is the sample mean difference of the change of the process parameter in all correlation rule triggering events.

[0125] When multiple process parameter correction rules are triggered at the same time, the process parameter correction rule with the maximum correction coefficient is selected as the correlation correction parameter.

[0126] The step of obtaining frequent patterns comprises: traversing all the correlation sequence pairs, extracting all the item prefix patterns, calculating the support, and extracting the item prefix patterns exceeding the preset minimum support to form initial frequent sequences. The item prefix pattern can be expressed as: , indicating that the process parameter state corresponds to the deviation feature . The formula for calculating the support is:

[0127] wherein, is the support, is the number of sequence pairs containing the item prefix pattern, is the total number of sequence pairs.

[0128] For each initial frequent sequence, a projection database is generated, and all suffix items of the current initial frequent sequence are extracted and combined to form candidate item patterns. The projection database only retains the correlation sequence pairs containing the item prefix pattern, and truncates all items before the item prefix pattern in the sequence, retaining only the subsequence (referred to as "suffix sequence") after the item prefix pattern, which is used for mining longer patterns.

[0129] For each candidate item pattern, the number of occurrences in the projection database is counted, and the frequent item patterns are screened out. The screening method is to retain the candidate item patterns with a support greater than or equal to the preset minimum support as the frequent item patterns.

[0130] For each frequent item pattern, the projection database is continued to be constructed, the prefix pattern is recursively expanded, and long sequence frequent patterns are generated. For each frequent item pattern, a new projection database is repeatedly constructed (only retaining the suffix sequence after the pattern).

[0131] ​Extract suffix items from the new projection database, combine with current frequent patterns to form new item candidate pattern, calculate support and screen, form frequent item sequence set.

[0132] When longer patterns with support ≥ minimum support cannot be generated, stop recursion.

[0133] Remove short patterns in long sequence frequent patterns that do not meet the preset length, and sort by length to form frequent patterns from short to long. The frequent pattern can be thick due to high-speed production, and the die gap can be restored to normal after increasing the die gap. Support 3%, confidence 85%.

[0134] The optimization steps for obtaining the wall thickness correction parameter include: As Figure 5 shown, a correction mapping table is constructed according to the mapping relationship between the associated correction parameter and the wall thickness adjustment parameter, and the wall thickness is sorted according to the influence weight of the associated correction parameter.

[0135] The sorting can be divided into: first level (die gap correction), second level (extrusion amount / rotation speed correction), third level (temperature / pressure correction).

[0136] According to the associated correction parameter and the correction coefficient, the adjustment amount of each level is adjusted to obtain the multi-level adjustment parameter. The multi-level adjustment parameter includes: local parameter, overall parameter and auxiliary parameter.

[0137] Local parameter: according to the associated correction parameter and the correction coefficient, the local wall thickness adjustment amount is calculated.

[0138] Overall parameter: based on the screw speed correction amount, the screw displacement and the flow efficiency coefficient, the extrusion amount adjustment amount is calculated, and the formula is expressed as:

[0139] In the formula, is the screw speed correction amount, is the displacement per revolution of the screw, is the melt flow efficiency coefficient.

[0140] Third level adjustment (auxiliary parameter): according to the head temperature correction amount, the viscosity compensation coefficient is calculated to correct the extrusion stability. According to the blow molding pressure correction amount ΔP, the stretching correction amount is adjusted.

[0141] Determine whether the wall thickness adjusted by the multi-level adjustment parameter reaches the preset target thickness threshold. If yes, the current multi-level adjustment parameter is taken as the wall thickness correction parameter, otherwise the correction coefficient is recalculated.

[0142] The wall thickness correction parameters are executed in steps according to priority: first, local adjustment of the die opening (single step ≤ 0.05 mm, interval of 3 cycles), then adjustment of extrusion amount / speed (single step ≤ ±1 r / s), and finally adjustment of auxiliary parameters (single step ≤ ±3℃ or ±0.05 MPa).

[0143] Dynamic feedback: After each adjustment, the real-time wall thickness is collected, the actual deviation is calculated, and if the deviation is >0.05mm, the correction coefficient is re-optimized and iteratively adjusted.

[0144] The wall thickness correction parameter set (including overall parameters, local parameters, and auxiliary parameters) is split according to the equipment control dimension. According to the communication protocol of the blow molding machine control system, the parsed instructions are converted into digital signals that the equipment can recognize, ensuring that the instruction transmission error is not compromised.

[0145] Execution is carried out in steps according to priority: First stage (0-2 seconds): Perform local gap correction of the die opening, control the servo motor to adjust to the target position at a rate of 0.02mm per step, and simultaneously collect feedback signals from the die opening position sensor; Second stage (2-5 seconds): Perform screw speed / extrusion amount correction, adjust the speed at a rate of ±0.5r / s per step, and monitor melt pressure sensor data in real time; The third stage (5-10 seconds): Perform temperature / pressure correction, adjusting the temperature at a rate of ±1℃ / s and the pressure at a rate of ±0.02MPa / s to avoid fluctuations in the melt state caused by sudden parameter changes.

[0146] The following data were collected simultaneously to verify the execution effect: Image data: real-time images of the product being molded were taken using an industrial camera to calculate the current wall thickness; Equipment status data: actual values ​​of screw speed, die clearance, die head temperature, and blow molding pressure; Environmental data: workshop temperature and humidity (fluctuations must be ≤±2℃ and ±5%).

[0147] Ten seconds after the correction parameters are executed, new time-series thickness data is extracted, and the corrected wall thickness deviation is calculated: if the overall deviation is ≤ ±0.03mm and the local deviation is ≤ ±0.02mm, the correction is deemed effective, and the production enters a stable production stage. If the deviation does not meet the standard (e.g., the local thickness is still 0.04mm too thick), the fine-tuning mechanism is triggered: the correction coefficient is recalculated based on the new deviation, and secondary correction parameters are generated.

[0148] If a parameter coupling conflict occurs (such as increasing the rotation speed causing the pressure to exceed the limit), the collaborative correction logic is activated: reduce the rotation speed adjustment range or compensate for the temperature adjustment to ensure that the wall thickness meets the standard under the collaborative action of multiple parameters.

[0149] After the correction parameters are verified, the current molding control parameters are locked, and the batch production mode is started: every 100 products are randomly sampled and detected to confirm the wall thickness stability (standard deviation ≤ 0.02 mm); the key parameters of each batch (such as raw material batch, environmental temperature, average wall thickness) are automatically recorded to form a traceable production file.

[0150] If an unexpected abnormality occurs during production (such as raw material supply interruption, sensor failure): the system automatically suspends production and saves the current parameter state; After troubleshooting, based on the wall thickness data before interruption and the parameter state, 3 trial production verifications are performed, and after meeting the standards, the batch production is resumed.

[0151] Comprehensive detection is performed on the offline products: dimensional accuracy: bottle mouth diameter, bottle body perpendicularity; Wall thickness uniformity: ultrasonic thickness gauge is used to detect key areas (such as bottle mouth sealing surface, bottle bottom corner); Mechanical properties: pressure resistance test, drop test (meet product standards).

[0152] If the finished product qualified rate ≥ 99.5%, the wall thickness correction parameters, molding control parameters and corresponding process conditions (such as raw material model, environmental parameters) of this production are stored in the process knowledge base; if the qualified rate is less than 95%, the deviation reason is traced back and analyzed, the frequent rules and correction coefficients mined by the sequence pattern mining are updated to provide optimization basis for subsequent production.

[0153] The image recognition-based blow molding product wall thickness online control method provided in the embodiment, through real-time image recognition and dynamic partition calibration, the sampling accuracy and synchronization of time series thickness data are significantly improved, combined with regional deviation feature extraction, the wall thickness control precision and stability are improved. Based on the associated correction parameters mined by the sequence pattern mining, parameter adjustment rules can be automatically generated without manual experience, and the frequent pattern can be recursively expanded to adapt to changes in raw materials and equipment state, realizing closed-loop adaptive control of "deviation-correction", intelligent optimization and dynamic adaptation of process parameters. Through the mapping relationship between the die gap distribution adjustment scheme and the local wall thickness deviation, differential correction strategies can be developed for different regions (such as bottle mouth sealing surface, bottle body load bearing area), avoiding interference of overall adjustment on other regions, and enhancing the directional correction ability of local deviation. High-precision, intelligent online control of blow molding product wall thickness is realized, and the production efficiency and cost control level are improved.

[0154] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0155] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An image recognition based on-line control method of blow molded article wall thickness, characterized by, The method comprises the following steps: Collecting raw material characteristic data, formulating type process parameters according to target blow molding shape, calculating wall thickness adjustment parameters according to wall thickness regulation method by adjusting melt extrusion amount and die gap shape; Adjusting the type process parameters according to the wall thickness adjustment parameters to obtain molding control parameters, collecting image data of the target blow molding product in the molding process, and processing the image data using a dynamic partition calibration method to obtain time-series thickness data; Judging whether the time-series thickness data reaches a preset target thickness threshold, and if yes, maintaining the current molding control parameters, otherwise optimizing the wall thickness adjustment parameters; Extracting wall thickness deviation features from the time-series thickness data, analyzing the linkage between the wall thickness deviation features and the type process parameters to obtain correlation correction parameters according to a sequence pattern mining method, and optimizing the wall thickness adjustment parameters to obtain wall thickness correction parameters.

2. The image recognition based blown plastic article wall thickness online control method according to claim 1, characterized in that, The step of formulating the type process parameters comprises: Determining performance indicators according to product use, obtaining shape parameters of the target blow molding product, and analyzing the basic performance and processing adaptability of the raw material to obtain the raw material characteristic data; Calculating the theoretical extrusion amount according to the single weight and production speed of the target product, and calculating the initial screw rotation speed according to the screw diameter and pitch, and setting the die head temperature of different functional segments according to the use function; Setting the blow molding pressure and cooling water temperature according to the raw material characteristic data, calculating the initial gap of the die according to the target wall thickness and blow ratio of the product, and correcting the initial gap of the die according to the historical optimal parameters of similar products to obtain the type process parameters.

3. The image recognition based blown parison wall thickness online control method of claim 2, wherein, The step of calculating the wall thickness adjustment parameters comprises: Calculating the melt volume extrusion amount in the current production according to the initial screw rotation speed; Collecting the average die gap, die gap distribution and die outlet diameter as the key parameters of the die; Calculating the target required extrusion amount and the target required gap with unchanged die shape according to the preset target thickness threshold; Extruding the raw material according to the target required extrusion amount, and correcting the local wall thickness deviation area according to the target required gap to obtain a die gap distribution adjustment scheme; Detecting the die head pressure data in the blow molding process, calculating the real-time melt viscosity according to the initial screw rotation speed, and adjusting the target required extrusion amount and the target required gap when the viscosity exceeds the preset reference viscosity to obtain the wall thickness adjustment parameters.

4. The image recognition based blown parison wall thickness online control method of claim 3, wherein, The step of adjusting the molding control parameters comprises: Building a parameter mapping table according to the corresponding relationship between the wall thickness adjustment parameters and the type process parameters, and determining the influence amplitude of the unit change of the type process parameters on the wall thickness to form a sensitivity coefficient table; Converting the wall thickness adjustment parameters into adjustment values of the process parameters based on the parameter mapping table and the sensitivity coefficient table; Sorting each parameter in the wall thickness adjustment parameters according to the directness of influence and response speed, and setting the adjustment rate according to the maximum adjustment amount of a single step; Superimposing the adjustment values on the type process parameters, and adjusting according to the equipment safety and process feasibility range to generate the molding control parameters.

5. The image recognition based blown plastic article wall thickness on-line control method according to claim 1, characterized in that, The step of obtaining the time-series thickness data comprises: The sampling frequency is calculated based on the moving speed of the blow molded product and the minimum detection accuracy, and the detection area is divided according to the structure and the circumferential direction of the blow molded product; The image data is collected according to the sampling frequency and the detection area, and pre-processing is performed to obtain pre-processing thickness data; The pre-processing thickness data collected by different sensors is calibrated based on the pulse of the main encoder of the production line as the reference time, the data segment is divided according to the forming cycle for intermittent production, and the abnormal value is removed and the continuity is checked to obtain the time series thickness data.

6. The image recognition based blown parison wall thickness online control method of claim 5, wherein, The steps of extracting the wall thickness deviation feature include: According to the preset target wall thickness threshold as the reference, the absolute deviation and the relative deviation of each sampling point are calculated to define the deviation, and the time series thickness data is sliced to form a regionalized sub-data set according to the detection area; From the perspective of time sequence, the trend feature, the fluctuation feature and the burst feature of the wall thickness deviation are analyzed to obtain the dynamic change rule; From the perspective of the spatial distribution of the blow molded product, the position characteristics of the wall thickness deviation are analyzed to identify local defects and regional differences; The dynamic change rule and the local defects and regional differences are integrated to form the wall thickness deviation feature.

7. The image recognition based blown parison wall thickness online control method of claim 6, wherein, The steps of obtaining the dynamic change rule include: The average deviation and the cumulative deviation in the preset period are calculated, and the change curve of the deviation with time is fitted by linear regression to obtain the trend feature; The standard deviation and the range of the regionalized sub-data set are calculated, and the fluctuation frequency and the corresponding amplitude are extracted by Fourier transform to obtain the fluctuation feature; The deviation peak value and the duration that exceed the preset target wall thickness threshold are extracted as the deviation time, and the deviation change amount of adjacent data points is calculated as the burst feature; The trend feature, the fluctuation feature and the burst feature are integrated to obtain the dynamic change rule.

8. The image recognition based blown parison wall thickness online control method of claim 7, wherein, The steps of obtaining the correlation correction parameter include: The type process parameters and the wall thickness deviation feature are divided into discrete states according to the normal range, and the adjustment action and the burst feature are sequentially coded to form a correlation sequence pair; The PrefixSpan algorithm is used to mine the frequent patterns in the correlation sequence pair; The frequent patterns are converted into process parameter correction rules, including trigger conditions, related process parameters, correction actions and confidence levels; Based on the statistical relationship between the process parameter change amount and the deviation change amount in the frequent patterns, a correction coefficient is calculated; When multiple process parameter correction rules are triggered at the same time, the process parameter correction rule with the maximum correction coefficient is selected as the correlation correction parameter.

9. The image recognition based blown parison wall thickness online control method of claim 8, wherein, The steps of obtaining the frequent patterns include: All the prefix patterns of the items are extracted by traversing all the correlation sequence pairs to calculate the support, and the item prefix patterns exceeding the preset minimum support are formed to form an initial frequent sequence; A projection database is generated for each initial frequent sequence, and all suffix items of the current initial frequent sequence are combined to form candidate item patterns; For each candidate item pattern, the number of occurrences in the projection database is counted, and the frequent item patterns are screened out; For each frequent item pattern, the projection database is continuously constructed, the prefix pattern is recursively expanded, and the long sequence frequent pattern is generated; The short patterns not satisfying the preset length in the long sequence frequent patterns are pruned, and the frequent patterns are sorted by length to form the frequent patterns from short to long.

10. The image recognition based blown parison wall thickness online control method of claim 8, wherein, The step of optimizing the wall thickness correction parameter comprises: A correction mapping table is constructed according to the mapping relationship between the correlation correction parameter and the wall thickness adjustment parameter, and a plurality of adjustment amounts are sorted according to the influence weight of the correlation correction parameter on the wall thickness; Each adjustment amount is adjusted according to the correlation correction parameter and the correction coefficient to obtain a plurality of adjustment parameters; It is judged whether the wall thickness adjusted by the plurality of adjustment parameters reaches the preset target thickness threshold, if yes, the current plurality of adjustment parameters are taken as the wall thickness correction parameter, otherwise, the correction coefficient is recalculated.

Images