Injection product quality monitoring method and device, electronic equipment and storage medium

Abstract

The invention provides an injection molding product quality monitoring method and device, electronic equipment and a storage medium, and belongs to the technical field of intelligent manufacturing. The deviation amount of the real-time sensing curve and the standard sensing interval at each sampling time point is calculated; the weighted sum of the deviation is compared with a deviation threshold value at the measuring point, and an injection molding monitoring result at the measuring point is obtained; and the injection molding monitoring results at all the measuring points are fused, and the injection molding quality of the produced injection molding product is determined. According to the method, a plurality of sensors are arranged in an injection mold to obtain a real-time sensing curve, the deviation of each sampling time point is determined according to the distribution relation between the real-time sensing curve and a standard sensing interval, and different weights are given to the standard sensing interval according to the importance of different stages in the injection molding process; according to the invention, the accuracy of quality monitoring can be effectively improved, the configuration of related detection parameters in the detection process can be more flexible, the operation is simple, the investment of manpower and material resources is effectively reduced, and the cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular, to a method, device, electronic device and storage medium for monitoring the quality of injection molded products. Background Art

[0002] Currently, the quality inspection of injection molded products is mainly completed by manual visual inspection. The general probability of quality defects is relatively small, but due to the large production volume, a large amount of manpower is required, so the cost performance of using manual visual inspection is very low.

[0003] The types of quality defects are generally divided into material shortage, shrinkage, flash, appearance defects, etc. By using the method of manual visual inspection, due to the lack of a unified standard, the reliability is often not high only relying on manual visual inspection, and there are still risks in quality control.

[0004] In addition, the causes of quality defects are generally caused by changes in the injection molding environment or injection molding equipment, and are persistent. Manual visual inspection is often carried out during the post-processing of injection molding, which is not timely, and cannot timely and effectively detect batch quality problems. Summary of the Invention

[0005] The present invention provides a method, device, electronic device and storage medium for monitoring the quality of injection molded products, so as to solve the many defects brought by the existing manual visual inspection, and realize intelligent, precise and low-cost detection.

[0006] In a first aspect, the present invention provides a method for monitoring the quality of injection molded products, including:

[0007] Obtain a real-time sensing curve at a measurement point in any injection molding cycle;

[0008] Calculate the deviation amount at each sampling time point between the real-time sensing curve and the standard sensing interval at the measurement point;

[0009] Obtain the injection molding monitoring result at the measurement point according to the size relationship between the weighted sum of all the deviation amounts and the deviation amount threshold at the measurement point;

[0010] Fuse the injection molding monitoring results at all measurement points to determine the injection molding quality of the injection molded products produced in any injection molding cycle.

[0011] According to the method for monitoring the quality of injection molded products provided by the present invention, the standard sensing interval at the measurement point is pre-constructed based on the following steps:

[0012] Construct a training sample set, and the training samples in the training sample set are historical sensing curves collected at the measurement point in different injection molding cycles in advance;

[0013] Obtain the data maximum value and the data minimum value of each of the historical sensing curves at any sampling time point;

[0014] Determine the data maximum value and the data minimum value as the interval extreme values of the measuring point at the any sampling time point;

[0015] Determine the standard sensing interval of the measuring point according to the interval extreme values of all sampling time points.

[0016] According to an injection product quality monitoring method provided by the present invention, the standard sensing interval of the measuring point is pre-constructed based on the following steps:

[0017] Construct a training sample set, where the training samples in the training sample set are historical sensing curves collected in advance at the measuring point in different injection molding cycles;

[0018] Determine the data expected value and the data variance of the any sampling time point according to the data of each historical sensing curve at the any sampling time point;

[0019] Combine the data expected value, the data variance and the confidence level calculated according to a preset confidence level to determine the confidence interval at the any sampling time point;

[0020] Determine the standard sensing interval according to the confidence intervals of all sampling time points.

[0021] According to an injection product quality monitoring method provided by the present invention, after constructing the training sample set, it further includes:

[0022] Screen the training sample set according to the defective product probability of the injection products produced in all the injection molding cycles, and retain a preset number of training samples closest to the sample central value;

[0023] The preset number is determined based on the defective product probability, and the sample central value is the central value of all the historical sensing curves.

[0024] According to an injection product quality monitoring method provided by the present invention, after screening the training sample set and retaining a preset number of training samples closest to the sample central value, it further includes:

[0025] Perform an alignment operation on each training sample based on the distribution of all sampling time points on the real-time sensing curve;

[0026] After the alignment operation, at least sampling time points corresponding one by one to all sampling time points on the real-time sensing curve are distributed on each training sample.

[0027] According to an injection molding product quality monitoring method provided by the present invention, for any measurement point at any sampling time point, calculating the deviation amount between the real-time sensing curve and the standard sensing interval at the measurement point includes:

[0028] When it is determined that the minimum value of the data in the standard sensing interval is greater than the data on the real-time sensing curve, the deviation amount is the difference between the data and the minimum value of the data;

[0029] When it is determined that the maximum value of the data in the standard sensing interval is less than the data on the real-time sensing curve, the deviation amount is the difference between the data and the maximum value of the data;

[0030] Otherwise, determine that the deviation amount is zero.

[0031] According to an injection molding product quality monitoring method provided by the present invention, obtaining the injection molding monitoring result at the measurement point according to the magnitude relationship between the weighted sum of all the deviation amounts and the deviation amount threshold at the measurement point includes:

[0032] Determine the injection molding time period to which each sampling time point belongs;

[0033] According to different weights pre-configured for different injection molding time periods, determine the weight of the deviation amount at each sampling time point;

[0034] According to the weight of each deviation amount, perform a weighted sum calculation on all the deviation amounts to obtain the weighted sum;

[0035] When it is determined that the weighted sum is greater than the deviation amount threshold, set the injection molding monitoring result at the measurement point as unqualified;

[0036] Otherwise, set the injection molding monitoring result at the measurement point as qualified.

[0037] According to an injection molding product quality monitoring method provided by the present invention, the injection molding time period includes an injection time period, a holding pressure time period, and a cooling time period;

[0038] Before determining the weight of the deviation amount at each sampling time point according to different weights pre-configured for different injection molding time periods, it further includes:

[0039] Perform regularization processing on the weight of the injection time period, the weight of the holding pressure time period, and the weight of the cooling time period;

[0040] The weight of the injection time period is greater than the weight of the holding pressure time period, and the weight of the holding pressure time period is greater than the weight of the cooling time period.

[0041] According to an injection product quality monitoring method provided by the present invention, fusing the injection monitoring results at all measurement points to determine the injection quality of the injection product produced in any injection mold cycle includes:

[0042] If it is determined that the injection monitoring result at any one of all the measurement points is unqualified, it is determined that the injection quality of the injection product produced in any injection mold cycle is unqualified;

[0043] Otherwise, it is determined that the injection quality of the injection product produced in any injection mold cycle is qualified.

[0044] According to an injection product quality monitoring method provided by the present invention, the real-time sensing curve is a pressure sensing curve or a temperature sensing curve.

[0045] In a second aspect, the present invention further provides an injection product quality monitoring device, including:

[0046] A data acquisition unit for acquiring a real-time sensing curve at a measurement point in any injection mold cycle;

[0047] A deviation amount calculation unit for calculating the deviation amount between the real-time sensing curve and the standard sensing interval at the measurement point at each sampling time point;

[0048] An injection monitoring unit for obtaining the injection monitoring result at the measurement point according to the magnitude between the weighted sum of all the deviation amounts and the deviation amount threshold at the measurement point;

[0049] A result detection unit for fusing the injection monitoring results at all measurement points to determine the injection quality of the injection product produced in any injection mold cycle.

[0050] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of any one of the above-mentioned injection product quality monitoring methods are implemented.

[0051] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above-mentioned injection product quality monitoring methods are implemented.

[0052] The injection product quality monitoring method, device, electronic device and storage medium provided by the present invention can effectively improve the accuracy of quality monitoring by installing multiple sensors in the injection mold to obtain real-time sensing curves, determining the deviation amount at each sampling time point based on the distribution relationship between the real-time sensing curves and the standard sensing interval, and assigning different weights to the standard sensing interval according to the importance of different stages in the injection process. The configuration of relevant detection parameters during the detection process can be more flexible, and the operation is simple, effectively reducing the input of human and material resources and reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0054] Figure 1 is a flowchart of the injection product quality monitoring method provided by the present invention;

[0055] Figure 2 is a flowchart of constructing the standard sensing interval provided by the present invention;

[0056] Figure 3 is a schematic diagram of curve alignment using the linear interpolation method provided by the present invention;

[0057] Figure 4 is a schematic diagram of the structure of the injection product quality monitoring device provided by the present invention;

[0058] Figure 5 is a schematic diagram of the structure of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention fall within the scope of protection of the present invention.

[0060] It should be noted that in the description of the embodiments of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element. The orientation or positional relationship indicated by terms such as "upper", "lower", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present invention. Unless otherwise expressly specified and limited, the terms "mounted", "connected", "coupled" shall be construed broadly, e.g., it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection, an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, and may be the internal communication of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention may be understood according to specific circumstances.

[0061] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category, and do not limit the number of objects. For example, the first object may be one or more.

[0062] The following is combined with Figures 1-5 to describe the injection molding product quality monitoring method, device, electronic device and storage medium provided by the embodiments of the present invention.

[0063] It should be noted that the execution subject of the injection molding product quality monitoring method provided by the present invention may be a server, a computer device, such as a mobile phone, a tablet computer, a notebook computer, a handheld computer, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), an industrial control computer, etc. Without further explanation, in the following embodiments, the industrial control computer that controls the operation of the injection molding machine is used as the execution subject for description, which is not regarded as a specific limitation of the protection scope of the present invention.

[0064] Figure 1It is a schematic flow chart of the injection product quality monitoring method provided by the present invention. As Figure 1 shown, it includes but is not limited to the following steps:

[0065] Step 101: Obtain the real-time sensing curve at a measurement point in any injection molding cycle.

[0066] To implement the injection product quality monitoring method provided by the present invention, sensors need to be installed and arranged at some key measurement points of the injection mold in advance.

[0067] For example, the area near the gate of the injection mold is the first to contact the flowing melt, and it contains the richest information. Therefore, a pressure sensor can be set at this part. The pressure sensor can directly measure the change in pressure and convert it into an electrical signal. Connect the pressure sensor to the signal receiving port of the industrial control computer. The industrial control computer can convert the electrical signal measured by the pressure sensor into a digital signal and record it to generate a pressure sensing curve.

[0068] In addition, the real-time sensor can also be a temperature sensing curve, which is collected in real time by means of a temperature sensor installed at a certain measurement point.

[0069] For the convenience of description, in the subsequent embodiments, the real-time sensing curve is taken as an example of the pressure sensing curve for description.

[0070] Of course, before collecting the real-time sensing curve, it is necessary to set the collection parameters in advance, such as the sampling frequency, sampling duration, etc. These collection parameters can be set according to the required collection accuracy.

[0071] Step 102: Calculate the deviation amount between the real-time sensing curve and the standard sensing interval at the measurement point at each sampling time point.

[0072] Assume that the injection pressure value at each measurement point is obtained at each sampling time point according to the preset sampling frequency, that is, the injection pressure at each measurement point.

[0073] In advance, according to the historical injection data, the standards for realizing quality detection are determined in advance, that is, for each different measurement point, at different sampling time points in each injection molding cycle, a standard sensing interval is determined in advance through experiments. This standard sensing interval includes a data maximum value and a data minimum value.

[0074] After the pressure sensing curve at a certain measurement point in the current injection molding cycle has been obtained, the injection pressure value corresponding to each sampling time point can be read from this pressure sensing curve.

[0075] For any sampling time point, if the corresponding injection pressure value is greater than the maximum value of the data within the standard sensing range at this measurement point, or the injection pressure value is less than the minimum value of the data within the standard sensing range at this measurement point, it can be considered that the pressure at this measurement point deviates at this any sampling time point, and the deviation amount at this sampling time point can be calculated according to the difference between the injection pressure value and the maximum value or the minimum value of the data.

[0076] Step 103: Obtain the injection monitoring result at this measurement point according to the magnitude relationship between the weighted sum of all the deviation amounts and the deviation amount threshold at this measurement point.

[0077] Different stages in the injection molding process may have different degrees of influence on the quality and performance of the product. For example, the injection stage and the holding pressure stage have a greater degree of influence compared to the cooling stage.

[0078] In view of this, the injection product quality monitoring method provided by the present invention configures different weights for different stages in the injection molding process, and then according to the stage to which the sampling time point belongs, configures this weight to the deviation amount determined for each sampling time point.

[0079] In this way, by calculating the weighted sum of the deviation amounts of all sampling time points at a certain measurement point, it is used as the total deviation amount at this measurement point during the entire injection molding process of this injection molding cycle.

[0080] Among them, the weighted sum of the deviation amounts of all sampling time points at a certain measurement point refers to, at a certain measurement point, the weight determined by the stage to which each sampling time point belongs is multiplied by the deviation amount of this sampling time point to obtain the weighted deviation amount of this sampling time point; then, the weighted deviation amounts of all sampling times are accumulated, and the weighted sum of the deviation amounts of all sampling time points can be calculated.

[0081] In addition, this application adopts an experimental method. By collecting relevant parameters in a large number of historical injection molding cycles of the same injection molding machine, the deviation amount threshold at each measurement point is determined in advance, and this deviation amount threshold is used to check the deviation amount collected at each measurement point during the actual injection molding process.

[0082] Compare the calculated total deviation amount with the deviation amount threshold at this measurement point. If the total deviation amount is greater than the deviation amount threshold, it is determined that the injection monitoring result at this measurement point is unqualified; otherwise, it can be determined that the injection monitoring result at this measurement point is qualified.

[0083] Among them, the deviation amount threshold at each measurement point is determined in advance by an experimental method, generally determined by analyzing a relatively large number of training samples collected at this measurement point, which will not be elaborated here.

[0084] Step 104: Integrate the injection molding monitoring results at all measurement points to determine the injection molding quality of the injection molded products produced in any injection molding cycle.

[0085] Generally, multiple sensors of the same or different categories are set at different measurement points in the injection mold of the injection molding machine, and different real-time sensors can be obtained respectively. By using the method provided in the above embodiment, the injection molding monitoring results at each measurement point can be obtained, and then the injection molding monitoring results at all measurement points can be integrated to accurately evaluate the injection molding quality of the injection molded products produced in this injection molding cycle.

[0086] The injection molded product quality monitoring method provided by the present invention can effectively improve the accuracy of quality monitoring by installing multiple sensors in the injection mold to obtain real-time sensing curves, determining the deviation amount of each sampling time point according to the distribution relationship between the real-time sensing curves and the standard sensing interval, and assigning different weights to the standard sensing interval according to the importance of different stages in the injection molding process. The configuration of relevant detection parameters in the detection process can be more flexible, the operation is simple, the input of manpower and material resources is effectively reduced, and the cost is reduced.

[0087] Based on the content of the above embodiment, as an optional embodiment, the standard sensing interval at the measurement point is pre-constructed based on the following steps:

[0088] Construct a training sample set, and the training samples in the training sample set are historical sensing curves collected in advance at the measurement point in different injection molding cycles;

[0089] Obtain the data maximum value and data minimum value of each historical sensing curve at any sampling time point;

[0090] Determine the data maximum value and the data minimum value as the interval extreme values at the measurement point at any sampling time point;

[0091] Determine the standard sensing interval at the measurement point according to the interval extreme values of all sampling time points.

[0092] In this embodiment, a method for determining the interval extreme value of the standard sensing interval by taking the data maximum value and data minimum value is provided.

[0093] Suppose there are N training samples in the constructed training sample set, and these training samples are historical sensing curves collected at a certain measurement point (hereinafter referred to as the target measurement point) in multiple injection molding cycles.

[0094] All historical sensing curves can be time-aligned first, that is, all sampling time points corresponding to the training samples are made consistent, including t 1 , t 2 , …, tm There are a total of m sampling time points. Then, the data of the nth training sample at the kth sampling time point is denoted as x n (t k ).

[0095] Assume that the interval extreme values (including the interval maximum value and the interval minimum value) of the standard sensing interval at these sampling time points are u 1 , u 2 , …, u m and b 1 , b 2 , …, b m , that is, the interval maximum value at the kth sampling time point is u k and the interval minimum value is b k , then there is:

[0096] u k =max(x p (t k )), 1 ≤ p ≤ N;

[0097] b k =min(x p (t k ), 1 ≤ p ≤ N;

[0098] where p is the pth among all training samples.

[0099] As another alternative embodiment, the present invention also provides a method for calculating the interval extreme values of the standard sensing interval at each sampling time point in a probability distribution manner, specifically including but not limited to:

[0100] Construct a training sample set, and the training samples in the training sample set are historical sensing curves collected in advance at the measurement points in different injection molding cycles;

[0101] According to the data of each historical sensing curve at any sampling time point, determine the data expected value and data variance of the any sampling time point;

[0102] Combine the data expected value, data variance, and confidence level calculated according to the preset confidence level to determine the confidence interval at the any sampling time point;

[0103] According to the confidence intervals of all sampling time points, determine the standard sensing interval.

[0104] The calculation formula for the data expected value μ k is:

[0105]

[0106] The data variance σk The calculation formula is as follows:

[0107]

[0108] Then the confidence interval at any sampling time point can be expressed as:

[0109] u k = μ k + cσ k ;

[0110] b k = μ k - cσ k ;

[0111] Wherein, u k is the upper limit value of the confidence interval, which can be set as the maximum value of the standard sensing interval at the kth sampling time point; b k is the lower limit value of the confidence interval, which can be set as the minimum value of the standard sensing interval at the kth sampling time point. c is the adjustment parameter of the interval width of the confidence interval, and its value range is non - negative real numbers. Generally, it is determined by the confidence level, representing the expected coverage degree of the confidence interval for the sampling time point, and can be preset.

[0112] The injection - molded product quality monitoring method provided by the present invention provides multiple ways to process the data of multiple training samples collected historically at each sampling time, and can successively determine the standard sensing interval corresponding to each sampling time point. In actual quality detection, fine - grained analysis can be carried out on the data at each sampling time point for different measuring points. Compared with the prior art by comparing curves, the detection accuracy has been significantly improved, the credibility is higher, and the entire detection process does not require manual participation, with high automation, effectively reducing the input of human and material resources and cutting costs.

[0113] Based on the content of the above - mentioned embodiment, as an alternative embodiment, after constructing the training sample set, it further includes:

[0114] According to the defective product probability of the injection - molded products produced by all the injection - molding cycles, screen the training sample set, and retain a preset number of training samples closest to the sample central value;

[0115] The preset number is determined based on the defective product probability, and the sample central value is the central value of all the historical sensing curves.

[0116] First, the defective product probability α of the injection - molding die of the injection - molding machine can be obtained according to historical experience or sampling.

[0117] Determine the number of all training samples in the training sample set for standard sensing interval training, denoted as N.

[0118] According to the defective product probability α, screen the training sample set to determine the number of training samples T finally used for training:

[0119]

[0120] where is the symbol for performing the floor calculation on x.

[0121] Figure 2 is the flow schematic diagram for constructing the standard sensing interval provided by the present invention. As Figure 2 shown, in the implementation manner of screening out the T training samples closest to the sample central value from N training samples for final training, it can be:

[0122] First, the calculated sample central value can be the average value, median or other representative statistics of all samples, and it is in units of sampling time points.

[0123] Then, for each training sample, calculate the distance between it and the central value. The distance can be measured using the Euclidean distance, Manhattan distance or other appropriate distance measurement methods. The smaller the distance, the closer the sample is to the central value.

[0124] After sorting the calculated distances of each training sample in ascending order, select the T training samples closest to the central value from the sorted samples for retention.

[0125] Finally, determine the standard sensing interval by adopting any one of the two methods provided in the above embodiments, including:

[0126] For each sampling time point, take the maximum value and the minimum value of the data in the T training samples to determine the interval extreme values of the standard sensing interval.

[0127] Or, for each sampling time point, perform a probability distribution calculation on the T training samples, and determine the standard sensing interval according to a preset confidence level.

[0128] For the injection product quality monitoring method provided by the present invention, before constructing the standard sensing interval at each sampling time point using the training samples collected historically, first eliminate the possible negative samples in the training sample set, which can further improve the accuracy of injection quality monitoring.

[0129] Based on the content of the above embodiments, as an optional embodiment, after screening the training sample set and retaining the preset number of training samples closest to the sample central value, it further includes:

[0130] Based on the distribution of all sampling time points on the real-time sensing curve, alignment operations are performed on each training sample;

[0131] On each training sample after the alignment operation, there are at least sampling time points corresponding one-to-one to all sampling time points on the real-time sensing curve.

[0132] To accurately determine the standard sensing interval at each sampling time point, after obtaining the sensing curve at a measurement point in any injection molding cycle, the present invention will perform a curve alignment operation on it. The reason is that due to the influence of equipment performance differences, etc., generally there will be a problem of misaligned acquisition time points, and it is impossible to directly calculate the deviation amount of each acquisition time point accurately according to the method provided in the above embodiments. This problem can be solved by curve alignment.

[0133] The curve alignment operation is a method for comparing and analyzing the similarity between different curves. In the present invention, by aligning the real-time sensing curve with each training sample (i.e., the historical sensing curve), it is mainly to ensure that both have the same sampling time points, that is, for each sampling time point, data can be read on both the real-time sensing curve and each training sample. In addition to performing curve alignment when determining the standard sensing interval, in the actual detection process, curve alignment operations are often also required for the collected real-time sensing curves.

[0134] Figure 3 It is a schematic diagram of curve alignment using the linear interpolation method provided by the present invention. As Figure 3 shown, there is data at both the upper limit and the lower limit of the standard sensing interval at the sampling time points from t 0 to t 4 . The real-time sensing curve has data at the acquisition times of t' 1 , t' 2 and t' 3 . To obtain the data of the real-time sensing curve at the sampling time point t 1 , the following linear interpolation method can be used for calculation:

[0135]

[0136]

[0136] Among them, x(t' 1 ) refers to the data of the real-time sensing curve at the acquisition time of t' 1 , x(t' 2 ) refers to the data of the real-time sensing curve at the acquisition time of t' 2 , and x(t 1 ) is the data of the real-time sensing curve calculated by the linear interpolation method at the acquisition time of t 1Data at that time.

[0137] Based on the content of the above embodiments, as an alternative embodiment, for any sampling time point of any measurement point, calculating the deviation amount between the real-time sensing curve and the standard sensing interval at the measurement point includes:

[0138] When it is determined that the minimum value of the data in the standard sensing interval is greater than the data on the real-time sensing curve, the deviation amount is the difference between the data and the minimum value of the data;

[0139] When it is determined that the maximum value of the data in the standard sensing interval is less than the data on the real-time sensing curve, the deviation amount is the difference between the data and the maximum value of the data;

[0140] Otherwise, determine that the deviation amount is zero.

[0141] During the actual operation process, according to the different numbers of sensors installed in the injection mold, data collection of the sensors at each measurement point will be performed in each injection cycle, respectively forming a real-time sensing curve.

[0142] Assume there are N measurement points, and each measurement point is equipped with only one sensor. Then the real-time sensing curves corresponding to the N sensors can be denoted as x 1 (t), x 2 (t), …, x N (t). For the real-time sensing curve of one of the sensors at t k The calculation method of the deviation amount at the sampling time point is as follows:

[0143]

[0144] Where, d n (t k ) is the deviation amount of the real-time sensing curve of the nth sensor at t k The sampling time point, x n (t k ) is the data of the real-time sensing curve of the nth sensor at t k The sampling time point, u n (t k ) is the minimum value of the data in the standard sensing interval at t k The sampling time point, q n (t k ) is the maximum value of the data in the standard sensing interval at t k The sampling time point.

[0145] Furthermore, obtaining the injection monitoring result at the measurement point according to the magnitude relationship between the weighted sum of all the deviation amounts and the deviation amount threshold at the measurement point includes:

[0146] Determine the injection molding time period to which each sampling time point belongs;

[0147] Determine the weight of the deviation amount of each sampling time point according to different weights pre-configured for different injection molding time periods;

[0148] Perform a weighted sum calculation on all deviation amounts according to the weight of each deviation amount to obtain the weighted sum;

[0149] When it is determined that the weighted sum is greater than the deviation threshold, set the injection molding monitoring result at the measuring point to unqualified;

[0150] Otherwise, set the injection molding monitoring result at the measuring point to qualified.

[0151] Specifically, after obtaining the deviation amount of the nth sensor at each sampling time point, the total deviation amount of the nth sensor in this injection molding cycle can be calculated by performing a weighted sum calculation in combination with the weight corresponding to the injection molding stage where each sampling time point is located:

[0152]

[0153] where d n (t k ) is the deviation amount of the nth sensor at the t k th sampling time point, c n (t k ) is the weight of the nth sensor at the t k th sampling time point, K is the total number of sampling time points, and d n is the total deviation amount of the nth sensor in this injection molding cycle.

[0154] After obtaining the total deviation amount d n of the nth sensor in this injection molding cycle, retrieve the pre-determined deviation threshold of the nth sensor to verify whether the total deviation amount d n in the current injection molding cycle exceeds the standard.

[0155] If d n is greater than the corresponding deviation threshold, it indicates that the sampling data at the measuring point where the current injection molding cycle is located for this sensor is abnormal, that is, it can be determined that the injection molding monitoring result at this measuring point is unqualified. If d n is less than or equal to the corresponding deviation threshold, it proves that the injection molding monitoring result at this measuring point is qualified.

[0156] The injection product quality monitoring method provided by the present invention can perform individual detection on each measuring point set in the injection mold, enabling more fine-grained implementation of refined management for the entire injection molding process, and the detection results will be more accurate.

[0157] As an alternative embodiment, the injection molding time period includes an injection time period, a holding pressure time period, and a cooling time period;

[0158] Before determining the weights of the deviation amounts at each sampling time point according to different weights pre-configured for different injection molding time periods, it further includes:

[0159] Performing regularization processing on the weight of the injection time period, the weight of the holding pressure time period, and the weight of the cooling time period;

[0160] The weight of the injection time period is greater than the weight of the holding pressure time period, and the weight of the holding pressure time period is greater than the weight of the cooling time period.

[0161] The influence of each injection molding stage on the quality of the injection molded product is different. By performing segmented weighting on the injection molding stages, the influence of different injection molding stages on the quality can be distinguished. Higher weights can be assigned to the injection stage and the holding pressure stage, which have a greater impact on the quality, while a relatively lower weight can be assigned to the cooling stage to further improve the accuracy of quality detection.

[0162] At the same time, the durations of the injection molding stages of different injection molds are different, and the segmentation points and weight magnitudes of the injection molding stages can be flexibly configured to adapt to the quality detection requirements of different injection molds.

[0163] In this embodiment, the entire injection molding process is set to three injection molding stages, namely the injection stage, the holding pressure stage, and the cooling stage, which is equivalent to dividing the entire injection molding time period into an injection time period, a holding pressure time period, and a cooling time period.

[0164] The above-mentioned division method for the entire injection molding time period can be: the injection time period includes two durations: the mold closing duration and the injection duration. Among them, the mold closing duration is generally a fixed value and can be set by historical data or experience. The injection duration can be determined according to two process parameters, the injection speed v and the injection stroke x of the injection mold, and the injection duration is obtained by x / v.

[0165] Of course, if the injection speed v and the injection stroke x are divided into multiple segments, that is, the injection speed has v 1 , v 2 , …, v n , and the injection stroke has x 1 , x 2 , …, x n , then the injection segment duration can be correspondingly determined as:

[0166]

[0167] where n is the total number of segments of the injection stroke x.

[0168] Regarding the holding pressure time period, it is mainly determined by the process parameter of "holding pressure duration". The holding pressure duration is generally set in segments, and the total holding pressure duration of all segments is the sum of the holding pressure durations of each segment.

[0169] In addition, excluding the above-mentioned injection time period and holding pressure time period, it is the cooling time period.

[0170] It should be noted that the above-mentioned division method for different injection molding stages is only for illustrative purposes and is not regarded as a specific limitation of the protection scope of the present invention. Other existing methods can also be used for more detailed division. The present invention only assigns different weights to the deviation amounts of the sampling time points in the different injection molding stages after division. Generally speaking, different non-negative weights will be assigned to different injection molding stages.

[0171] As an alternative embodiment, after assigning a weight to each injection molding stage, the weights of all injection molding stages can also be regularized.

[0172] The purpose of regularizing all weights is to standardize them so that their sum is equal to 1. The purpose of doing this is to ensure that the relative proportions of the weights are appropriate overall and can be more conveniently used in subsequent deviation amount calculations or analyses.

[0173] The effects of such a sampling processing method are mainly manifested in:

[0174] 1) It can standardize the weights: Through regularization, the range of the weights can be restricted between 0 and 1, which is convenient for understanding and comparing each weight. This can avoid the situation where the absolute values of the weights are too large or too small, making them more interpretable.

[0175] 2) The sum of the weights is unified to 1: Through regularization, it can be ensured that the sum of all weights is 1. This means that the relative proportion of each weight is appropriate and can show the importance of each factor in the whole. This is very useful when weighing the importance of different factors.

[0176] 3) Simplify calculations and analyses: The regularized weights can be more conveniently used for calculations and analyses. For example, the regularized weights can be multiplied by other parameters with weights to obtain a comprehensive result without considering the numerical range or sum of the weights.

[0177] All in all, by regularizing the weights, it can be ensured that they have an appropriate numerical range and the sum is 1, so as to better reflect the relative importance of each weight in the whole and improve the accuracy and interpretability of detection.

[0178] Based on the content of the above embodiments, as an alternative embodiment, the method of fusing the injection molding monitoring results at all measurement points to determine the injection molding quality of the injection molded products produced in any injection molding cycle includes:

[0179] If it is determined that the injection molding monitoring result at any one of all the measurement points is unqualified, it is determined that the injection molding quality of the injection molded products produced in the any injection molding cycle is unqualified;

[0180] Otherwise, it is determined that the injection molding quality of the injection molded products produced in the any injection molding cycle is qualified.

[0181] Specifically, in one injection molding cycle, for the real-time sensing curves at each measurement point, the corresponding total deviation degree d n is calculated and compared with the deviation amount threshold D n related to this measurement point. If d n ≤D n , the injection molding monitoring result at this measurement point is qualified; if d n >D n , the injection molding monitoring result at this measurement point is determined to be unqualified for the quality judgment of this injection molding cycle.

[0182] For all N measurement points, N injection molding monitoring results can be obtained according to the above logic. The determination of the injection molding quality of this injection molded part is obtained by fusing these N injection molding monitoring results.

[0183] As an alternative fusion method: if any one of the N injection molding monitoring results is unqualified, it is determined that the injection molding quality of this injection molded part is unqualified.

[0184] Of course, other logical discrimination methods can also be customized to perform logical calculations on the N injection molding monitoring results to obtain the final determination result.

[0185] Finally, the result of the final detection algorithm for the injection molding quality can be associated with the robotic arm to achieve the function of controlling the robotic arm to sort out defective products.

[0186] Figure 4 is a schematic structural diagram of the injection molded product quality monitoring device provided by the present invention. As shown in Figure 4 , it mainly includes a data acquisition unit 41, a deviation amount calculation unit 42, an injection molding monitoring unit 43, and a result detection unit 44, where:

[0187] The data acquisition unit 41 is used to obtain the real-time sensing curve at a measurement point in any injection molding cycle;

[0188] The deviation amount calculation unit 42 is used to calculate the deviation amount between the real-time sensing curve and the standard sensing interval at the measurement point at each sampling time point;

[0189] The injection molding monitoring unit 43 is configured to obtain the injection molding monitoring result at the measurement point according to the magnitude relationship between the weighted sum of all the deviation amounts and the deviation amount threshold at the measurement point;

[0190] The result detection unit 44 is configured to fuse the injection molding monitoring results at all the measurement points to determine the injection molding quality of the injection molded product produced in any injection molding cycle.

[0191] It should be noted that the injection molded product quality monitoring device provided in the embodiment of the present invention can execute the injection molded product quality monitoring method described in any of the above embodiments during specific operation, and details thereof are not described in this embodiment.

[0192] The injection molded product quality monitoring device provided by the present invention can effectively improve the accuracy of quality monitoring by installing multiple sensors in the injection mold to obtain real-time sensing curves, determining the deviation amounts at each sampling time point based on the distribution relationship between the real-time sensing curves and the standard sensing intervals, and assigning different weights to the standard sensing intervals according to the importance of different stages in the injection molding process. The configuration of relevant detection parameters during the detection process can be more flexible, and the operation is simple, effectively reducing the investment in human and material resources and reducing costs.

[0193] Figure 5 is a schematic structural diagram of an electronic device provided by the present invention. As Figure 5 shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540. Among them, the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the injection molded product quality monitoring method, and the method includes: obtaining a real-time sensing curve at a measurement point in any injection molding cycle; calculating the deviation amount at each sampling time point between the real-time sensing curve and the standard sensing interval at the measurement point; obtaining the injection molding monitoring result at the measurement point according to the magnitude relationship between the weighted sum of all the deviation amounts and the deviation amount threshold at the measurement point; fusing the injection molding monitoring results at all the measurement points to determine the injection molding quality of the injection molded product produced in any injection molding cycle.

[0194] In addition, when the logical instructions in the above-mentioned memory 530 can be 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 such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0195] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the injection product quality monitoring method provided in the above-mentioned various embodiments. The method includes: obtaining a real-time sensing curve at a measurement point in any injection molding cycle; calculating the deviation amount at each sampling time point between the real-time sensing curve and the standard sensing interval at the measurement point; obtaining the injection monitoring result at the measurement point according to the magnitude relationship between the weighted sum of all the deviation amounts and the deviation amount threshold at the measurement point; and fusing the injection monitoring results at all the measurement points to determine the injection quality of the injection product produced in any injection molding cycle.

[0196] On another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is configured to execute the injection product quality monitoring method provided in the above-mentioned various embodiments. The method includes: obtaining a real-time sensing curve at a measurement point in any injection molding cycle; calculating the deviation amount at each sampling time point between the real-time sensing curve and the standard sensing interval at the measurement point; obtaining the injection monitoring result at the measurement point according to the magnitude relationship between the weighted sum of all the deviation amounts and the deviation amount threshold at the measurement point; and fusing the injection monitoring results at all the measurement points to determine the injection quality of the injection product produced in any injection molding cycle.

[0197] The device embodiments described above are merely illustrative. 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 to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0198] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0199] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An injection molding product quality monitoring method, characterized in that, it includes: Obtain the real-time sensing curve at a measurement point in any injection molding cycle; Calculate the deviation amount between the real-time sensing curve and the standard sensing interval at the measurement point at each sampling time point; Obtain the injection molding monitoring result at the measurement point according to the magnitude relationship between the weighted sum of all the deviation amounts and the deviation amount threshold at the measurement point; Fuse the injection molding monitoring results at all measurement points to determine the injection molding quality of the injection molding products produced in any injection molding cycle.

2. The injection molding product quality monitoring method according to claim 1, characterized in that, The standard sensing interval at the measurement point is pre-constructed based on the following steps: Construct a training sample set, and the training samples in the training sample set are historical sensing curves collected in advance at the measurement point in different injection molding cycles; Obtain the data maximum value and the data minimum value of each historical sensing curve at any sampling time point; Determine the interval extreme values at the measurement point at any sampling time point by using the data maximum value and the data minimum value; Determine the standard sensing interval at the measurement point according to the interval extreme values at all sampling time points.

3. The injection molding product quality monitoring method according to claim 1, characterized in that, The standard sensing interval at the measurement point is pre-constructed based on the following steps: Construct a training sample set, and the training samples in the training sample set are historical sensing curves collected in advance at the measurement point in different injection molding cycles; Determine the data expected value and the data variance at any sampling time point according to the data of each historical sensing curve at any sampling time point; Combine the data expected value, the data variance and the confidence level calculated according to the preset confidence level to determine the confidence interval at any sampling time point; Determine the standard sensing interval according to the confidence intervals at all sampling time points.

4. The injection molding product quality monitoring method according to any one of claims 2-3, characterized in that, After constructing the training sample set, it further includes: Screen the training sample set according to the defective product probability of the injection molding products produced in all the injection molding cycles, and retain the preset number of training samples closest to the sample central value; The preset number is determined based on the defective product probability, and the sample central value is the central value of all the historical sensing curves.

5. The injection molding product quality monitoring method according to claim 4, characterized in that, After screening the training sample set and retaining the preset number of training samples closest to the sample central value, it further includes: Perform an alignment operation on each training sample based on the distribution of all sampling time points on the real-time sensing curve; After the alignment operation, at least the sampling time points corresponding one by one to all the sampling time points on the real-time sensing curve are distributed on each training sample.

6. The injection molding product quality monitoring method according to claim 1, characterized in that, For any sampling time point of any measurement point, calculating the deviation amount between the real-time sensing curve and the standard sensing interval at the measurement point includes: When it is determined that the minimum value of the data in the standard sensing interval is greater than the data on the real-time sensing curve, the deviation amount is the difference between the data and the minimum value of the data; When it is determined that the maximum value of the data in the standard sensing interval is less than the data on the real-time sensing curve, the deviation amount is the difference between the data and the maximum value of the data; Otherwise, determine that the deviation amount is zero.

7. The injection product quality monitoring method according to claim 1, characterized in that, obtaining the injection monitoring result at the measuring point according to the magnitude between the weighted sum of all the deviation amounts and the deviation amount threshold at the measuring point, includes: determine the injection time period to which each sampling time point belongs; determine the weight of the deviation amount at each sampling time point according to different weights pre-configured for different injection time periods; perform a weighted sum calculation on all the deviation amounts according to the weight of each deviation amount to obtain the weighted sum; when it is determined that the weighted sum is greater than the deviation amount threshold, set the injection monitoring result at the measuring point to unqualified; otherwise, set the injection monitoring result at the measuring point to qualified.

8. The injection product quality monitoring method according to claim 7, characterized in that, the injection time period includes an injection time period, a holding pressure time period, and a cooling time period; before determining the weight of the deviation amount at each sampling time point according to different weights pre-configured for different injection time periods, further includes: perform regularization processing on the weight of the injection time period, the weight of the holding pressure time period, and the weight of the cooling time period; the weight of the injection time period is greater than the weight of the holding pressure time period, and the weight of the holding pressure time period is greater than the weight of the cooling time period.

9. The injection product quality monitoring method according to claim 1, characterized in that, fusing the injection monitoring results at all the measuring points to determine the injection quality of the injection products produced by any injection mold number, includes: when it is determined that the injection monitoring result at any one of all the measuring points is unqualified, determine that the injection quality of the injection products produced by any injection mold number is unqualified; otherwise, determine that the injection quality of the injection products produced by any injection mold number is qualified.

10. The injection product quality monitoring method according to claim 1, characterized in that, the real-time sensing curve is a pressure sensing curve or a temperature sensing curve.

11. An injection product quality monitoring device, characterized in that, includes: a data acquisition unit for obtaining a real-time sensing curve at a measuring point in any injection mold number; a deviation amount calculation unit for calculating the deviation amount between the real-time sensing curve and the standard sensing interval at the measuring point at each sampling time point; an injection monitoring unit for obtaining the injection monitoring result at the measuring point according to the magnitude between the weighted sum of all the deviation amounts and the deviation amount threshold at the measuring point; a result detection unit for fusing the injection monitoring results at all the measuring points to determine the injection quality of the injection products produced by any injection mold number.

12. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, when the processor executes the computer program, the injection product quality monitoring method according to any one of claims 1 to 10 is implemented.

13. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the injection product quality monitoring method according to any one of claims 1 to 10 is implemented.

Images