CN113665079B

CN113665079B - Plastic injection molding process control method and system

Info

Publication number: CN113665079B
Application number: CN202110976691.9A
Authority: CN
Inventors: 王静衡
Original assignee: Wuhan Hengde Industrial Co ltd
Current assignee: Wuhan Hengde Industrial Co ltd
Priority date: 2021-08-24
Filing date: 2021-08-24
Publication date: 2023-06-30
Anticipated expiration: 2041-08-24
Also published as: CN113665079A

Abstract

The invention discloses a control method and a system for a plastic injection molding process, wherein the method comprises the following steps: at least collecting data of a machine, a die and related auxiliary machines; analyzing the data by adopting a Markov distance algorithm to generate a group of standard process curves; respectively carrying out segmentation treatment on each standard process curve to obtain segmentation results; based on the segmentation result, respectively analyzing the fluctuation range of each parameter point on each section of curve of each standard process curve; and judging the quality of the plastic injection molded product based on the fluctuation range of each parameter point on each section of curve of each standard process curve to obtain a product quality judgment result, wherein the product quality judgment result comprises good products and defective products. Compared with the existing mode of manually determining the process parameters, the invention can collect and analyze the process parameters, can more effectively control the plastic injection molding process, further reduces the rejection rate of products and improves the stability of the product quality.

Description

Plastic injection molding process control method and system

Technical Field

The invention relates to the technical field of plastic injection molding, in particular to a plastic injection molding process control method and a plastic injection molding process control system.

Background

At present, in the plastic injection molding industry, the common cultural degree of operators of the regulator is not high, the process technology is mostly derived from teaching and experience accumulation of teachers and students, and the set parameters are set by adopting a trial-and-error method when the machine is started for production each time, so that the problems of high product rejection rate and unstable quality are easy to occur.

Therefore, how to collect and analyze the technological parameters during plastic injection molding, so as to control the plastic injection molding process in a more effective way, thereby reducing the rejection rate of products and improving the stability of the quality of the products is a problem to be solved urgently.

Disclosure of Invention

In view of the above, the invention provides a plastic injection molding process control method, which can collect and analyze process parameters and can more effectively control the plastic injection molding process, thereby reducing the rejection rate of products and improving the stability of product quality compared with the existing mode of manually determining the process parameters.

The invention provides a plastic injection molding process control method, which is characterized by comprising the following steps:

at least collecting data of a machine, a die and related auxiliary machines;

analyzing the data by adopting a Markov distance algorithm to generate a group of standard process curves;

respectively carrying out segmentation treatment on each standard process curve to obtain segmentation results;

based on the segmentation result, respectively analyzing the fluctuation range of each parameter point on each section of curve of each standard process curve;

and judging the quality of the plastic injection molded product based on the fluctuation range of each parameter point on each section of curve of each standard process curve to obtain a product quality judgment result, wherein the product quality judgment result comprises good products and defective products.

Preferably, the method further comprises:

acquiring a feedback result of a quality person on the judgment result of the product quality;

and adjusting a threshold value for judging the quality of the product based on the judging result of the quality of the product and the feedback result.

Preferably, the method further comprises:

clustering the process curves corresponding to the defective products in the judging result of the product quality to obtain the categories of the process curves corresponding to the defective products;

acquiring identification content for identifying the category of the process curve corresponding to the defective product by a craftsman, wherein the identification content comprises: poor content and poor cause.

Preferably, the method further comprises:

judging the quality of a newly produced plastic injection molded product based on the adjusted threshold value for judging the quality of the product to obtain a judging result of the quality of the newly produced product, wherein the judging result of the quality of the newly produced product comprises good products and defective products;

and matching the process curve corresponding to the newly produced defective product with the category of the process curve corresponding to the defective product, and outputting the defective content and the defective reason of the newly produced defective product.

Preferably, the step of separately performing a segmentation process on each standard process curve to obtain segmentation results includes:

each standard process curve is divided into a filling stage, a feeding stage, a pressure maintaining stage and a cooling stage.

A plastic injection molding process control system, comprising:

the data acquisition module is used for at least acquiring data of the machine, the die and related auxiliary machines;

the first analysis module is used for analyzing the data by adopting a Markov distance algorithm to generate a group of standard process curves;

the segmentation module is used for respectively carrying out segmentation processing on each standard process curve to obtain segmentation results;

the second analysis module is used for respectively analyzing the fluctuation range of each parameter point on each section of curve of each standard process curve based on the segmentation result;

the first judging module is used for judging the quality of the plastic injection molded product based on the fluctuation range of each parameter point on each section of curve of each standard process curve to obtain a judging result of the product quality, wherein the judging result of the product quality comprises good products and defective products.

Preferably, the system further comprises:

the first acquisition module is used for acquiring feedback results of judgment results of quality personnel on the product quality;

and the adjusting module is used for adjusting a threshold value for judging the quality of the product based on the judging result of the quality of the product and the feedback result.

Preferably, the system further comprises:

the clustering module is used for clustering the process curves corresponding to the defective products in the judging result of the product quality to obtain the categories of the process curves corresponding to the defective products;

the second obtaining module is used for obtaining identification contents for identifying the category of the process curve corresponding to the defective product by a craftsman, and the identification contents comprise: poor content and poor cause.

Preferably, the system further comprises:

the second judging module is used for judging the quality of the newly produced plastic injection molded product based on the adjusted threshold value for judging the quality of the product to obtain a judging result of the quality of the newly produced product, wherein the judging result of the quality of the newly produced product comprises good products and defective products;

and the matching module is used for matching the process curve corresponding to the newly produced defective product with the category of the process curve corresponding to the defective product and outputting the defective content and the defective reason of the newly produced defective product.

Preferably, the segmentation module is specifically configured to:

In summary, the invention discloses a control method for plastic injection molding process, when the plastic injection molding process is required to be controlled, firstly, at least collecting data of a machine, a die and related auxiliary machines, then analyzing the data by adopting a mahalanobis distance algorithm to generate a group of standard process curves, and respectively carrying out sectional treatment on each standard process curve to obtain a sectional result; then, based on the segmentation result, respectively analyzing the fluctuation range of each parameter point on each section of curve of each standard process curve; and judging the quality of the plastic injection molded product based on the fluctuation range of each parameter point on each section of curve of each standard process curve to obtain a product quality judgment result, wherein the product quality judgment result comprises good products and defective products. Compared with the existing mode of manually determining the process parameters, the invention can collect and analyze the process parameters, can more effectively control the plastic injection molding process, further reduces the rejection rate of products and improves the stability of the product quality.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of an example 1 of a method for analyzing plastic injection molding process parameters according to the present disclosure;

FIG. 2 is a schematic diagram of an example of analysis of data using a Mahalanobis distance algorithm according to the present disclosure;

FIG. 3 is a schematic diagram of the fluctuation range of a process parameter according to the present disclosure;

FIG. 4 is a flow chart of an example 2 of a method for analyzing plastic injection molding process parameters according to the present disclosure;

FIG. 5 is a schematic diagram of an embodiment 1 of a system for analyzing parameters of a plastic injection molding process according to the present invention;

fig. 6 is a schematic structural diagram of an embodiment 2 of an analysis system for plastic injection molding process parameters according to the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

As shown in fig. 1, a flowchart of an embodiment 1 of a plastic injection molding process control method disclosed in the present invention may include the following steps:

s101, at least collecting data of a machine, a die and related auxiliary machines;

when more efficient control of the plastic injection molding process is desired, at least data of the machine, the mold and related auxiliary machines are first collected, that is, the collected data includes, but is not limited to, data of the machine, the mold and related auxiliary machines. For example, in data collection, sensing data of the machine, mold and associated auxiliaries is collected. Wherein, in order to make the control of the plastic injection molding process more effective, the data acquisition can be at least more than 50 times.

For example, pressure data of the machine can be collected through a pressure sensor, speed data of the machine can be collected through a speed sensor, and temperature data of the machine can be collected through a first temperature sensor; pressure data of the mold is collected through a pressure sensor, speed data of the mold is collected through a speed sensor, and temperature data of the mold is collected through a temperature sensor.

S102, analyzing the data by adopting a Markov distance algorithm to generate a group of standard process curves;

after at least the data of the machine, the mould and the related auxiliary machines are collected, a mahalanobis distance algorithm is further adopted to rotate the variables according to the main components, the dimensions are mutually independent and standardized, the dimensions are uniformly distributed, the analysis of the main components shows that the main components are the directions of the feature vectors, the variance of each direction is the corresponding feature value, the rotation is only needed according to the directions of the feature vectors, then the feature value is scaled by times, for example, as shown in fig. 2, the point B in the diagram is more likely to be a point in the sample, the point A is more likely to be an outlier, the inherent relation between the data is analyzed by the method, and a set of standard process curves is generated.

S103, respectively carrying out segmentation processing on each standard process curve to obtain segmentation results;

because the influence weights of parameters on the product quality are different in different stages of plastic injection molding, the standard process curve can be subjected to sectional treatment after the standard process curve is generated, and a sectional result is obtained.

Specifically, the standard process curve can be divided into a filling stage, a feeding stage, a pressure maintaining stage and a cooling stage according to the plastic injection molding process.

S104, respectively analyzing the fluctuation range of each parameter point on each section of curve of each standard process curve based on the segmentation result;

after the standard process curves are subjected to sectional treatment, each parameter point on each section of the curves is further analyzed, and the fluctuation range of each parameter point is obtained. For example, as shown in fig. 3, the solid line is a standard process curve, and the upper and lower dotted lines are ranges in which each parameter point allows fluctuation, so it can be seen that the ranges in which each parameter point allows fluctuation are different.

Wherein the parameter points include, but are not limited to: the mold cavity pressure, the mold cavity temperature, the machine system pressure, the screw rod position, the screw rod advancing speed, the mold cooling medium flow speed and inlet and outlet temperature, the material drying temperature, the barrel section temperature, the environment temperature and the like.

S105, judging the quality of the plastic injection molded product based on the fluctuation range of each parameter point on each section of curve of each standard process curve to obtain a product quality judgment result, wherein the product quality judgment result comprises good products and defective products.

After the fluctuation range of each parameter point on each section of curve of each standard process curve is analyzed, in the plastic injection molding process, the quality of a plastic injection molded product is further judged according to the fluctuation range of each parameter point on each section of curve of each standard process curve, and a judgment result of the quality of the plastic injection molded product is obtained. For example, judging whether the plastic injection molded product is good or bad according to the fluctuation range of each parameter point on each section of curve of each standard process curve.

In summary, in the above embodiment, when the plastic injection molding process needs to be controlled, at least data of a machine, a mold and related auxiliary machines are collected first, and then the data are analyzed by a mahalanobis distance algorithm to generate a set of standard process curves, and each standard process curve is processed in a segmentation way to obtain a segmentation result; then, based on the segmentation result, respectively analyzing the fluctuation range of each parameter point on each section of curve of each standard process curve; and judging the quality of the plastic injection molded product based on the fluctuation range of each parameter point on each section of curve of each standard process curve to obtain a product quality judgment result, wherein the product quality judgment result comprises good products and defective products. Compared with the existing mode of manually determining the process parameters, the method can collect and analyze the process parameters, can more effectively control the plastic injection molding process, further reduces the rejection rate of products and improves the stability of the product quality.

As shown in fig. 4, a flowchart of an embodiment 2 of a plastic injection molding process control method according to the present disclosure may include the following steps:

s401, at least collecting data of a machine, a die and related auxiliary machines;

S402, analyzing the data by adopting a Markov distance algorithm to generate a group of standard process curves;

S403, respectively carrying out segmentation processing on each standard process curve to obtain segmentation results;

S404, respectively analyzing the fluctuation range of each parameter point on each section of curve of each standard process curve based on the segmentation result;

S405, judging the quality of a plastic injection molded product based on the fluctuation range of each parameter point on each section of curve of each standard process curve to obtain a product quality judgment result, wherein the product quality judgment result comprises good products and defective products;

S406, obtaining a feedback result of a judgment result of quality personnel on the product quality;

after the result of judging the quality of the plastic injection molded product according to the fluctuation range of each parameter point on each section of curve of each standard process curve is obtained, positive feedback or negative feedback can be further carried out on the judgment result of the quality of the product by a quality person, so that the feedback result of the judgment result of the quality of the product by the quality person is obtained.

S407, adjusting a threshold value for judging the quality of the product based on the judgment result and the feedback result of the quality of the product;

after the feedback result of the quality personnel on the judgment result of the product quality is obtained, the threshold value for judging the quality of the product can be further adjusted according to the judgment result of the product quality and the feedback result, so that the accuracy of judging the product quality can be improved through the adjusted threshold value.

For example, the standard deviation of 1000 positive samples can be calculated according to a variance calculation formula of normal distribution, then the median deviation position of the test samples in normal distribution is calculated, if the program initially sets the threshold value to be within 5 standard deviations and is qualified, the test samples are within 4.5 standard deviations, the quality personnel judges that the product is unqualified, after feeding back to the program, the program automatically adjusts the threshold value to be 5- (5-4.5) 1.2=4.4 standard deviations, the same quality personnel judges that the product in 5.5 standard deviations is qualified, and the program automatically adjusts the threshold value to be 5+ (5.5-5) 0.8=5.4 standard deviations, so that the program judging result meets the product quality requirement more. It should be noted that the above method is only one of many means for adjusting the threshold value, and the method for adjusting the threshold value includes, but is not limited to, this.

S408, clustering the process curves corresponding to the defective products in the judging result of the product quality to obtain the categories of the process curves corresponding to the defective products;

after the result of judging the quality of the plastic injection molded product according to the fluctuation range of each parameter point on each section of curve of each standard process curve is obtained, the process curves corresponding to the defective products can be further clustered, and the categories of the process curves corresponding to the defective products are obtained.

S409, acquiring identification content for identifying the category of the process curve corresponding to the defective product by a process staff, wherein the identification content comprises: poor content and cause of the poor;

after the category of the process curve corresponding to the defective product is obtained, the category of the process curve corresponding to the defective product can be further identified by a process staff, and defective content and defective reasons are identified.

S410, judging the quality of a newly produced plastic injection molded product based on the adjusted threshold value for judging the quality of the product, and obtaining a judging result of the quality of the newly produced product, wherein the judging result of the quality of the newly produced product comprises good products and defective products;

after the adjusted threshold value for judging the quality of the product is obtained, the quality of the new product can be judged according to the adjusted threshold value for judging the quality of the product when the new product of plastic injection molding is produced, and the judging result of the quality of the newly produced product is obtained, wherein the judging result of the quality of the newly produced product comprises good products and defective products.

S411, matching the process curve corresponding to the newly produced defective product with the category of the process curve corresponding to the defective product, and outputting the defective content and the defective reason of the newly produced defective product.

And in the judging result of the quality of the newly produced product, further matching the process curve corresponding to the newly produced defective product with the category of the process curve corresponding to the defective product, and outputting the defective content and the defective reason of the newly produced defective product according to the matching result. In the plastic injection molding process, the process staff can intuitively obtain the bad content and bad reasons of the bad products.

As shown in fig. 5, a schematic structural diagram of an embodiment 1 of a plastic injection molding process control system according to the present disclosure may include:

the data acquisition module 501 is used for at least acquiring data of the machine, the die and related auxiliary machines;

The first analysis module 502 is configured to analyze the data by using a mahalanobis distance algorithm, and generate a set of standard process curves;

A segmentation module 503, configured to perform segmentation processing on each standard process curve to obtain a segmentation result;

The second analysis module 504 is configured to analyze a fluctuation range of each parameter point on each segment of the standard process curve based on the segmentation result;

The first judging module 505 is configured to judge the quality of the plastic injection molded product based on the fluctuation range of each parameter point on each section of the curve of each standard process curve, so as to obtain a judging result of the quality of the product, where the judging result of the quality of the product includes good products and defective products.

As shown in fig. 6, a schematic structural diagram of an embodiment 2 of a plastic injection molding process control system according to the present disclosure may include:

the data acquisition module 601 is configured to at least acquire data of a machine, a mold and related auxiliary machines;

The first analysis module 602 is configured to analyze the data by using a mahalanobis distance algorithm to generate a set of standard process curves;

The segmentation module 603 is configured to perform segmentation processing on each standard process curve to obtain a segmentation result;

The second analysis module 604 is configured to analyze a fluctuation range of each parameter point on each segment of the standard process curve based on the segmentation result;

The first judging module 605 is configured to judge quality of a plastic injection molded product based on a fluctuation range of each parameter point on each section of curve of each standard process curve, so as to obtain a judging result of the quality of the product, where the judging result of the quality of the product includes good products and defective products;

A first obtaining module 606, configured to obtain a feedback result of the product quality judgment result by the quality personnel;

An adjusting module 607, configured to adjust a threshold value for determining the quality of the product based on the determination result and the feedback result of the quality of the product;

The clustering module 608 is configured to cluster the process curves corresponding to the defective products in the product quality judgment result, so as to obtain the types of the process curves corresponding to the defective products;

The second obtaining module 609 is configured to obtain identification content for identifying a category of a process curve corresponding to the defective product by a process personnel, where the identification content includes: poor content and cause of the poor;

A second judging module 610, configured to judge the quality of the newly produced plastic injection molded product based on the adjusted threshold value for judging the quality of the product, so as to obtain a judging result of the quality of the newly produced product, where the judging result of the quality of the newly produced product includes good products and defective products;

The matching module 611 is configured to match the process curve corresponding to the newly produced defective product with the category of the process curve corresponding to the defective product, and output the defective content and the defective reason of the newly produced defective product.

In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling a plastic injection molding process, comprising:

at least collecting data of a machine, a die and related auxiliary machines;

judging the quality of a plastic injection molded product based on the fluctuation range of each parameter point on each section of curve of each standard process curve to obtain a product quality judgment result, wherein the product quality judgment result comprises good products and defective products;

the method further comprises the steps of:

2. The method as recited in claim 1, further comprising:

3. The method as recited in claim 2, further comprising:

4. The method according to claim 1, wherein the step of separately performing the segmentation process on each standard process curve to obtain segmented results includes:

5. A plastic injection molding process control system, comprising:

the first judging module is used for judging the quality of the plastic injection molded product based on the fluctuation range of each parameter point on each section of curve of each standard process curve to obtain a judging result of the product quality, wherein the judging result of the product quality comprises good products and defective products;

the system further comprises:

6. The system of claim 5, further comprising:

7. The system of claim 6, further comprising:

8. The system of claim 5, wherein the segmentation module is specifically configured to: