CN118068781A - Control method for production stability and consistency of laminated adhesive film - Google Patents
Control method for production stability and consistency of laminated adhesive film Download PDFInfo
- Publication number
- CN118068781A CN118068781A CN202311479475.9A CN202311479475A CN118068781A CN 118068781 A CN118068781 A CN 118068781A CN 202311479475 A CN202311479475 A CN 202311479475A CN 118068781 A CN118068781 A CN 118068781A
- Authority
- CN
- China
- Prior art keywords
- device group
- adhesive film
- operation data
- laminated adhesive
- consistency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 123
- 239000002313 adhesive film Substances 0.000 title claims abstract description 108
- 230000006399 behavior Effects 0.000 claims abstract description 86
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000011217 control strategy Methods 0.000 claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 13
- 239000011248 coating agent Substances 0.000 claims description 54
- 238000000576 coating method Methods 0.000 claims description 54
- 239000012535 impurity Substances 0.000 claims description 52
- 238000000034 method Methods 0.000 claims description 46
- 230000008569 process Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 9
- 230000001276 controlling effect Effects 0.000 abstract description 6
- 230000001105 regulatory effect Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 10
- 230000008439 repair process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000012939 laminating adhesive Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention relates to the technical field of production of a laminated adhesive film, in particular to a control method for production stability and consistency of the laminated adhesive film, which comprises the following steps: based on the characteristics affecting the production stability and consistency of the laminated adhesive film, establishing corresponding system control models under different production flows through a machine learning algorithm; acquiring real-time operation data of the laminated adhesive film production system in a preset time period, and performing first classification processing on the real-time operation data; then selecting a corresponding system control model, obtaining a corresponding control strategy through the model and executing the control strategy. And establishing a system control model based on a machine learning algorithm by utilizing the historical operation data, automatically matching the system control model with the real-time operation data after the first classification treatment, feeding back the out-of-control behavior of the laminated adhesive film production system, and simultaneously automatically regulating and controlling the laminated adhesive film production system and repairing the out-of-control behavior by using the system control model to ensure the stability and consistency of the laminated adhesive film production.
Description
Technical Field
The invention relates to the technical field of production of a laminated adhesive film, in particular to a control method for production stability and consistency of the laminated adhesive film.
Background
At present, a data system for counting error behaviors of production equipment devices of a build-up adhesive film for a Flip Chip Ball Grid Array (FCBGA) package loading board cannot rapidly judge whether equipment devices are prone to be found according to error data, the error behaviors of each equipment device are relatively independent and are handled by different personnel, the common problem of the equipment devices cannot be timely and accurately found, and some error behaviors of a process which can be controlled by a computer cannot be automatically repaired, so that instability factors exist in the build-up adhesive film production line for the FCBGA package loading board, consistency of the quality of the build-up adhesive film cannot be guaranteed, and overall production quality is affected.
Accordingly, the prior art is still in need of improvement and development.
Disclosure of Invention
In view of the shortcomings of the prior art, the invention aims to provide a control method for the production stability and consistency of a laminating adhesive film, and aims to solve the problems that an existing laminating adhesive film production line cannot timely feed back out a runaway behavior and automatically repair the runaway behavior.
The technical scheme of the invention is as follows:
a control method for production stability and consistency of a laminated adhesive film comprises the following steps:
collecting historical operation data of a laminated adhesive film production system;
Determining characteristics affecting the production stability and consistency of the laminated adhesive film according to the historical operation data;
based on the characteristics affecting the production stability and consistency of the laminated adhesive film, establishing corresponding system control models under different production flows through a machine learning algorithm;
acquiring real-time operation data of the laminated adhesive film production system in a preset time period, and performing first classification processing on the real-time operation data;
And selecting a corresponding system control model according to the real-time operation data after the first classification processing, and obtaining and executing a corresponding control strategy through the system control model.
The method for controlling the production stability and consistency of the laminated adhesive film comprises the steps of coating a device group, an online thickness measuring device group and an online impurity detecting device group, wherein different production processes adopt different types of coating device groups, online thickness measuring device groups and online impurity detecting device groups, and the coating device groups, the online thickness measuring device groups and the online impurity detecting device groups are respectively provided with different devices, and each device is provided with different device cavities.
The control method for the production stability and consistency of the laminated adhesive film comprises the steps of coating device group out-of-control data, coating data, on-line thickness measuring device group out-of-control data, thickness measuring data, on-line impurity detecting device group out-of-control data and impurity detecting data.
The control method for the production stability and consistency of the laminated adhesive film comprises the steps of:
Acquiring the number of first out-of-control behaviors of the coating device group, the online thickness measuring device group and the online impurity detecting device group, wherein the number of the first out-of-control behaviors is acquired based on the real-time operation data of the coating device group, the online thickness measuring device group and the online impurity detecting device group;
and acquiring an error device group from the coating device group, the online thickness measuring device group and the online impurity detecting device group based on the number of the first out-of-control behaviors.
The control method for the production stability and consistency of the laminated adhesive film further comprises the following steps after the first classification treatment is carried out on the real-time operation data:
Performing second classification processing on the real-time operation data of the error device group, and acquiring the number of second uncontrolled behaviors of each device chamber of the error device group, wherein the number of second uncontrolled behaviors is acquired based on the real-time operation data of the error device group;
based on the number of second runaway actions, an error device chamber is obtained from the error device group.
The control method for the production stability and consistency of the laminated adhesive film comprises the steps of obtaining the number of first out-of-control behaviors of the coating device group, the online thickness measuring device group and the online impurity detecting device group, wherein the method comprises the following steps:
And directly acquiring the sum of the runaway behaviors of all devices corresponding to the coating device group, the online thickness measuring device group and the online impurity detecting device group as the number of the first runaway behaviors.
The control method for the production stability and consistency of the laminated adhesive film comprises the steps of:
Providing a first threshold;
Comparing the number of first runaway behaviors corresponding to the coating device group, the online thickness measuring device group and the online impurity detecting device group with the first threshold value;
And taking the device group with the number of the first out-of-control actions being greater than or equal to the first threshold value as the error device group.
The control method for the production stability and consistency of the laminated adhesive film comprises the following steps:
storing real-time operation data of the error device group and real-time operation data of the error device chamber;
if the real-time operation data of the error device group are acquired, first alarm information is sent out;
And if the real-time operation data of the error device cavity is acquired, sending out second alarm information.
The control strategy comprises adjusting production parameters of a laminated adhesive film production system or disabling the error device group.
The control method for the production stability and consistency of the laminated adhesive film, wherein the characteristics affecting the production stability and consistency of the laminated adhesive film are determined according to the historical operation data, comprises the following steps:
after normalizing the historical operation data, performing multi-round training by using a base model;
after each round of training, eliminating the characteristics of a plurality of weight coefficients, and then carrying out the next round of training based on a new characteristic set;
And combining the individual characteristics to obtain the characteristics which determine the influence on the production stability and consistency of the laminated adhesive film.
The beneficial effects are that: the invention provides a control method for production stability and consistency of a laminated adhesive film, which comprises the following steps: collecting historical operation data of a laminated adhesive film production system; determining characteristics affecting the production stability and consistency of the laminated adhesive film according to the historical operation data; based on the characteristics affecting the production stability and consistency of the laminated adhesive film, establishing corresponding system control models under different production flows through a machine learning algorithm; acquiring real-time operation data of the laminated adhesive film production system in a preset time period, and performing first classification processing on the real-time operation data; and selecting a corresponding system control model according to the real-time operation data after the first classification processing, and obtaining and executing a corresponding control strategy through the system control model. According to the invention, the actual running condition of the laminated adhesive film production system is fully considered, a system control model is established based on a machine learning algorithm by utilizing historical running data under the condition of not changing the existing process and device production condition, the system control model is automatically matched with the real-time running data after the first classification treatment, the out-of-control behavior of the laminated adhesive film production system is fed back, meanwhile, the out-of-control behavior is automatically regulated and controlled and repaired by the system control model, and the stability and consistency of the laminated adhesive film production are ensured.
Drawings
FIG. 1 is a flow chart of a method for controlling the production stability and consistency of a laminated adhesive film according to the present invention.
Detailed Description
The invention provides a control method for the production stability and consistency of a laminated adhesive film, which is used for making the purposes, the technical scheme and the effects of the invention clearer and more definite, and is further described in detail below. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As shown in FIG. 1, the invention provides a control method for the production stability and consistency of a laminated adhesive film, which comprises the following steps:
step S10: collecting historical operation data of a laminated adhesive film production system;
Step S20: determining characteristics affecting the production stability and consistency of the laminated adhesive film according to the historical operation data;
Step S30: based on the characteristics affecting the production stability and consistency of the laminated adhesive film, establishing corresponding system control models under different production flows through a machine learning algorithm;
step S40: acquiring real-time operation data of the laminated adhesive film production system in a preset time period, and performing first classification processing on the real-time operation data;
Step S50: and selecting a corresponding system control model according to the real-time operation data after the first classification processing, and obtaining and executing a corresponding control strategy through the system control model.
In this embodiment, the actual operation condition of the laminated adhesive film production system is fully considered, the historical operation data is utilized to build a system control model based on a machine learning algorithm under the condition that the existing process and the existing device production condition are not changed, the system control model is automatically matched with the real-time operation data after the first classification treatment, the out-of-control behavior of the laminated adhesive film production system is monitored in real time, the out-of-control behavior of the laminated adhesive film production system is fed back to a user, meanwhile, the out-of-control behavior is automatically regulated and controlled and repaired through the system control model, the situation expansion is prevented by adopting rapid measures, and the stability and consistency of the laminated adhesive film production are ensured.
Specifically, the invention achieves the purposes of timely feeding back the out-of-control behavior of the build-up adhesive film production system and processing the out-of-control behavior by establishing the system control model, thereby establishing the whole-flow fine control standard of the build-up adhesive film production system and realizing the high stability and consistency of the build-up adhesive film for the flip chip ball grid array FCBGA package carrier plate.
In some embodiments, the laminated adhesive film production system comprises a coating device group, an online thickness measuring device group and an online impurity detection device group, different production processes adopt different types of coating device groups, online thickness measuring device groups and online impurity detection device groups, and the coating device groups, the online thickness measuring device groups and the online impurity detection device groups respectively have different devices, and each device has different device chambers. The production system with the layout is convenient for acquiring the operation data of each device group and each device cavity, and is beneficial to the establishment of a system control model and the feedback and repair of the out-of-control behavior of the system.
In some embodiments, the historical operating data includes coating device set run-away data, coating data, on-line thickness measurement device set run-away data, thickness measurement data, on-line impurity detection device set run-away data, impurity detection data. The out-of-control data of the coating device group and the coating data can reflect that the coating device has error behaviors in the production flow; the out-of-control data of the online thickness measuring device group and the thickness measuring data can reflect that the online thickness measuring device group has error behaviors in the production flow; the out-of-control data of the online impurity detection device group and the impurity detection data can reflect that the online impurity detection device group has error behaviors in the production flow.
In some embodiments, in the step S40, performing a first classification process on the real-time operation data includes:
Step S41: acquiring the number of first out-of-control behaviors of the coating device group, the online thickness measuring device group and the online impurity detecting device group, wherein the number of the first out-of-control behaviors is acquired based on the real-time operation data of the coating device group, the online thickness measuring device group and the online impurity detecting device group;
step S42: and acquiring an error device group from the coating device group, the online thickness measuring device group and the online impurity detecting device group based on the number of the first out-of-control behaviors.
The number of the first out-of-control actions of the coating device group, the online thickness measuring device group and the online impurity detecting device group is obtained, the first classification processing is carried out on the coating device group, the online thickness measuring device group and the online impurity detecting device group by using the number of the first out-of-control actions, an error device group is obtained, a corresponding system control model can be selected according to the error device group, the control strategy and execution can be obtained more accurately, and the stability and consistency of the production of the laminated adhesive film are ensured.
In some embodiments, obtaining the number of first runaway behaviors of the coating device set, the online thickness measuring device set, the online impurity detection device set, comprises: and directly acquiring the sum of the runaway behaviors of all devices corresponding to the coating device group, the online thickness measuring device group and the online impurity detecting device group as the number of the first runaway behaviors. The number of the first out-of-control actions is obtained, the error device group is obtained based on the number of the first out-of-control actions, a system control model corresponding to the error device group is selected, then a corresponding control strategy is selected for the error device group by using the system control model and is executed, the purpose of automatically repairing the error device group by the system control model is achieved, and the stability and consistency of the production of the laminated adhesive film are achieved.
In a preferred embodiment, a method of obtaining a number of first runaway behaviors of the coating device set, the on-line thickness measuring device set, the on-line impurity detection device set, includes: respectively acquiring the number of sub-runaway behaviors of the coating device group, the online thickness measuring device group and the online impurity detecting device group, wherein the number of the sub-runaway behaviors is acquired based on the operation data of each device chamber; and obtaining the number of the first runaway behaviors based on the sum of the numbers of all the sub-runaway behaviors corresponding to the coating device group, the online thickness measuring device group and the online impurity detecting device group.
In some embodiments, the first classification process is to aggregate data of uncontrolled behavior in operational data of the same type of device group. In another embodiment, the first classification process is to collect the data of the out-of-control behavior and the data of the normal operation in the operation data corresponding to the device group of the same type, and the operation condition of the device group is conveniently known by comparing the sizes of the data of the out-of-control behavior and the data of the normal operation. The first runaway behavior means that the performance of the build-up adhesive film produced by each type of device group in a preset time does not reach the standard value, specifically, the performance of the build-up adhesive film produced by one device chamber of one device of one type of device group does not reach the standard value, namely, the device group of the type is considered to correspond to the first runaway behavior.
In some embodiments, after performing the first classification processing on the real-time operation data, the method further includes the steps of:
Step SS41: performing second classification processing on the real-time operation data of the error device group, and acquiring the number of second uncontrolled behaviors of each device chamber of the error device group, wherein the number of second uncontrolled behaviors is acquired based on the real-time operation data of the error device group;
Step SS42: based on the number of second runaway actions, an error device chamber is obtained from the error device group.
Because each device group comprises a plurality of devices and each device is provided with different device chambers, the number of second uncontrolled behaviors of each device chamber of the error device group is obtained by carrying out second classification processing on the real-time operation data of the error device group, and finally the error device chambers are obtained from the error device group based on the number of the second uncontrolled behaviors, the error device chambers in the layer-increasing adhesive film system can be reflected more accurately, and the system control model can accurately feed back and process the uncontrolled behaviors more timely, so that a full-flow fine control standard is established, and the high stability and consistency of the production of the layer-increasing adhesive film for the flip chip ball grid array FCBGA package loading board are realized.
In some embodiments, in the step S42, an error device group is obtained from the coating device group, the online thickness measuring device group, and the online impurity detecting device group, and the method includes the steps of:
step S421: providing a first threshold;
Step S422: comparing the number of first runaway behaviors corresponding to the coating device group, the online thickness measuring device group and the online impurity detecting device group with the first threshold value;
step S423: and taking the device group with the number of the first out-of-control actions being greater than or equal to the first threshold value as the error device group.
In this embodiment, by setting the first threshold, the error device group can be accurately fed back to the user by using the comparison between the first threshold and the number of the first runaway behaviors, so as to achieve the purpose of fast and efficient error reporting.
In some embodiments, in step SS42, obtaining an error device chamber from the error device group includes the steps of:
step SS421: providing a second threshold value, the second threshold value being smaller than the first threshold value;
step SS422: comparing the number of second runaway behaviors to the second threshold;
Step SS423: and taking the device chamber with the number of the second out-of-control actions being greater than or equal to the second threshold as the error device chamber.
In some embodiments, the method for controlling the production stability and consistency of the laminated adhesive film further comprises:
storing real-time operation data of the error device group and real-time operation data of the error device chamber;
if the real-time operation data of the error device group are acquired, first alarm information is sent out;
And if the real-time operation data of the error device cavity is acquired, sending out second alarm information.
In some embodiments, the control strategy includes adjusting production parameters of the laminated adhesive film production system or disabling the set of error devices.
In some embodiments, in the step S20, determining, according to the historical operation data, features that affect the production stability and consistency of the laminated adhesive film, includes the steps of:
Step S21: after normalizing the historical operation data, performing multi-round training by using a base model;
Step S22: after each round of training, eliminating the characteristics of a plurality of weight coefficients, and then carrying out the next round of training based on a new characteristic set;
step S23: and combining the individual characteristics to obtain the characteristics which determine the influence on the production stability and consistency of the laminated adhesive film.
In this embodiment, the individual features are combined to obtain a combined feature, i.e., a synthesized feature; the combination of the features is helpful for expressing nonlinear relation, constructing more and better features and improving model precision.
In some embodiments, the method for controlling the production stability and consistency of the laminated adhesive film further comprises the steps of: and the system control model is combined with the real-time operation data to optimize model parameters, so that a better system control model is obtained.
In some embodiments, the preset time is 24-48 hours; preferably, the preset time is 48 hours.
In some embodiments, the control method of the production stability and consistency of the build-up adhesive film is used in the production of the build-up adhesive film for the FCBGA packaging loading board.
Specifically, the embodiment processes real-time operation data obtained in a preset time period through first classification processing, namely, gathers performance data of the coating device group, the online thickness measuring device group and the online impurity detecting device group, so as to obtain the number of first out-of-control behaviors of each type of device group, and finds an error device group from the coating device group, the online thickness measuring device group and the online impurity detecting device group according to the number of the first out-of-control behaviors. And then processing the obtained real-time operation data of the error device group by a second classification processing method, namely summarizing the performance data of the error device group, so as to obtain the number of second uncontrolled behaviors of each device chamber in the error device group, selecting a corresponding system control model based on the number of first uncontrolled behaviors and/or the number of second uncontrolled behaviors, selecting a corresponding control strategy by using the system control model, executing the control strategy, realizing timely feedback and rapid automatic repair of the laminated adhesive film production system, and ensuring the stability and consistency of laminated adhesive film production. By the method, all error device groups and all error device cavities can be found out in a centralized manner, on one hand, whether the problem of equipment tendency exists or not is easily judged, so that adverse effects of the error device groups and the error device cavities on the production yield of the build-up adhesive film for the FCBGA package carrier board are prevented; on the other hand, aiming at the error device and the error device cavity, the system control model can be used for centralized analysis and maintenance, so that the problems can be found in time, corresponding solutions are adopted, and the high stability and consistency of the production of the build-up adhesive film for the FCBGA package carrier plate are ensured.
The following examples are further given to illustrate the invention in detail. It is also to be understood that the following examples are given solely for the purpose of illustration and are not to be construed as limitations upon the scope of the invention, since numerous insubstantial modifications and variations will now occur to those skilled in the art in light of the foregoing disclosure.
Example 1
The embodiment provides a control method for production stability and consistency of a laminated adhesive film, which comprises the following steps:
Step 1: collecting historical operation data of a laminated adhesive film production system (a coating device group, an online thickness measuring device group and an online impurity detecting device group);
The operation data includes: performance data corresponding to runaway behavior and performance data corresponding to normal operation.
The method for acquiring the operation data comprises the following steps: after the corresponding process of the laminated adhesive film is finished in a certain device group or a device cavity, the control system acquires parameters of the laminated adhesive film, wherein the parameters can be adhesive film thickness parameters or adhesive film apparent parameters and the like; comparing the parameter of the laminated adhesive film with a standard value, if the parameter of the laminated adhesive film reaches the standard value, considering the operation data corresponding to the device group or the device cavity as normal operation, otherwise, considering the operation data corresponding to the device group or the device cavity as out-of-control operation;
Step 2: determining characteristics affecting the production stability and consistency of the laminated adhesive film according to the historical operation data;
step 3: based on the characteristics affecting the production stability and consistency of the laminated adhesive film, establishing corresponding system control models under different production flows through a machine learning algorithm;
Step 4: acquiring the number of first uncontrolled behaviors of a coating device group, an online thickness measuring device group and an online impurity detecting device group in a preset time period, wherein the number of the first uncontrolled behaviors is obtained based on the real-time operation data of the coating device group, the online thickness measuring device group and the online impurity detecting device group, and the number of the first uncontrolled behaviors is subjected to first classification processing based on the number of the first uncontrolled behaviors;
It should be noted that the preset time is within a time period set before the data acquisition, and in the time period, the operation data of the build-up adhesive film is acquired; the preset time is set according to the frequency of abnormal behaviors of the device group, the device and the device cavity in the past; the preset time in this example was 48 hours.
Among all the acquired operation data, the operation data corresponding to the coating device group, the online thickness measuring device group and the online impurity detecting device group are mutually independent, and the first classification treatment is to collect the operation data of the device group of the same type, so that the overall analysis of all the data of the device group of the same type with out-of-control behavior is facilitated, and whether the device group of the same type has a prone error or not is judged by a system control model.
Step 5: acquiring an error device group from the coating device group, the online thickness measuring device group and the online impurity detecting device group based on the number of the first out-of-control behaviors;
the method for acquiring the error device group from the coating device group, the online thickness measuring device group and the online impurity detecting device group comprises the following steps: providing a first threshold; comparing whether the number of first runaway behaviors of each device group is greater than or equal to the first threshold; if yes, taking the device group with the number of the first out-of-control behaviors being greater than or equal to the first threshold value as an error device group.
It should be further noted that the first threshold value is set according to the occurrence frequency of the runaway behavior of the previous device group, for example, in the previous statistics, the number of the occurrence of the runaway behavior of the coating device group is at most 4 within 24 hours, and the first threshold value of the coating device group is set to be 5.
It should be noted that after the error device group is obtained, a corresponding system control model can be selected by the error device group, the system control model is utilized to correct the operation parameters of the error device group according to the machine learning algorithm, if the operation parameters exceed the correction range of the system control model, the error device group can be deactivated, so that the problem of scrapping of the build-up adhesive film caused by continuous production using the error device group can be avoided.
If the error machine set is obtained, first alarm information is sent to related personnel, and the related personnel are timely reminded of knowing the running condition of the device set in the production of the laminated adhesive film, so that the related personnel can check and repair the error device set, and the production loss is reduced. The method comprises the steps of acquiring the error device group and storing related information of the error device group, such as error time, error quantity, device group model number, error type and the like. This facilitates the storage of information as a history for convenient subsequent viewing.
Step 6: performing second classification processing on the operation data of the error device group, and acquiring the number of second uncontrolled behaviors of each device cavity, wherein the number of second uncontrolled behaviors is acquired based on the operation data of the error device group;
The performance data of each device chamber is independent from the acquired operation data of the error device, and the second classification processing method is to aggregate the operation data corresponding to each device chamber. This facilitates an overall analysis of all data from uncontrolled behavior for each device chamber to determine if the device chamber has a predisposition error.
Step 7: and acquiring an error device chamber based on the acquired number of the second out-of-control behaviors of the coating device group, the online thickness measuring device group and the online impurity detecting device group, and correcting parameters of the error chamber by utilizing the system control model, wherein the error chamber can be deactivated if the parameters exceed the correction range of the system control model.
A method of locating a faulty device chamber from among different device chambers, comprising: providing a second threshold value, the second threshold value being smaller than the first threshold value; comparing whether the number of second runaway behaviors of each device chamber is greater than or equal to a second threshold; if so, taking the device chamber with the number of the second out-of-control actions being greater than or equal to the second threshold as the wrong device chamber.
It should be noted that, one device group includes a plurality of device chambers, the first threshold is a judgment value of the device group, and the second threshold is a judgment value of the device chambers, so the second threshold is smaller than the first threshold.
If the device chamber with errors is obtained, a second alarm message is sent to related personnel, and the related personnel are timely reminded of knowing the operation condition of the device chamber in the production of the laminated adhesive film, so that the related personnel can check and repair the device chamber with errors, and the production loss is reduced. Information of the faulty device is stored together with information of the faulty device chamber, such as the faulty time, the faulty number, the device chamber model number, the faulty type, etc. This facilitates the storage of information as a history for convenient subsequent viewing.
According to the embodiment, the number of the out-of-control behaviors corresponding to the specific device groups or the device chambers is summarized, so that the relative independence of the out-of-control behaviors is avoided, and the device tendency can be judged rapidly. Related personnel can know the running condition of the equipment device in time through alarm information, thereby avoiding hysteresis caused by information transmission barriers and reducing the probability of error in the production of the laminated adhesive film. According to the result of the out-of-control behavior of the summarized equipment, the corresponding system control model established by a machine learning algorithm is used for correcting or a single related person is used for detecting and maintaining the equipment, so that the automatic repair priority is realized, the stability and consistency of the production of the laminated adhesive film are ensured, the common problem is favorably found, and the fundamental solution is found.
In summary, the method for controlling the production stability and consistency of the laminated adhesive film provided by the invention comprises the following steps: collecting historical operation data of a laminated adhesive film production system; determining characteristics affecting the production stability and consistency of the laminated adhesive film according to the historical operation data; based on the characteristics affecting the production stability and consistency of the laminated adhesive film, establishing corresponding system control models under different production flows through a machine learning algorithm; acquiring real-time operation data of the laminated adhesive film production system in a preset time period, and performing first classification processing on the real-time operation data; and selecting a corresponding system control model according to the real-time operation data after the first classification processing, and obtaining and executing a corresponding control strategy through the system control model. According to the invention, the actual running condition of the laminated adhesive film production system is fully considered, a system control model is established based on a machine learning algorithm by utilizing historical running data under the condition of not changing the existing process and device production condition, the system control model is automatically matched with the real-time running data after the first classification treatment, the out-of-control behavior of the laminated adhesive film production system is fed back, meanwhile, the out-of-control behavior is automatically regulated and controlled and repaired by the system control model, and the stability and consistency of the laminated adhesive film production are ensured.
It is to be understood that the invention is not limited in its application to the examples described above, but is capable of modification and variation in light of the above teachings by those skilled in the art, and that all such modifications and variations are intended to be included within the scope of the appended claims.
Claims (10)
1. A control method for the production stability and consistency of a laminated adhesive film is characterized by comprising the following steps:
collecting historical operation data of a laminated adhesive film production system;
Determining characteristics affecting the production stability and consistency of the laminated adhesive film according to the historical operation data;
based on the characteristics affecting the production stability and consistency of the laminated adhesive film, establishing corresponding system control models under different production flows through a machine learning algorithm;
acquiring real-time operation data of the laminated adhesive film production system in a preset time period, and performing first classification processing on the real-time operation data;
And selecting a corresponding system control model according to the real-time operation data after the first classification processing, and obtaining and executing a corresponding control strategy through the system control model.
2. The method for controlling the production stability and consistency of a laminated adhesive film according to claim 1, wherein the laminated adhesive film production system comprises a coating device group, an online thickness measuring device group and an online impurity detecting device group, different production processes adopt different types of coating device groups, online thickness measuring device groups and online impurity detecting device groups, and the coating device groups, the online thickness measuring device groups and the online impurity detecting device groups are respectively provided with different devices, and each device is provided with a different device chamber.
3. The method for controlling the production stability and consistency of a laminated adhesive film according to claim 2, wherein the historical operation data comprises coating device group control data, coating data, on-line thickness measuring device group control data, thickness measuring data, on-line impurity detecting device group control data, and impurity detecting data.
4. The method for controlling the production stability and consistency of a laminated adhesive film according to claim 2, wherein the performing a first classification process on the real-time operation data comprises:
Acquiring the number of first out-of-control behaviors of the coating device group, the online thickness measuring device group and the online impurity detecting device group, wherein the number of the first out-of-control behaviors is acquired based on the real-time operation data of the coating device group, the online thickness measuring device group and the online impurity detecting device group;
and acquiring an error device group from the coating device group, the online thickness measuring device group and the online impurity detecting device group based on the number of the first out-of-control behaviors.
5. The method for controlling the production stability and consistency of a laminated adhesive film according to claim 4, further comprising the steps of:
Performing second classification processing on the real-time operation data of the error device group, and acquiring the number of second uncontrolled behaviors of each device chamber of the error device group, wherein the number of second uncontrolled behaviors is acquired based on the real-time operation data of the error device group;
based on the number of second runaway actions, an error device chamber is obtained from the error device group.
6. The method for controlling the production stability and consistency of a laminated adhesive film according to claim 4, wherein obtaining the number of first runaway behaviors of the coating device group, the on-line thickness measuring device group and the on-line impurity detecting device group comprises:
And directly acquiring the sum of the runaway behaviors of all devices corresponding to the coating device group, the online thickness measuring device group and the online impurity detecting device group as the number of the first runaway behaviors.
7. The method for controlling the production stability and consistency of a laminated adhesive film according to claim 4, wherein the step of obtaining an error device group from the coating device group, the on-line thickness measuring device group and the on-line impurity detecting device group comprises the steps of:
Providing a first threshold;
Comparing the number of first runaway behaviors corresponding to the coating device group, the online thickness measuring device group and the online impurity detecting device group with the first threshold value;
And taking the device group with the number of the first out-of-control actions being greater than or equal to the first threshold value as the error device group.
8. The method for controlling the production stability and consistency of a laminated adhesive film according to claim 5, further comprising:
storing real-time operation data of the error device group and real-time operation data of the error device chamber;
if the real-time operation data of the error device group are acquired, first alarm information is sent out;
And if the real-time operation data of the error device cavity is acquired, sending out second alarm information.
9. The method of claim 4, wherein the control strategy comprises adjusting production parameters of a laminated film production system or disabling the error device group.
10. The method for controlling the production stability and consistency of a laminated film according to claim 1, wherein determining the characteristics affecting the production stability and consistency of a laminated film according to the historical operation data comprises the steps of:
after normalizing the historical operation data, performing multi-round training by using a base model;
after each round of training, eliminating the characteristics of a plurality of weight coefficients, and then carrying out the next round of training based on a new characteristic set;
And combining the individual characteristics to obtain the characteristics which determine the influence on the production stability and consistency of the laminated adhesive film.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311479475.9A CN118068781A (en) | 2023-11-07 | 2023-11-07 | Control method for production stability and consistency of laminated adhesive film |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311479475.9A CN118068781A (en) | 2023-11-07 | 2023-11-07 | Control method for production stability and consistency of laminated adhesive film |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118068781A true CN118068781A (en) | 2024-05-24 |
Family
ID=91106367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311479475.9A Pending CN118068781A (en) | 2023-11-07 | 2023-11-07 | Control method for production stability and consistency of laminated adhesive film |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118068781A (en) |
-
2023
- 2023-11-07 CN CN202311479475.9A patent/CN118068781A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108491305B (en) | Method and system for detecting server fault | |
| TWI312951B (en) | Methods and systems of offline measurement for process tool monitoring and computer-readable storage medium | |
| US8849438B2 (en) | Factory level process and final product performance control system | |
| CN101128786A (en) | Automated throughput control system and method of operating the same | |
| CN117391411B (en) | Product processing management system based on IOT (internet of things) | |
| CN115081257B (en) | Chip loss optimization method and system for electric power energy | |
| CN115808911A (en) | Industrial Internet of things regulation and control method and system for producing defective products in production line | |
| US8010212B2 (en) | Fuzzy control method for adjusting a semiconductor machine | |
| CN115169876A (en) | Closed-loop management method for magnetic component production line, computer equipment and storage medium | |
| CN118068781A (en) | Control method for production stability and consistency of laminated adhesive film | |
| CN113580763B (en) | Control method, system and equipment for output parameters of printing semi-finished products in printing workshop | |
| CN117433615B (en) | Gas meter correction method, system, electronic equipment and medium | |
| CN111719130B (en) | Temperature adjusting method in semiconductor coating equipment and semiconductor coating equipment | |
| CN117689254A (en) | Yield and processing suggestion generation system and generation method | |
| CN106557839B (en) | Equipment maintenance strategy optimization method and system based on big data | |
| CN114692899A (en) | Production plan optimization device, system, method and computer readable medium | |
| CN109001989B (en) | Machine control method based on intelligent learning algorithm | |
| CN111861181A (en) | Intelligent production system and production line formulation method for digital energy products | |
| CN114384885B (en) | Process parameter adjusting method, device, equipment and medium based on abnormal working conditions | |
| CN117764424A (en) | Method and device for detecting production line, processor and electronic equipment | |
| US7595467B2 (en) | Fault detection system and method for managing the same | |
| CN114172479A (en) | Whole-plate crystal fine-tuning method and system | |
| CN104901982B (en) | A kind of online data monitoring system and monitoring method | |
| CN118134106B (en) | Automatic production line productivity prediction method and device based on data driving | |
| CN102254788B (en) | Manufacturing execution system and manufacturing system having virtual measuring function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |