Intelligent coating production whole-process monitoring and optimizing system and method and medium

Abstract

The invention discloses an intelligent coating production whole process monitoring and optimizing system and method and a medium, and relates to the technical field of production monitoring, and the system comprises a process link monitoring module, a link anomaly analysis module and a link anomaly optimization module. According to the method, each flow link of coating production can be finely and deeply analyzed, coating production of each flow link can be efficiently monitored in multiple dimensions, abnormal flow links can be accurately marked, links needing to be optimized in coating production are determined, subsequent accurate optimization processing of the abnormal flow links is facilitated, and the coating production efficiency is improved. And a link abnormality optimization module is arranged to comprehensively ensure that the core process links are optimized preferentially, and the abnormal process links of the coating are optimized orderly and reasonably in sequence on the premise that the whole-process production of the coating is not influenced.

Description

Technical Field

[0001] The present invention relates to the field of production monitoring technology, and more specifically, to an intelligent coating production full-process monitoring and optimization system, method and medium. Background Art

[0002] In the coatings production industry, the traditional production monitoring method mainly relies on manual inspection and simple automated monitoring equipment. However, with the continuous expansion of coatings production scale and the increasing complexity of production processes, this traditional monitoring method has gradually exposed many problems.

[0003] First, traditional monitoring methods are obviously insufficient in covering the entire process of coating production. Since coating production involves multiple links, each of which has its own specific process requirements and quality control points, traditional monitoring methods can often only monitor some key links, making it difficult to achieve detailed and comprehensive monitoring of the entire process. This results in some potential problems and anomalies that may not be discovered in time, thus affecting the production efficiency and product quality of the coating.

[0004] Secondly, traditional monitoring methods have limitations in anomaly detection and processing. When anomalies occur during the coating production process, traditional monitoring methods can only provide simple alarm information, but cannot conduct in-depth analysis and accurate location of the cause of the anomaly. This results in the anomaly being handled in a less timely and accurate manner, which may cause more serious production problems and even lead to the shutdown of the production line.

[0005] In addition, traditional monitoring methods can often only rely on experience for simple adjustments and optimizations, that is, the link where the abnormality occurs is optimized. When there are multiple links that need to be optimized at the same time, it is often impossible to accurately identify the core links that need to be optimized first, resulting in insignificant optimization effects. Summary of the invention

[0006] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an intelligent coating production full-process monitoring and optimization system, method and medium.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] Intelligent coating production full process monitoring and optimization system, including process link monitoring module, link abnormality analysis module, link abnormality optimization module;

[0009] The process link monitoring module: during the coating production process, the link monitoring value of each process link in the coating production is updated every second;

[0010] The link abnormality analysis module: determines whether to mark a process link as an abnormal process link based on the comparison result of the link monitoring value of the process link and the link monitoring threshold;

[0011] The abnormal link optimization module obtains the abnormal process optimization value of the abnormal process link, sorts all the abnormal process links in order from large to small according to the numerical value of the abnormal process optimization value, and optimizes the abnormal process links in order according to the sorting order.

[0012] Furthermore, the link monitoring value of the process link is updated as follows: set g time points with equal time intervals within a time length of s, and at each time point, obtain the link performance judgment value of the process link, sort all link performance judgment values ​​in sequence according to the order of time points, calculate the difference between the two adjacent link performance judgment values ​​after sorting and take the absolute value to obtain the link performance fluctuation value, sum up all link performance fluctuation values ​​and take the average to obtain the link performance fluctuation mean Mdsk, sum up the two adjacent link performance judgment values ​​after sorting to obtain the link performance continuous value, sum up all link performance continuous values ​​and take the average to obtain the link performance continuous mean Ksdt, set the link performance judgment boundary value, and when the link performance judgment value is greater than or equal to the link performance judgment boundary value, mark the time point corresponding to the link performance judgment boundary value as the link performance abnormal point, mark the total number of link performance abnormal points as Pahd, and use the formula The link monitoring value Stgb of the process link is obtained, where ka is the performance fluctuation coefficient, kb is the performance continuity coefficient, and kc is the performance abnormality coefficient.

[0013] Furthermore, the link performance judgment value of the process link is obtained as follows: collect various link performance data of the coating produced in the process link, combine the various link performance data into a link performance data set, obtain the link performance judgment model corresponding to the process link, input the link performance data set into the link performance judgment model, and the link performance judgment model outputs the link performance judgment value of the process link.

[0014] Furthermore, based on the comparison result between the link monitoring value of the process link and the link monitoring threshold, determine whether to mark the process link as an abnormal process link. Specifically, set the link monitoring threshold. When the link monitoring value of the process link is greater than or equal to the link monitoring threshold, mark the process link as an abnormal process link, and simultaneously generate a link abnormality record for the process link. The link abnormality record includes the link monitoring value and the link abnormality time.

[0015] Furthermore, the abnormal process optimization value of the abnormal process link is obtained as follows: the next process link of the abnormal process link is marked as the process succession link, the process stage value and historical abnormal value of the abnormal process link are obtained, and marked as Y1, Y2, Y1 is the process stage value of the abnormal process link, Y2 is the historical abnormal value of the abnormal process link, the process stage value and historical abnormal value of the process succession link are obtained, and marked as Z1, Z2, Z1 is the process stage value of the process succession link, Z2 is the historical abnormal value of the process succession link, and the formula is used. Obtain the abnormal process optimization value DZet of the abnormal process link.

[0016] Furthermore, the process stage value is obtained as follows: obtain all link monitoring values ​​Stgb of the process link within the duration h, set the link monitoring value coefficient to BSz, sort all link monitoring values ​​in the order of update, calculate the difference between the two adjacent link monitoring values ​​after sorting and take the absolute value to obtain the link monitoring difference, set the link monitoring threshold difference, and when the link monitoring difference is greater than or equal to the link monitoring threshold difference, increase the link monitoring gap times by one, mark the link monitoring gap times as ECA, and use the formula The process stage value LCjd of the process link is obtained, where b=1, 2, ..., B, and B is the total number of link monitoring values.

[0017] Furthermore, the method for obtaining historical abnormal values ​​is as follows: obtain all link abnormality records of the process link within a time length of h, mark the total number of link abnormality records as Fgk, sort all link abnormality records in chronological order of the link abnormality moments, calculate the time difference between the link abnormality moments of two adjacent link abnormality records after sorting, obtain the link abnormality interval, set the link abnormality standard interval, when the link abnormality interval is greater than or equal to the link abnormality standard interval, increase the number of low standard intervals by one, when the link abnormality interval is less than the link abnormality standard interval, increase the number of high standard intervals by one, mark the number of low standard intervals as Lsz, and mark the number of high standard intervals as Gyt, and use the formula SKhg=Fgk*ea*(Lsz*eb+Gyt*ec) ​​to obtain the historical abnormal value SKhg of the process link, where ea is the abnormality quantity coefficient, eb is the low standard quantity coefficient, and ec is the high standard quantity coefficient.

[0018] Furthermore, the intelligent coating production full process monitoring and optimization method includes the following steps:

[0019] Step 1: During the coating production process, update the link monitoring value of each process link in the coating production every second;

[0020] Step 2: Based on the comparison result between the link monitoring value of the process link and the link monitoring threshold, determine whether to mark the process link as an abnormal process link;

[0021] Step 3: Obtain the abnormal process optimization value of the abnormal process link;

[0022] Step 4: Sort all abnormal process links in descending order according to the abnormal process optimization value, and optimize the abnormal process links in the sorted order.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The method of the present invention can monitor the paint production of each process link in an efficient and multi-dimensional manner, and accurately mark abnormal process links. The system of the present invention can perform detailed and in-depth analysis on each process link of paint production through a process link monitoring module and a link abnormality analysis module, determine the links that need to be optimized in paint production, and facilitate subsequent accurate optimization of abnormal process links. A link abnormality optimization module is set to comprehensively ensure that the core process links are optimized first, and the abnormal process links of the paint are optimized in sequence in an orderly and reasonable manner without affecting the full process production of the paint. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flow chart of the whole process monitoring and optimization method for intelligent coating production;

[0026] Figure 2 A flowchart for obtaining link performance judgment values;

[0027] Figure 3 This is the module diagram of the intelligent coating production full-process monitoring and optimization system. DETAILED DESCRIPTION

[0028] Example 1

[0029] Reference Figure 1 , the whole process monitoring and optimization method of intelligent coating production includes the following steps:

[0030] Step 1: During the coating production process, update the link monitoring value of each process link in the coating production every second;

[0031] Step 2: Based on the comparison result between the link monitoring value of the process link and the link monitoring threshold, determine whether to mark the process link as an abnormal process link;

[0032] Step 3: Obtain the abnormal process optimization value of the abnormal process link;

[0033] Step 4: Sort all abnormal process links in descending order according to the abnormal process optimization value, and optimize the abnormal process links in the sorted order.

[0034] The above method can monitor the coating production in each process link efficiently and multi-dimensionally, and accurately mark abnormal process links.

[0035] Example 2

[0036] Reference Figure 2-Figure 3 , intelligent coating production full-process monitoring and optimization system, including process link monitoring module, link abnormality analysis module, link abnormality optimization module.

[0037] Process link monitoring module: During the paint production process, the link monitoring value of each process link in the paint production is updated every second (the paint production includes multiple process links, which include but are not limited to mixing and dispersing links, grinding and refining links, and filtering and purification links).

[0038] The updating method of the link monitoring value of the process link is as follows: set g time points with equal time intervals within the duration s, and at each time point, obtain the link performance judgment value of the process link, sort all link performance judgment values ​​in order according to the sequence of time points, calculate the difference between the two adjacent link performance judgment values ​​after sorting and take the absolute value to obtain the link performance fluctuation value, sum up all link performance fluctuation values ​​and take the average to obtain the link performance fluctuation mean Mdsk, sum up the two adjacent link performance judgment values ​​after sorting to obtain the link performance continuous value, sum up all link performance continuous values ​​and take the average to obtain the link performance continuous mean Ksdt, set the link performance judgment boundary value (the link performance continuous threshold is the set threshold value), when the link performance judgment value is greater than or equal to the link performance judgment boundary value, mark the time point corresponding to the link performance judgment boundary value as the link performance abnormal point, when the link performance judgment value is less than the link performance judgment boundary value, do not do the corresponding processing, mark the total number of link performance abnormal points as Pahd, and use the formula The link monitoring value Stgb of this process link is obtained, where ka is the performance fluctuation coefficient, kb is the performance continuity coefficient, kc is the performance abnormality coefficient, the value of ka is 0.84, the value of kb is 0.98, and the value of kc is 0.69.

[0039] The method for obtaining the link performance judgment value of the process link is as follows: collect various link performance data of the coating produced in the process link (different process links need to collect different link performance data for the produced coatings, in order to determine the production quality of the coatings in different process links. Taking the mixing and dispersion link as an example, it is necessary to collect the following link performance data of the coating: viscosity data, particle size distribution data, sedimentation data, etc. Taking the filtration and purification link as an example, it is necessary to collect the following link performance data of the coating: impurity content data, purity data, uniformity data, etc.), combine the various link performance data into a link performance data set, obtain the link performance judgment model corresponding to the process link, input the link performance data set into the link performance judgment model, and the link performance judgment model outputs the link performance judgment value of the process link.

[0040] In the whole production process of the coating, since each process link is for the purpose of further processing the coating, different process links need to monitor different link performance data, and different process links correspond to different link performance judgment models. The training and construction methods of different link performance judgment models are the same, and only the training data needs to be replaced accordingly. This embodiment takes the mixing and dispersion link as an example, and discloses the training and construction methods of the link performance judgment model: k groups of link performance data of the mixing and dispersion link are obtained, wherein each group of link performance data of the mixing and dispersion link includes but is not limited to viscosity data, particle size distribution data, and sedimentation data. The above link performance data can be real data, or The data can be preset for model training. The link performance data of each group of mixing and dispersing links are combined into a link performance data set to build a deep learning model. The link performance data set is used as training data for the deep learning model. A link performance judgment value is assigned to each training data, wherein the link performance judgment value ranges from (1 to 3). The larger the link performance judgment value, the worse the paint production quality of the mixing and dispersing link. The smaller the link performance judgment value, the higher the paint production quality of the mixing and dispersing link. The training data is divided into 50% training set and 50% validation set, and the training data is trained. After the training is completed, a link performance judgment model for the mixing and dispersing link is obtained.

[0041] Link abnormality analysis module: Set the link monitoring threshold (the link monitoring threshold is the set threshold). When the link monitoring value of a process link is greater than or equal to the link monitoring threshold, the process link is marked as an abnormal process link, and the link abnormality record of the process link is generated simultaneously. The link abnormality record includes the link monitoring value and the link abnormality time. When the link monitoring value of a process link is less than the link monitoring threshold, no corresponding processing is performed.

[0042] Through the process link monitoring module and the link abnormality analysis module, each process link of paint production can be analyzed in detail and in depth, and the links that need to be optimized in paint production can be determined, so as to facilitate the subsequent precise optimization of abnormal process links.

[0043] Abnormal link optimization module: obtain the abnormal process optimization value of the abnormal process link, sort all the abnormal process links in order from large to small according to the abnormal process optimization value, and optimize the abnormal process links in the sorted order.

[0044] The abnormal process optimization value of the abnormal process link is obtained as follows: mark the next process link of the abnormal process link as the process succession link, obtain the process stage value and historical abnormal value of the abnormal process link, and mark them as Y1, Y2, where Y1 is the process stage value of the abnormal process link and Y2 is the historical abnormal value of the abnormal process link, obtain the process stage value and historical abnormal value of the process succession link, and mark them as Z1, Z2, where Z1 is the process stage value of the process succession link and Z2 is the historical abnormal value of the process succession link, and use the formula Obtain the abnormal process optimization value DZet of the abnormal process link (this formula is the cosine similarity calculation formula).

[0045] The method for obtaining the process stage value is as follows: obtain all link monitoring values ​​Stgb of the process link within the h duration (h duration > s duration), set the link monitoring value coefficient to BSz, z = 1, 2, 3, ... z; BS1 < BS2 < BS3 < ... < BSz, set each link monitoring value coefficient to correspond to a link monitoring value range, the link monitoring value range includes (0, Stg1], (Stg1, Stg2], ..., (StgB-1, StgB], when Stgb∈(0, Stg1], the link monitoring value coefficient is BS1, sort all link monitoring values ​​in the order of update, calculate the difference between the two adjacent link monitoring values ​​after sorting and take the absolute value to obtain the link monitoring difference, set the link monitoring threshold difference (the link monitoring threshold difference is the set threshold), when the link monitoring difference is greater than or equal to the link monitoring threshold difference, increase the link monitoring gap times by one, when the link monitoring difference is less than the link monitoring threshold difference, do not do the corresponding processing, mark the link monitoring gap times as ECA, and use the formula The process stage value LCjd of the process link is obtained, where b=1, 2, ..., B, and B is the total number of link monitoring values.

[0046] The method for obtaining historical abnormal values ​​is as follows: obtain all link abnormality records of the process link within a time length of h, mark the total number of link abnormality records as Fgk, sort all link abnormality records in chronological order of the link abnormality moments, calculate the time difference between the link abnormality moments of the two adjacent link abnormality records after sorting, obtain the link abnormality interval, set the link abnormality standard interval (the link abnormality standard interval is the set threshold), when the link abnormality interval is greater than or equal to the link abnormality standard interval, increase the number of low-standard intervals by one, when the link abnormality interval is less than the link abnormality standard interval, increase the number of high-standard intervals by one, mark the number of low-standard intervals as Lsz, and mark the number of high-standard intervals as Gyt, and use the formula SKhg=Fgk*ea*(Lsz*eb+Gyt*ec) ​​to obtain the historical abnormal value SKhg of the process link, where ea is the abnormality quantity coefficient, eb is the low-standard quantity coefficient, ec is the high-standard quantity coefficient, the value of ea is 1.31, the value of eb is 0.72, and the value of ec is 0.48.

[0047] Set up an abnormal link optimization module to comprehensively ensure that the core process links are optimized first, and optimize the abnormal process links of the coating in an orderly and reasonable manner without affecting the full process production of the coating.

[0048] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0049] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0050] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0051] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0052] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0053] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0054] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0055] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Intelligent coating production full process monitoring and optimization system, characterized by: It includes process link monitoring module, link abnormality analysis module, and link abnormality optimization module; The process link monitoring module: during the coating production process, the link monitoring value of each process link in the coating production is updated every second; The link abnormality analysis module: determines whether to mark a process link as an abnormal process link based on the comparison result of the link monitoring value of the process link and the link monitoring threshold; The abnormal link optimization module obtains the abnormal process optimization value of the abnormal process link, sorts all the abnormal process links in order from large to small according to the numerical value of the abnormal process optimization value, and optimizes the abnormal process links in order according to the sorting order.

2. The intelligent coating production full-process monitoring and optimization system according to claim 1 is characterized in that: The updating method of the link monitoring value of the process link is as follows: set g time points with equal time intervals within the duration s, and obtain the link performance judgment value of the process link at each time point, sort all link performance judgment values ​​in sequence according to the order of time points, calculate the difference between the two adjacent link performance judgment values ​​after sorting and take the absolute value to obtain the link performance fluctuation value, sum up all link performance fluctuation values ​​and take the average to obtain the link performance fluctuation mean Mdsk, sum up the two adjacent link performance judgment values ​​after sorting to obtain the link performance continuous value, sum up all link performance continuous values ​​and take the average to obtain the link performance continuous mean Ksdt, set the link performance judgment boundary value, and when the link performance judgment value is greater than or equal to the link performance judgment boundary value, mark the time point corresponding to the link performance judgment boundary value as the link performance abnormal point, mark the total number of link performance abnormal points as Pahd, and use the formula The link monitoring value Stgb of the process link is obtained, where ka is the performance fluctuation coefficient, kb is the performance continuity coefficient, and kc is the performance abnormality coefficient.

3. The intelligent coating production full-process monitoring and optimization system according to claim 2 is characterized in that: The method for obtaining the link performance judgment value of the process link is as follows: collect various link performance data of the coating produced in the process link, combine the various link performance data into a link performance data set, obtain the link performance judgment model corresponding to the process link, input the link performance data set into the link performance judgment model, and the link performance judgment model outputs the link performance judgment value of the process link.

4. The intelligent coating production full-process monitoring and optimization system according to claim 1 is characterized in that: Based on the comparison result between the link monitoring value of the process link and the link monitoring threshold, determine whether to mark the process link as an abnormal process link. Specifically, set the link monitoring threshold. When the link monitoring value of the process link is greater than or equal to the link monitoring threshold, mark the process link as an abnormal process link, and simultaneously generate a link abnormality record for the process link. The link abnormality record includes the link monitoring value and the link abnormality time.

5. The intelligent coating production full-process monitoring and optimization system according to claim 1 is characterized in that: The abnormal process optimization value of the abnormal process link is obtained as follows: mark the next process link of the abnormal process link as the process succession link, obtain the process stage value and historical abnormal value of the abnormal process link, and mark them as [Y1, Y2], where Y1 is the process stage value of the abnormal process link and Y2 is the historical abnormal value of the abnormal process link, obtain the process stage value and historical abnormal value of the process succession link, and mark them as [Z1, Z2], where Z1 is the process stage value of the process succession link and Z2 is the historical abnormal value of the process succession link, and use the formula Obtain the abnormal process optimization value DZet of the abnormal process link.

6. The intelligent coating production full-process monitoring and optimization system according to claim 5 is characterized in that: The method of obtaining the process stage value is as follows: obtain all link monitoring values ​​Stgb of the process link within the duration of h, set the link monitoring value coefficient to BSz, sort all link monitoring values ​​in the order of update, calculate the difference between the two adjacent link monitoring values ​​after sorting and take the absolute value to obtain the link monitoring difference, set the link monitoring threshold difference, when the link monitoring difference is greater than or equal to the link monitoring threshold difference, increase the link monitoring gap times by one, mark the link monitoring gap times as ECA, and use the formula The process stage value LCjd of the process link is obtained, where b=1, 2, ..., B, and B is the total number of link monitoring values.

7. The intelligent coating production full-process monitoring and optimization system according to claim 5 is characterized in that: The method for obtaining historical anomaly values ​​is as follows: obtain all link anomaly records of the process link within a time length of h, mark the total number of link anomaly records as Fgk, sort all link anomaly records in chronological order of the link anomaly moments, calculate the time difference between the link anomaly moments of two adjacent link anomaly records after sorting, obtain the link anomaly interval, set the link anomaly standard interval, when the link anomaly interval is greater than or equal to the link anomaly standard interval, increase the number of low standard intervals by one, when the link anomaly interval is less than the link anomaly standard interval, increase the number of high standard intervals by one, mark the number of low standard intervals as Lsz, and mark the number of high standard intervals as Gyt, use the formula SKhg=Fgk*ea*(Lsz*eb+Gyt*ec) ​​to obtain the historical anomaly value SKhg of the process link, where ea is the anomaly quantity coefficient, eb is the low standard quantity coefficient, and ec is the high standard quantity coefficient.

8. An intelligent coating production full-process monitoring and optimization method, applied to the intelligent coating production full-process monitoring and optimization system according to claim 1, characterized in that: The steps include: Step 1: During the coating production process, update the link monitoring value of each process link in the coating production every second; Step 2: Based on the comparison result between the link monitoring value of the process link and the link monitoring threshold, determine whether to mark the process link as an abnormal process link; Step 3: Obtain the abnormal process optimization value of the abnormal process link; Step 4: Sort all abnormal process links in descending order according to the abnormal process optimization value, and optimize the abnormal process links in the sorted order.

9. Intelligent coating production full process monitoring and optimization media, characterized by: Applicable to executing the intelligent coating production full-process monitoring and optimization method described in claim 8.

Images