Automatic production control system and method based on artificial intelligence

Abstract

The invention discloses an automatic production control system and method based on artificial intelligence, and relates to the technical field of coating automatic production, the system comprises a raw material processing module, a process intelligent mixing module, a self-adaptive packaging module and an automatic production control module; the output end of the raw material processing module is connected with the input end of the process intelligent mixing module; the output end of the process intelligent mixing module is connected with the input end of the self-adaptive packaging module; the automatic production control module is connected with the raw material processing module, the technology intelligent mixing module and the self-adaptive packaging module. According to the method, intelligent parameter adjustment in the automatic coating production process can be achieved, and the problem that the coating yield is low in the face of brand-new coatings or brand-new plant environments and brand-new machines is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of automated coating production, and in particular to an automated production control system and method based on artificial intelligence. Background Art

[0002] In the current field of paint automation production technology, the production line can generally be divided into four areas: raw material storage area, production area, packaging area and finished product storage area. The raw material storage area should be equipped with appropriate storage equipment, such as storage tanks and tanks, to ensure the safety and preservation quality of the raw materials. The production area is used for automatic production of paint, including raw material batching, stirring, filtering, viscosity adjustment and other processes. Finally, the packaging area is equipped for packaging and labeling the produced paint.

[0003] However, in the current automated production process of paint, paint production is often carried out using existing paint production parameters. When faced with new paint or a new factory environment or a new machine, the paint yield rate will be problematic. Current technical means are often attempted through manual experience, which is time-consuming and labor-intensive, and requires guidance from extremely experienced engineers. There is a lack of intelligent data analysis on the parameter adjustment direction and the correlation between several parameters, making its application in new paint scenarios very complicated. Summary of the invention

[0004] The purpose of the present invention is to provide an automated production control system and method based on artificial intelligence to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: an automated production control method based on artificial intelligence, the method comprising the following steps:

[0006] S1. Obtain the raw materials required for coating production, store them in the raw material processing module, and feed the raw materials into the automated production control system via the feeding device;

[0007] S2. The administrator inputs the initial parameters, and the automated production control system mixes, stirs and filters according to the set initial parameters to form a finished coating;

[0008] S3, monitor the success rate of finished paint, conduct intelligent feedback, form intelligent adjustment of system parameters, and output the finished paint when the success rate meets the threshold set by the administrator;

[0009] S4. Call the adaptive packaging module to automatically package the finished paint and output it to the production platform, and the automated production is completed.

[0010] According to the above technical solution, in steps S1 to S2, it also includes:

[0011] Inspect the raw materials and compare them with the raw material parameters input by the system to ensure that the parameters of the raw materials are within the raw material parameter range input by the system;

[0012] The initial parameters refer to the original parameters of the produced coating, which are obtained by the administrator according to daily experience or existing technology.

[0013] According to the above technical solution, in step S3, it also includes:

[0014] The success rate refers to the proportion of finished coatings that meet quality inspection requirements, which include appearance, viscosity and drying time. The system sets thresholds for each inspection requirement, performs quality inspection on the finished coatings, and the proportion that meets the requirements is taken as the success rate.

[0015] According to the above technical solution, it also includes:

[0016] Get the initial parameters, recorded as the set {x 1 、x 2 , …, x n}, where x 1 、x 2 , …, x n Respectively represent the values ​​of the 1st, 2nd, ..., nth parameters in the initial parameters;

[0017] Monitor the success rate of finished coatings. When the success rate does not meet the threshold set by the administrator, perform random parameter adjustments. The random adjustment refers to re-taking values ​​and combining parameters within the parameter range, and then producing coatings again. Set a constant K. If the success rate of finished coatings in K consecutive groups does not meet the threshold set by the administrator, then take the data of the K groups whose success rate of finished coatings does not meet the threshold set by the administrator to form a data reference set. Sort the data of the data reference set in order of success rate from low to high to form a data reference list. If there is data in the K groups whose success rate of finished coatings meets the threshold set by the administrator, take the coating production parameters closest to the threshold set by the administrator to produce coatings.

[0018] In the data reference list, select any initial parameter x i , for x i Conduct adjacent data analysis, which refers to calculating the growth rate:

[0019]

[0020] Among them, H i+1 , H i Represent the initial parameters x i The adjacent data, H i+1 In H i rear; L represents the growth rate;

[0021] Analyze the formed growth rate, calculate the proportion greater than 0 or less than 0, select the one with a larger proportion as the mainstream growth mode of the growth rate, and input the data of the non-mainstream growth mode into the first data set;

[0022] Calculate the success rate growth rate corresponding to each mainstream growth method to form a coordinate (a 1 、b 1 ), where a 1 Refers to the growth rate of adjacent data under the mainstream growth mode; b 1 Refers to the success rate growth rate corresponding to the adjacent data growth rate under the mainstream growth mode; linear fitting is performed on all the formed coordinates, and the formed function is used as the initial parameter x i Correlation function between the initial parameter x and the success rate. If the slope of the function is greater than 0, it means that the initial parameter x i There is a positive correlation with the success rate, and vice versa, a negative correlation;

[0023] The correlation functions are calculated for all initial parameters and the output forms a correlation function relationship list;

[0024] Take the data in the first data set and calculate the initial parameter x i The growth rate of other initial parameters other than j , then x j The growth rate in the first data set is denoted as {m 1 、m 2 ,…,m t}, where m 1 、m 2 ,…,m t Represents x j The growth rate in the first data set, t represents the number of data in the first data set;

[0025] For the initial parameter x i Other initial parameters x in the mainstream growth method j The growth rates of adjacent data in are calculated, and the average value is taken to form other initial parameters x j At the initial parameter x i The characteristic value under the mainstream growth mode;

[0026] Construct initial parameters x i The priority of the associated parameters is:

[0027]

[0028] Where P represents the initial parameter x i The priority of the associated parameters, m S Point to x jThe sth data in the first data set; u represents other initial parameters x j At the initial parameter x i The characteristic value under the mainstream growth mode;

[0029] The associated parameter priorities of the initial parameters are calculated for all initial parameters.

[0030] According to the above technical solution, the intelligent adjustment of the system parameters includes:

[0031] Obtain a list of related function relationships of all initial parameters, compare the absolute values ​​of the slopes of all related functions, take the initial parameter corresponding to the function with the largest absolute value as the first adjustment initial parameter, determine whether it is positively or negatively correlated with the success rate, and adjust it in the direction of improving the success rate. During the adjustment process, keep other initial parameters unchanged. If the success rate threshold set by the administrator cannot be reached when adjusted to the parameter range boundary set by the administrator, adjust other initial parameters;

[0032] The adjustment of other initial parameters includes:

[0033] Get the priority of the associated parameters of the current initial parameters, select the initial parameters with the lowest priority of the associated parameters and start adjusting until the success rate threshold set by the administrator is met. If all adjustments are completed and the success rate threshold set by the administrator still cannot be met, then take the next larger slope value of the related function and readjust;

[0034] If the adjustment of all related functions cannot meet the success rate threshold set by the administrator, an alarm will be issued.

[0035] An automated production control system based on artificial intelligence, the system comprising: a raw material processing module, a process intelligent mixing module, an adaptive packaging module and an automated production control module;

[0036] The raw material processing module is used to store, transport and pre-treat the raw materials required for paint production; the process intelligent mixing module is used to mix, stir and filter the raw materials according to the system setting parameters to form finished paint, monitor the success rate of the finished paint, perform intelligent feedback, form intelligent adjustment of system parameters, and output the finished paint when the success rate meets the threshold set by the administrator; the adaptive packaging module is used to automatically package the finished paint and store packaging materials; the automated production control module is used to monitor and control the data of the automated production line in real time, and the control means has control over other modules of the automated production control system and can realize the switching of each module;

[0037] The output end of the raw material processing module is connected to the input end of the process intelligent mixing module; the output end of the process intelligent mixing module is connected to the input end of the adaptive packaging module; the automated production control module is respectively connected to the raw material processing module, the process intelligent mixing module, and the adaptive packaging module.

[0038] According to the above technical solution, the process intelligent mixing module includes an initial parameter processing unit and an intelligent feedback unit;

[0039] The initial parameter processing unit is used to mix, stir and filter the raw materials according to the system setting parameters to form a finished coating, monitor the success rate of the finished coating, and perform intelligent feedback; the intelligent feedback unit forms an intelligent adjustment of the system parameters based on the intelligent feedback, and outputs the finished coating when the success rate meets the threshold set by the administrator;

[0040] The output end of the initial parameter processing unit is connected to the input end of the intelligent feedback unit.

[0041] According to the above technical solution, the adaptive packaging module includes a packaging material storage unit and an automatic packaging unit;

[0042] The packaging material storage unit is a packaging device for storing finished paint; the automatic packaging unit is used to connect to a filling machine to automatically package the finished paint;

[0043] The output end of the packaging material storage unit is connected to the input end of the automatic packaging unit.

[0044] According to the above technical solution, the automated production control module includes a monitoring unit and a control unit;

[0045] The monitoring unit is used to monitor the data of the automated production line in real time; the control unit is used to have control over other modules of the automated production control system and can realize the switching on and off of each module.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention can realize intelligent adjustment of parameters in the automated production process of coatings, solve the problem of low coating yield when facing new coatings or new factory environments, and new machines, does not require rich manual experience guidance, saves manpower and material resources, and provides intelligent parameter data analysis, making the application in new coating scenarios simpler and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 The present invention is a flowchart of an automated production control method based on artificial intelligence. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Example: Figure 1 As shown, the present invention provides an automated production control method based on artificial intelligence, the method comprising: obtaining raw materials required for coating production, storing them in a raw material processing module, and feeding the raw materials into an automated production control system via a feeding device; inspecting the raw materials, comparing the raw material parameters input by the system, and ensuring that the parameters of the raw materials are within the raw material parameter range input by the system;

[0050] The administrator inputs the initial parameters, and the automated production control system mixes, stirs and filters according to the set initial parameters to form the finished coating;

[0051] The initial parameters refer to the original parameters of the produced coating, which are obtained by the administrator according to daily experience or existing technology.

[0052] Monitor the success rate of finished paint, conduct intelligent feedback, and form intelligent adjustments to system parameters. When the success rate meets the threshold set by the administrator, the finished paint is output;

[0053] The success rate refers to the proportion of finished coatings that meet quality inspection requirements, which include appearance, viscosity and drying time. The system sets thresholds for each inspection requirement, performs quality inspection on the finished coatings, and the proportion that meets the requirements is taken as the success rate.

[0054] Get the initial parameters, recorded as the set {x 1 、x 2 , …, x n}, where x 1 、x 2 , …, x n Respectively represent the values ​​of the 1st, 2nd, ..., nth parameters in the initial parameters;

[0055] Monitor the success rate of finished coatings. When the success rate does not meet the threshold set by the administrator, perform random parameter adjustments. The random adjustment refers to re-taking values ​​and combining parameters within the parameter range, and then producing coatings again. Set a constant K. If the success rate of finished coatings in K consecutive groups does not meet the threshold set by the administrator, then take the data of the K groups whose success rate of finished coatings does not meet the threshold set by the administrator to form a data reference set. Sort the data of the data reference set in order of success rate from low to high to form a data reference list. If there is data in the K groups whose success rate of finished coatings meets the threshold set by the administrator, take the coating production parameters closest to the threshold set by the administrator to produce coatings.

[0056] In the data reference list, select any initial parameter x i , for x i Conduct adjacent data analysis, which refers to calculating the growth rate:

[0057]

[0058] Among them, H i+1 , H i Represent the initial parameters x i The adjacent data, H i+1 In H i rear; L represents the growth rate;

[0059] Analyze the formed growth rate, calculate the proportion greater than 0 or less than 0, select the one with a larger proportion as the mainstream growth mode of the growth rate, and input the data of the non-mainstream growth mode into the first data set;

[0060] Calculate the success rate growth rate corresponding to each mainstream growth method to form a coordinate (a 1 、b 1 ), where a 1 Refers to the growth rate of adjacent data under the mainstream growth mode; b 1 Refers to the success rate growth rate corresponding to the adjacent data growth rate under the mainstream growth mode; linear fitting is performed on all the formed coordinates, and the formed function is used as the initial parameter x i Correlation function between the initial parameter x and the success rate. If the slope of the function is greater than 0, it means that the initial parameter x i There is a positive correlation with the success rate, and vice versa, a negative correlation;

[0061] The correlation functions are calculated for all initial parameters and the output forms a correlation function relationship list;

[0062] Take the data in the first data set and calculate the initial parameter x i The growth rate of other initial parameters other than j, then x j The growth rate in the first data set is denoted as {m 1 、m 2 ,…,m t}, where m 1 、m 2 ,…,m t Represents x j The growth rate in the first data set, t represents the number of data in the first data set;

[0063] For the initial parameter x i Other initial parameters x in the mainstream growth method j The growth rates of adjacent data in are calculated, and the average value is taken to form other initial parameters x j At the initial parameter x i The characteristic value under the mainstream growth mode;

[0064] Construct initial parameters x i The priority of the associated parameters is:

[0065]

[0066] Where P represents the initial parameter x i The priority of the associated parameters, m S Point to x j The sth data in the first data set; u represents other initial parameters x j At the initial parameter x i The characteristic value under the mainstream growth mode;

[0067] The associated parameter priorities of the initial parameters are calculated for all initial parameters.

[0068] The intelligent adjustment of the system parameters includes:

[0069] Obtain a list of related function relationships of all initial parameters, compare the absolute values ​​of the slopes of all related functions, take the initial parameter corresponding to the function with the largest absolute value as the first adjustment initial parameter, determine whether it is positively or negatively correlated with the success rate, and adjust it in the direction of improving the success rate. During the adjustment process, keep other initial parameters unchanged. If the success rate threshold set by the administrator cannot be reached when adjusted to the parameter range boundary set by the administrator, adjust other initial parameters;

[0070] The adjustment of other initial parameters includes:

[0071] Get the priority of the associated parameters of the current initial parameters, select the initial parameters with the lowest priority of the associated parameters and start adjusting until the success rate threshold set by the administrator is met. If all adjustments are completed and the success rate threshold set by the administrator still cannot be met, then take the next larger slope value of the related function and readjust;

[0072] If the adjustment of all related functions cannot meet the success rate threshold set by the administrator, an alarm will be issued.

[0073] In this embodiment, an automated production control system based on artificial intelligence is also provided, the system comprising: a raw material processing module, a process intelligent mixing module, an adaptive packaging module and an automated production control module;

[0074] The raw material processing module is used to store, transport and pre-treat the raw materials required for paint production; the process intelligent mixing module is used to mix, stir and filter the raw materials according to the system setting parameters to form finished paint, monitor the success rate of the finished paint, perform intelligent feedback, form intelligent adjustment of system parameters, and output the finished paint when the success rate meets the threshold set by the administrator; the adaptive packaging module is used to automatically package the finished paint and store packaging materials; the automated production control module is used to monitor and control the data of the automated production line in real time, and the control means has control over other modules of the automated production control system and can realize the switching of each module;

[0075] The output end of the raw material processing module is connected to the input end of the process intelligent mixing module; the output end of the process intelligent mixing module is connected to the input end of the adaptive packaging module; the automated production control module is respectively connected to the raw material processing module, the process intelligent mixing module, and the adaptive packaging module.

[0076] The process intelligent mixing module includes an initial parameter processing unit and an intelligent feedback unit;

[0077] The initial parameter processing unit is used to mix, stir and filter the raw materials according to the system setting parameters to form a finished coating, monitor the success rate of the finished coating, and perform intelligent feedback; the intelligent feedback unit forms an intelligent adjustment of the system parameters based on the intelligent feedback, and outputs the finished coating when the success rate meets the threshold set by the administrator;

[0078] The output end of the initial parameter processing unit is connected to the input end of the intelligent feedback unit.

[0079] The adaptive packaging module includes a packaging material storage unit and an automatic packaging unit;

[0080] The packaging material storage unit is a packaging device for storing finished paint; the automatic packaging unit is used to connect to a filling machine to automatically package the finished paint;

[0081] The output end of the packaging material storage unit is connected to the input end of the automatic packaging unit.

[0082] The automated production control module includes a monitoring unit and a control unit;

[0083] The monitoring unit is used to monitor the data of the automated production line in real time; the control unit is used to have control over other modules of the automated production control system and can realize the switching on and off of each module.

[0084] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An automated production control method based on artificial intelligence, characterized in that: The method comprises the following steps: S1. Obtain the raw materials required for coating production, store them in the raw material processing module, and feed the raw materials into the automated production control system via the feeding device; S2. The administrator inputs the initial parameters, and the automated production control system mixes, stirs and filters according to the set initial parameters to form a finished coating; S3, monitor the success rate of finished paint, conduct intelligent feedback, form intelligent adjustment of system parameters, and output the finished paint when the success rate meets the threshold set by the administrator; S4. Call the adaptive packaging module to automatically package the finished paint and output it to the production platform, and the automated production is completed.

2. The method for automated production control based on artificial intelligence according to claim 1, characterized in that: In steps S1 to S2, it also includes: Inspect the raw materials and compare them with the raw material parameters input by the system to ensure that the parameters of the raw materials are within the raw material parameter range input by the system; The initial parameters refer to the original parameters of the produced coating, which are obtained by the administrator according to daily experience or existing technology.

3. The method for automated production control based on artificial intelligence according to claim 1, characterized in that: In step S3, it also includes: The success rate refers to the proportion of finished coatings that meet quality inspection requirements, which include appearance, viscosity and drying time. The system sets thresholds for each inspection requirement, performs quality inspection on the finished coatings, and the proportion that meets the requirements is taken as the success rate.

4. The method for automated production control based on artificial intelligence according to claim 1, characterized in that: Also includes: Get the initial parameters, recorded as the set {x1, x2, ..., x n }, where x1, x2, …, x n Respectively represent the values ​​of the 1st, 2nd, ..., nth parameters in the initial parameters; Monitor the success rate of finished coatings. When the success rate does not meet the threshold set by the administrator, perform random parameter adjustments. The random adjustment refers to re-taking values ​​and combining parameters within the parameter range, and then producing coatings again. Set a constant K. If the success rate of finished coatings in K consecutive groups does not meet the threshold set by the administrator, then take the data of the K groups whose success rate of finished coatings does not meet the threshold set by the administrator to form a data reference set. Sort the data of the data reference set in order of success rate from low to high to form a data reference list. If there is data in the K groups whose success rate of finished coatings meets the threshold set by the administrator, take the coating production parameters closest to the threshold set by the administrator to produce coatings. In the data reference list, select any initial parameter x i , for x i Conduct adjacent data analysis, which refers to calculating the growth rate: Among them, H i+1 , H i Represent the initial parameters x i The adjacent data, H i+1 In H i rear; L represents the growth rate; Analyze the formed growth rate, calculate the proportion greater than 0 or less than 0, select the one with a larger proportion as the mainstream growth mode of the growth rate, and input the data of the non-mainstream growth mode into the first data set; Calculate the success rate growth rate corresponding to each mainstream growth mode to form coordinates (a1, b1), where a1 refers to the adjacent data growth rate under the mainstream growth mode; b1 refers to the success rate growth rate corresponding to the adjacent data growth rate under the mainstream growth mode; perform linear fitting on all the formed coordinates, and the formed function is used as the initial parameter x i Correlation function between the initial parameter x and the success rate. If the slope of the function is greater than 0, it means that the initial parameter x i There is a positive correlation with the success rate, and vice versa, a negative correlation; The correlation functions are calculated for all initial parameters and the output forms a correlation function relationship list; Take the data in the first data set and calculate the initial parameter x i The growth rate of other initial parameters other than j , then x j The growth rate in the first data set is recorded as {m1, m2, ..., m t }, where m1, m2, …, m t Represents x j The growth rate in the first data set, t represents the number of data in the first data set; For the initial parameter x i Other initial parameters x in the mainstream growth method j The growth rates of adjacent data in are calculated, and the average value is taken to form other initial parameters x j At the initial parameter x i The characteristic value under the mainstream growth mode; Construct initial parameters x i The priority of the associated parameters is: Where P represents the initial parameter x i The priority of the associated parameters, m S Point to x j The sth data in the first data set; u represents other initial parameters x j At the initial parameter x i The characteristic value under the mainstream growth mode; The associated parameter priorities of the initial parameters are calculated for all initial parameters.

5. The method for automated production control based on artificial intelligence according to claim 4, characterized in that: The intelligent adjustment of the system parameters includes: Obtain a list of related function relationships of all initial parameters, compare the absolute values ​​of the slopes of all related functions, take the initial parameter corresponding to the function with the largest absolute value as the first adjustment initial parameter, determine whether it is positively or negatively correlated with the success rate, and adjust it in the direction of improving the success rate. During the adjustment process, keep other initial parameters unchanged. If the success rate threshold set by the administrator cannot be reached when adjusted to the parameter range boundary set by the administrator, adjust other initial parameters; The adjustment of other initial parameters includes: Get the priority of the associated parameters of the current initial parameters, select the initial parameters with the lowest priority of the associated parameters and start adjusting until the success rate threshold set by the administrator is met. If all adjustments are completed and the success rate threshold set by the administrator still cannot be met, then take the next larger slope value of the related function and readjust; If the adjustment of all related functions cannot meet the success rate threshold set by the administrator, an alarm will be issued.

6. An automated production control system based on artificial intelligence, characterized in that: The system includes: raw material processing module, process intelligent mixing module, adaptive packaging module and automated production control module; The raw material processing module is used to store, transport and pre-treat the raw materials required for paint production; the process intelligent mixing module is used to mix, stir and filter the raw materials according to the system setting parameters to form finished paint, monitor the success rate of the finished paint, perform intelligent feedback, form intelligent adjustment of system parameters, and output the finished paint when the success rate meets the threshold set by the administrator; the adaptive packaging module is used to automatically package the finished paint and store packaging materials; the automated production control module is used to monitor and control the data of the automated production line in real time, and the control means has control over other modules of the automated production control system and can realize the switching of each module; The output end of the raw material processing module is connected to the input end of the process intelligent mixing module; the output end of the process intelligent mixing module is connected to the input end of the adaptive packaging module; the automated production control module is respectively connected to the raw material processing module, the process intelligent mixing module, and the adaptive packaging module.

7. The artificial intelligence-based automated production control system according to claim 6, characterized in that: The process intelligent mixing module includes an initial parameter processing unit and an intelligent feedback unit; The initial parameter processing unit is used to mix, stir and filter the raw materials according to the system set parameters to form a finished coating, monitor the success rate of the finished coating, and perform intelligent feedback; the intelligent feedback unit forms an intelligent adjustment of the system parameters based on the intelligent feedback, and outputs the finished coating when the success rate meets the threshold set by the administrator; The output end of the initial parameter processing unit is connected to the input end of the intelligent feedback unit.

8. The artificial intelligence-based automated production control system according to claim 6, characterized in that: The adaptive packaging module includes a packaging material storage unit and an automatic packaging unit; The packaging material storage unit is a packaging device for storing finished paint; the automatic packaging unit is used to connect to a filling machine to automatically package the finished paint; The output end of the packaging material storage unit is connected to the input end of the automatic packaging unit.

9. The artificial intelligence-based automated production control system according to claim 6, characterized in that: The automated production control module includes a monitoring unit and a control unit; The monitoring unit is used to monitor the data of the automated production line in real time; the control unit is used to have control over other modules of the automated production control system and can realize the switching on and off of each module.

Images