Production control method and production safety management system based on digital twinning

Abstract

The invention discloses a digital twinning-based production control method and a production safety management system, and relates to the field of production control. The production process of a to-be-controlled production product is controlled from the perspective of reducing time consumed for producing the to-be-controlled production product; the shutdown maintenance operation is carried out when the production equipment involved in the production process reaches which state grade, and when the production equipment reaches different state grades, the shutdown maintenance time consumption of the production equipment is different; by adjusting the state grade data of each type of production equipment during optimal shutdown, the overall time consumption for producing the to-be-controlled production product is minimum; by setting a plurality of grades of the production equipment, a quantitative data value for measuring the current state of the production equipment is provided, label data is provided for subsequently constructing a final production equipment state grade mapping model set, and an acquisition basis is also provided for subsequently acquiring test data required for constructing a final production equipment maintenance time consumption mapping equation set.

Description

Technical Field

[0001] The present invention belongs to the field of production control. Specifically, it particularly relates to a production control method and a production safety management system based on digital twin. Background Art

[0002] During the production process of safety helmets, it involves the shutdown and maintenance of production equipment. If the set shutdown and maintenance time for each production equipment is unreasonable, it will affect the normal operation of the equipment, thereby reducing production efficiency. On the one hand, too long a shutdown time will lead to production interruption and the inability to complete production tasks on time; too short a shutdown time may not completely solve equipment problems, resulting in frequent equipment failures, which also affects production efficiency. On the other hand, unreasonable shutdown and maintenance time may increase the idle costs of labor and equipment. Summary of the Invention

[0003] In view of the problems in the related art, the present invention proposes a production control method and a production safety management system based on digital twin to overcome the above-mentioned technical problems existing in the existing related art.

[0004] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0005] The present invention provides a production control method based on digital twin, including the following steps:

[0006] S1. Set several production stages, corresponding production equipment types involved, and corresponding equipment parameter types when producing the production product to be controlled, to obtain a set of production stages to be controlled, a matrix of production equipment types to be controlled, and a matrix of production equipment parameter types to be controlled;

[0007] S2. According to the matrix of production equipment types to be controlled and the matrix of production equipment parameter types to be controlled, collect several groups of historical data on the elapsed time of current use, various types of production equipment parameter data, corresponding maintenance personnel data, maintenance elapsed time data, and corresponding production equipment status level data for each type of production equipment to be controlled, to obtain a set of historical production equipment parameter data matrices, a historical production equipment elapsed time data matrix, a historical production equipment status level data matrix, a historical maintenance personnel quantity matrix, and a historical maintenance elapsed time data matrix; and construct a set of final production equipment status level mapping models and a set of final production equipment maintenance elapsed time mapping equations;

[0008] S3. Set a lower limit threshold for the status level of each production equipment according to the matrix of production equipment types to be controlled, to obtain a set of lower limit thresholds for equipment status levels;

[0009] Adjust the lower limit threshold set of the equipment status level according to the final production equipment status level mapping model set, the final production equipment maintenance time-consuming mapping equation set, the production stage set to be controlled, the matrix of the types of production equipment to be controlled, and the matrix of the types of production equipment parameter types to be controlled, so as to obtain the final lower limit threshold set of the equipment status level, and minimize the overall time-consuming of the production product to be controlled;

[0010] This solution controls the production process of the production product to be controlled from the perspective of reducing the time-consuming required for production. Specifically, for the production equipment involved in its production process, when it reaches what state level, shutdown maintenance operations are carried out. When the production equipment reaches different state levels, the time consumption for its shutdown maintenance is also different; Therefore, this solution aims to adjust the state level data of the optimal shutdown time of each type of production equipment to minimize the overall time-consuming of the production of the production product to be controlled;

[0011] Among them, by setting the production stage set to be controlled, the matrix of the types of production equipment to be controlled, and the matrix of the types of production equipment parameter types to be controlled, because different production equipment is involved in different stages of the production process. By dividing the production process into stages, the accuracy of adjusting the state level of the production equipment at shutdown is improved; The parameter equipment of the production equipment also has an impact on the total duration of its work maintenance. By considering the impact of the production equipment parameters, the accuracy of the state level of the current production equipment obtained subsequently is further improved; By constructing the final production equipment status level mapping model set and the final production equipment maintenance time-consuming mapping equation set, it provides data basis for subsequently obtaining the status level data of each production equipment in real time during the production of the production product to be controlled and the time-consuming data required for its maintenance at the current state level, so as to adjust the state level data of the optimal shutdown time of each type of production equipment.

[0012] Preferably, S1 includes the following steps:

[0013] S11. Set the production product to be controlled; Set several production stages when producing the production product to be controlled to obtain the production stage set to be controlled; Set the types of production equipment and the corresponding equipment parameter types involved in each production stage in the production stage set to be controlled to obtain the matrix of the types of production equipment to be controlled and the matrix of the types of production equipment parameter types to be controlled; The production product to be controlled is preferably a safety helmet;

[0014] S12. In coordination with the set of production stages to be controlled, the matrix of types of production equipment to be controlled, and the matrix of types of production equipment parameter sets to be controlled, collect parameter data of various types of production equipment during several historical production processes to obtain a historical production equipment parameter data matrix set; construct a digital twin model for each type of production equipment based on the historical production equipment parameter data matrix set to obtain a set of digital twin models of production equipment to be controlled;

[0015] The construction of a digital twin model requires data. Therefore, collect parameter data of various types of production equipment during several historical production processes to construct a digital twin model for the corresponding production equipment; a digital twin model is a technology that combines physical entities with virtual models. Through digitalization, it realizes the simulation, monitoring, and optimization of physical objects; it can achieve real-time monitoring of the physical world, accurate three-dimensional visualization, and prediction of potential faults in physical systems through Internet of Things sensors and big data analysis, so as to perform maintenance in advance, reduce downtime and maintenance costs.

[0016] Preferably, S2 includes the following steps:

[0017] S21. Set several equipment status levels for each type of production equipment in the matrix of types of production equipment to be controlled to obtain a set of production equipment status levels;

[0018] In coordination with the set of digital twin models of production equipment to be controlled, the matrix of types of production equipment to be controlled, the set of production equipment status levels, and the matrix of types of production equipment parameter sets to be controlled, collect several sets of historical data on the elapsed time of current use, parameter data of various types of production equipment, and corresponding production equipment status level data for each type of production equipment to be controlled to obtain a historical production equipment parameter data matrix set, a historical production equipment elapsed time data matrix, and a historical production equipment status level data matrix a - 1;

[0019] S22. Collect the data on the number of maintenance personnel and the corresponding elapsed time required to repair each production equipment status level data in the historical production equipment status level data matrix to the corresponding initial production equipment status level data to obtain a historical maintenance personnel quantity matrix a - 2 and a historical maintenance elapsed time data matrix a - 3; a - 1, a - 2, and a - 3 are as follows,

[0020]

[0021] Among them, respectively represent the status level data of the j-th type of production equipment in the i-th group of collected history, the number of personnel used for its maintenance, and the time-consuming data for its maintenance; b1 represents the total number of production equipment types involved in the production equipment type matrix to be controlled; b2 represents the total number of groups of the currently used time-consuming data, various types of production equipment parameter data, and the corresponding production equipment status level data in the collection history in S21;

[0022] Construct a final production equipment status level mapping model set according to the historical production equipment parameter data matrix set, the historical production equipment used time-consuming data matrix, and the historical production equipment status level data matrix;

[0023] S23. Construct a final production equipment maintenance time-consuming mapping equation set according to the production equipment status level data, the historical maintenance personnel number matrix, and the historical maintenance time-consuming data matrix;

[0024] By setting several levels of production equipment, quantitative data values for measuring the current status of production equipment are provided, which provides label data for constructing the final production equipment status level mapping model set later, and also provides a collection basis for collecting the test data required for constructing the final production equipment maintenance time-consuming mapping equation set later; The final production equipment status level mapping model is used to realize the mapping from the production equipment used time-consuming data and the production equipment parameter data to the production equipment status level data; The final production equipment maintenance time-consuming mapping equation set is used to realize the mapping from the production equipment status level data and the number of maintenance personnel to the time-consuming data required for maintenance; It provides a mapping model and tool for adjusting the status level data of each equipment that needs to be shut down for maintenance during the production process of the production product to be controlled later.

[0025] Preferably, S23 includes the following steps:

[0026] S231. Construct an initial production equipment maintenance time-consuming mapping equation set a = {a1,..., a i ,..., a a′}, a i represents the initial production equipment maintenance time-consuming mapping equation set for the i-th type of production equipment in the production equipment parameter type set matrix to be controlled, a' represents the total number of production equipment types in the production equipment parameter type set matrix to be controlled, and the total number of production equipment types in the production equipment parameter type set matrix to be controlled is the same as the total number of the set initial production equipment maintenance time-consuming mapping equations; a i is as follows,

[0027]

[0028] In the formula, is the dependent variable, representing the data of maintenance time consumption; represents a i mapping relationship; are all independent variables, respectively representing the number of maintenance personnel and the data of the equipment status level before maintenance;

[0029] S232. In combination with the initial mapping equation set of the maintenance time consumption of the production equipment, each data in the historical production equipment status level data matrix and the historical number of maintenance personnel matrix is respectively combined and substituted into the corresponding initial mapping equation of the maintenance time consumption of the production equipment for mapping, so as to obtain the initial mapping data matrix of the historical maintenance time consumption as follows,

[0030]

[0031] wherein, represents the initial mapping data obtained by inputting into the j-th initial mapping equation of the maintenance time consumption of the production equipment in the initial mapping equation set of the maintenance time consumption of the production equipment for mapping;

[0032] S233. Set the error threshold of the mapping of the maintenance time consumption; calculate the error data between the corresponding column data in the initial mapping data matrix of the historical maintenance time consumption and the historical maintenance time consumption data matrix, so as to obtain the historical maintenance time consumption mapping error data set c = {c1,..., c j ,..., c b1}, c j represents the error data between the j-th column data in the initial mapping data matrix of the historical maintenance time consumption and the historical maintenance time consumption data matrix; the calculation formula is as follows,

[0033]

[0034] When there is historical maintenance time consumption mapping error data greater than or equal to the error threshold of the mapping of the maintenance time consumption in the historical maintenance time consumption mapping error data set, adjust the initial mapping equation of the maintenance time consumption of the production equipment corresponding to the historical maintenance time consumption mapping error data until there is no historical maintenance time consumption mapping error data greater than or equal to the error threshold of the mapping of the maintenance time consumption in the historical maintenance time consumption mapping error data set, and then obtain the final mapping equation set of the maintenance time consumption of the production equipment; otherwise, use the initial mapping equation set of the maintenance time consumption of the production equipment as the final mapping equation set of the maintenance time consumption of the production equipment;

[0035] By substituting the collected relevant historical production data into the corresponding initial production equipment maintenance time mapping equation, on the one hand, the mapping accuracy of the initial production equipment maintenance time mapping equation is detected, and on the other hand, when the mapping accuracy of the initial production equipment maintenance time mapping equation meets the requirements, the subsequent process of adjusting the mapping equation can be avoided, improving the construction efficiency of the mapping equation; among them, by setting a maintenance time mapping error threshold, a quantitative judgment basis is provided for determining whether the error between the mapping data and the actual data of the initial production equipment maintenance time mapping equation meets the requirements.

[0036] Preferably, S3 includes the following steps:

[0037] S31. Set the total time threshold for all stages in the production stage to be controlled and the total time data for the overall production to be controlled to obtain the total time threshold for the production to be controlled; then set the lower threshold of the status level for each production equipment type in the production equipment type matrix to be controlled and the number of maintenance personnel configured to obtain the set of lower threshold of equipment status levels and the set of the number of maintenance personnel for the equipment to be controlled;

[0038] S32. Adjust the set of lower threshold of equipment status levels in combination with the total time data for the overall production to be controlled, the set of the number of maintenance personnel for the equipment to be controlled, the set of stage time thresholds to be controlled, the set of final production equipment status level mapping models, the set of final production equipment maintenance time mapping equations, and the matrix of the set of production equipment parameter types to be controlled to obtain the set of final lower threshold of equipment status levels;

[0039] S33. Use the set of final lower threshold of equipment status levels in the actual production process of the product to be controlled;

[0040] Since there are time requirements for each stage in the production process, the time for each stage is preset in advance; when a production equipment fails, it needs to be shut down for maintenance; when the production equipment is in different status levels, the corresponding maintenance time is also different; by optimizing and adjusting the status level of each equipment during shutdown maintenance, the overall production cycle of the product to be controlled can be adjusted, making the overall production cycle of the product to be controlled shorter and improving the production efficiency.

[0041] Preferably, S32 includes the following steps:

[0042] S321. In combination with the production equipment type matrix to be controlled, set the current production stage and several types of production equipment in the current production stage to obtain the set of production equipment in the current stage;

[0043] In cooperation with the matrix of the parameter types of the production equipment to be controlled, the used time data of each production equipment in the current stage production equipment set and the average values of various types of parameters at multiple time points in the past usage are obtained in real time, so as to obtain the current used time data set and the equipment parameter matrix in the current stage; then, in cooperation with the final production equipment status level mapping model set, the used time data and the parameter data set of each production equipment in the current used time data set and the equipment parameter matrix in the current stage are input into the corresponding final production equipment status level mapping model for mapping, so as to obtain the real-time status level data set of the equipment in the current stage;

[0044] S322. In cooperation with the equipment status level lower limit threshold set, when there is equipment status level data in the real-time status level data set of the equipment in the current stage that is less than or equal to the corresponding equipment status level lower limit threshold, the production equipment corresponding to the equipment status level data is immediately shut down for maintenance according to the set of the number of maintenance personnel of the equipment to be controlled, and the corresponding shutdown maintenance time is calculated in cooperation with the final production equipment maintenance time mapping equation set; after the maintenance is completed, the used time data corresponding to the production equipment is set to 0; otherwise, no maintenance is required; after the current production stage ends, record the total time of the current production stage; use the sum value of the total time of the current production stage and the total time data of the production to be controlled as a whole to replace the total time data of the production to be controlled as a whole;

[0045] S323. After the current production stage ends, take the next stage of the current production stage as the current production stage and repeat S321 and S322 until the current production stage is the last production stage to be controlled in the set of production stages to be controlled;

[0046] S324. When the total time data of the production to be controlled as a whole is greater than or equal to the total time threshold of the production to be controlled, adjust the equipment status level lower limit threshold set until the total time data of the production to be controlled as a whole is less than the total time threshold of the production to be controlled, so as to obtain the final equipment status level lower limit threshold set; otherwise, use the equipment status level lower limit threshold set as the final equipment status level lower limit threshold set;

[0047] By obtaining the status level data of each production device in real time, it is determined whether the production device needs to be shut down for maintenance; the normal time-consuming data and shutdown maintenance data of each stage are added together, which is recorded as the actual time-consuming data of the entire production process, providing an adjustment direction for adjusting the status level data of the production device during shutdown maintenance in the future; among them, the final production device status level mapping model set is used to obtain the real-time status level data of each production device; the final production device maintenance time-consuming mapping equation set is used to calculate the time-consuming data required for shutting down and maintaining the production device at the current status level, so that the actual time-consuming data of the entire production process can be calculated.

[0048] Preferably, the adjustment of the lower limit threshold set of the device status level in S324 includes the following steps:

[0049] S3241. Set the value range of each device status level lower limit threshold in the lower limit threshold set of the device status level according to the actual situation to obtain the lower limit threshold value range set of the device status level As follows,

[0050]

[0051] Among them, respectively represent the lower limit and upper limit of the value of the i-th device status level lower limit threshold in the lower limit threshold set of the device status level;

[0052] Construct a manta ray population for adjusting the lower limit threshold of the device status level; set the maximum number of iterations of the manta ray population for adjusting the lower limit threshold of the device status level as and the current number of iterations as which are respectively recorded as the maximum number of iterations of the lower limit threshold and the current number of iterations of the lower limit threshold; the number of search space dimensions of the manta ray population for adjusting the lower limit threshold of the device status level is the same as b1;

[0053] S3242. Set the initial position of each manta ray in the manta ray population for adjusting the lower limit threshold of the device status level according to the lower limit threshold value range set of the device status level to obtain the second initial position matrix c′2; as follows,

[0054]

[0055] Among them, c′ 2ji represents the position component of the initial position of the j-th manta ray in the manta ray population for adjusting the lower limit threshold of the device status level on the i-th device status level dimension in the lower limit threshold set of the device status level, represents the scale of the manta ray population for adjusting the lower limit threshold of the device status level; the calculation formula of c′ 2ji is as follows,

[0056]

[0057] In the formula, ceil represents the ceiling function; rand 2ji represents a random number between 0 and 1 generated for c′ 2ji ;

[0058] S3243. Set the lower threshold of the device status level to adjust the fitness function c~2 of the manta ray population as follows

[0059]

[0060] In the formula, d′ represents the total production time data to be controlled corresponding to the set of lower thresholds of the device status level in S322 replaced by a set of lower thresholds of the device status level obtained in each iteration

[0061] S3244. Start the iteration. Before the iteration, set the current iteration number of the lower threshold to 1. In the first iteration process, use the lower threshold of the device status level to adjust the fitness function of the manta ray population Calculate the fitness value of the initial position of each manta ray in the second initial position matrix to obtain the third fitness value set; take the maximum fitness value in the third fitness value set and the corresponding initial position of the manta ray as the third global best fitness and the third global best position respectively; update the initial position of each manta ray in the second initial position matrix according to the third global best fitness and the third global best position; after the update is completed, add 1 to the current iteration number of the lower threshold and enter the next iteration

[0062] In each subsequent iteration process, use the lower threshold of the device status level to adjust the fitness function c~2 of the manta ray population to calculate the fitness value of the position of each manta ray in the manta ray population with the lower threshold of the device status level updated in the previous iteration process to obtain the fourth fitness value set; take the maximum fitness value in the fourth fitness value set and the corresponding position of the manta ray as the fourth global best fitness and the fourth global best position respectively; update the position of each manta ray in the manta ray population with the lower threshold of the device status level updated in the previous iteration process according to the fourth global best fitness and the fourth global best position; after the update is completed, add 1 to the current iteration number of the lower threshold and enter the next iteration

[0063] S3245. When Adjust the iteration to obtain the second final global best fitness and the second final global best position; otherwise, continue the iteration until ; take the second final global best fitness as the optimized total production time data to be controlled

[0064] When the overall total time-consuming data of the production to be controlled after optimization is less than the total time-consuming threshold of the production to be controlled, the adjustment is completed, and the second final global optimal position is used as the final lower threshold set of the equipment state level; otherwise, return to S3244 to continue the iteration until the overall total time-consuming data of the production to be controlled after optimization is less than the total time-consuming threshold of the production to be controlled;

[0065] The manta ray optimization algorithm only contains a small number of adjustable parameters, which makes it easy to understand and implement. It has a powerful global optimization ability, good adaptability and stability, and is suitable for dealing with practical problems that require specified precision; based on the above advantages, in this solution, the manta ray optimization algorithm is used to simultaneously perform multiple iterative adjustments on each equipment state level lower threshold in the equipment state level lower threshold set, and the overall time-consuming data of producing the product to be controlled is used as the fitness function. Therefore, as the iteration progresses, each equipment state level lower threshold obtained by the iteration makes the overall time-consuming data of producing the product to be controlled smaller and smaller, and finally controls the overall time-consuming data of producing the product to be controlled within the total time-consuming threshold of the production to be controlled, meeting the production requirements.

[0066] A production safety management system includes a production parameter setting module to be controlled, a digital twin model construction module for production equipment, a production equipment state level setting module, a historical production data collection module, a state level mapping model construction module, a maintenance time-consuming mapping equation construction module, an initial setting module for the lower threshold of the equipment state level, and an adjustment and optimization module for the lower threshold of the state.

[0067] The present invention has the following beneficial effects:

[0068] 1. In the present invention, the production process is controlled from the perspective of reducing the time required to produce the product to be controlled. Regarding the production equipment involved in the production process, when it reaches what state level for shutdown and maintenance operations, the time consumption for shutdown and maintenance is different when the production equipment reaches different state levels; therefore, this solution aims to adjust the state level data of the optimal shutdown time for each type of production equipment to minimize the overall time consumption for producing the product to be controlled.

[0069] 2. In the present invention, by setting several levels of production equipment, quantitative data values for measuring the current state of the production equipment are provided, which provides label data for constructing the final production equipment state level mapping model set later, and also provides a collection basis for collecting test data required for constructing the final production equipment maintenance time-consuming mapping equation set later.

[0070] 3. In the present invention, the lower threshold values of each device state level in the device state level lower threshold set are simultaneously adjusted iteratively multiple times by using the manta ray optimization algorithm, and the overall time-consuming data for producing the product to be controlled is used as the fitness function. Therefore, as the iteration progresses, each lower threshold value of the device state level obtained by iteration makes the overall time-consuming data for producing the product to be controlled smaller and smaller, and finally the overall time-consuming data for producing the product to be controlled is controlled within the total threshold of the time-consuming for the production to be controlled, meeting the production requirements.

[0071] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0073] Figure 1 It is a schematic diagram of the modules of a production safety management system according to the present invention;

[0074] Figure 2 It is a schematic flowchart of the process for constructing the final production equipment state level mapping model set and the final production equipment maintenance time-consuming mapping equation set in the present invention;

[0075] Figure 3 It is a schematic flowchart of a production control method based on digital twin according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0076] The technical solutions in the embodiments of the invention will be clearly and completely described below with reference to the drawings in the embodiments of the invention. Obviously, the described embodiments are only a part of the embodiments of the invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the invention without creative efforts belong to the scope of protection of the invention.

[0077] Embodiment 1

[0078] Please refer to Figure 2 and Figure 3 , this embodiment is a production control method based on digital twin, including the following steps:

[0079] S1. Set several production stages, corresponding production equipment types, and corresponding equipment parameter types when producing the product to be controlled, to obtain the set of production stages to be controlled, the matrix of production equipment types to be controlled, and the matrix of production equipment parameter types to be controlled;

[0080] The S1 includes the following steps:

[0081] S11. Set the product to be controlled in production; set several production stages when producing the product to be controlled, to obtain the set of production stages to be controlled; set the production equipment types and corresponding equipment parameter types involved in each production stage in the set of production stages to be controlled, to obtain the matrix of production equipment types to be controlled and the matrix of production equipment parameter types to be controlled; the product to be controlled in production is preferably a safety helmet; taking the production process of a safety helmet as an example, the set of production stages to be controlled includes injection molding stage, assembly stage, grinding and polishing stage, printing and spraying stage, quality inspection stage, and packaging stage, etc.; the matrix of production equipment types to be controlled includes injection molding machines, presses, vacuum forming machines, laser engraving machines, and corresponding product performance testing equipment, etc.; the matrix of production equipment parameter types to be controlled includes parameter types of injection molding machines, such as injection pressure, injection temperature, and cooling time, etc.; parameter types of presses, such as pressure, temperature, pressing time; parameter types of vacuum forming machines, such as vacuum degree, heating temperature, forming time, etc.; parameter types of laser engraving machines, such as laser power, engraving speed, etc.; parameter types of product testing equipment (taking the safety helmet testing equipment as an example), such as impact drop hammer mass, puncture drop hammer mass, drop hammer height, etc.;

[0082] S12. Match the set of production stages to be controlled, the matrix of production equipment types to be controlled, and the matrix of production equipment parameter types to be controlled, collect parameter data of various types of production equipment in several groups of historical production processes, to obtain the set of historical production equipment parameter data matrices; construct a digital twin model for each production equipment according to the set of historical production equipment parameter data matrices, to obtain the set of digital twin models of production equipment to be controlled;

[0083] The steps of constructing a digital twin model for each production equipment according to the set of historical production equipment parameter data matrices in S12 to obtain the set of digital twin models of production equipment to be controlled include the following steps:

[0084] S121. Remove the noise data in the set of historical production equipment parameter data matrices, such as abnormally high or low values caused by sensor failures, to obtain the set of historical production equipment parameter data matrices after denoising;

[0085] S122. Fill in the missing values in the denoised historical production equipment parameter data matrix set. Methods such as mean filling and interpolation method (such as linear interpolation) can be used to ensure the integrity of the data, and the filled historical production equipment parameter data matrix set is obtained;

[0086] S123. Perform data standardization processing on the filled historical production equipment parameter data matrix set. After the processing is completed, the final historical production equipment parameter data matrix set is obtained; construct a digital twin model for each production equipment according to the final historical production equipment parameter data matrix set, and obtain the digital twin model set of the production equipment to be controlled;

[0087] S2. According to the production equipment type matrix to be controlled and the production equipment parameter type set matrix to be controlled, collect several groups of historical data on the current used time, various types of production equipment parameter data, corresponding maintenance personnel data and maintenance time data, and corresponding production equipment status level data for each production equipment type to be controlled, and obtain the historical production equipment parameter data matrix set, the historical production equipment used time data matrix, the historical production equipment status level data matrix, the historical maintenance personnel quantity matrix and the historical maintenance time data matrix; and construct the final production equipment status level mapping model set and the final production equipment maintenance time mapping equation set;

[0088] The said S2 includes the following steps:

[0089] S21. Set several equipment status levels for each production equipment in the production equipment type matrix to be controlled, and obtain the production equipment status level set; the production equipment status levels in the production equipment status level set are represented by positive integers. The larger the value of the production equipment status level, the better the state of the production equipment, and it can continue to work for a longer time. The determination of the production equipment status level can be based on the current wear degree of the production equipment;

[0090] In cooperation with the digital twin model set of the production equipment to be controlled, the production equipment type matrix to be controlled, the production equipment status level set and the production equipment parameter type set matrix to be controlled, collect several groups of historical data on the current used time, various types of production equipment parameter data and corresponding production equipment status level data for each production equipment type to be controlled, and obtain the historical production equipment parameter data matrix set, the historical production equipment used time data matrix, and the historical production equipment status level data matrix a - 1;

[0091] S22. Collect the maintenance personnel data and corresponding time data required to repair each production equipment status level data in the historical production equipment status level data matrix to the corresponding initial production equipment status level data, and obtain the historical maintenance personnel quantity matrix and the historical maintenance time-consuming data matrix are as follows,

[0092]

[0093] wherein, respectively represent the status level data of the j-th type of production equipment in the i-th group of historical data collected, the number of personnel used for its maintenance, and the time-consuming data for its maintenance; b1 represents the total number of production equipment types involved in the production equipment type matrix to be controlled; b2 represents the total number of groups of historical data on the time consumed for its current use, various types of production equipment parameter data, and the corresponding production equipment status level data in S21;

[0094] Construct a final production equipment status level mapping model set according to the historical production equipment parameter data matrix set, the historical production equipment used time-consuming data matrix, and the historical production equipment status level data matrix;

[0095] The steps of constructing a final production equipment status level mapping model set in S22 according to the historical production equipment parameter data matrix set, the historical production equipment used time-consuming data matrix, and the historical production equipment status level data matrix are as follows:

[0096] S221. For each type of production equipment, construct a corresponding initial SVM model and set the training data ratio to obtain an initial SVM model set; divide the historical production equipment parameter data matrix set, the historical production equipment used time-consuming data matrix, and the historical production equipment status level data matrix according to the training data ratio to obtain a historical production equipment parameter training data matrix set, a historical production equipment used time-consuming training data matrix, a historical production equipment status level training data matrix, a historical production equipment parameter test data matrix set, a historical production equipment used time-consuming test data matrix, and a historical production equipment status level test data matrix;

[0097] S222. Set a corresponding training error threshold for each of the initial SVM models to obtain a training error threshold set; use the historical production equipment parameter training data matrix set and the historical production equipment used time-consuming training data matrix as training data, and use the historical production equipment status level training data matrix as training labels, and input them into the corresponding initial SVM models in the initial SVM model set for training respectively; during the training process, when the training error is less than the corresponding training error threshold in the training error threshold set, stop training; otherwise, continue training; when each initial SVM model is trained, obtain a trained SVM model set;

[0098] S223. Set a corresponding test accuracy threshold for each of the initial SVM models to obtain a set of test accuracy thresholds; use the historical production equipment parameter test data matrix set, the historical production equipment used time test data matrix as test data, and the historical production equipment status level test data matrix as test labels, and input them into the corresponding trained SVM models in the trained SVM model set for testing respectively; after the testing is completed, obtain a test accuracy data set; when there is test accuracy data in the test accuracy data set that is less than the corresponding test accuracy threshold in the test accuracy threshold set, return the trained SVM model corresponding to the test accuracy data to S222 for continued training until there is no test accuracy data in the test accuracy data set that is less than the corresponding test accuracy threshold in the test accuracy threshold set, and obtain the final production equipment status level mapping model set; otherwise, use the trained SVM model set as the final production equipment status level mapping model set;

[0099] S23. Construct a set of final production equipment maintenance time mapping equations according to the production equipment status level data, the historical maintenance personnel quantity matrix, and the historical maintenance time data matrix;

[0100] S23 includes the following steps:

[0101] S231. Construct an initial set of production equipment maintenance time mapping equations \(a = \{a_1,...,a_{i},...,a_{a'}\}\), where \(a_{i}\) represents the initial production equipment maintenance time mapping equation set for the \(i\)-th type of production equipment in the matrix of the set of production equipment parameter types to be controlled, \(a'\) represents the total number of production equipment types in the matrix of the set of production equipment parameter types to be controlled, and the total number of production equipment types in the matrix of the set of production equipment parameter types to be controlled is the same as the total number of the set of initial production equipment maintenance time mapping equations set; \(a_{i}\) is as follows, i ,...,a a′},a i represents the initial production equipment maintenance time mapping equation set for the \(i\)-th type of production equipment in the matrix of the set of production equipment parameter types to be controlled, \(a'\) represents the total number of production equipment types in the matrix of the set of production equipment parameter types to be controlled, and the total number of production equipment types in the matrix of the set of production equipment parameter types to be controlled is the same as the total number of the set of initial production equipment maintenance time mapping equations set; \(a i is as follows,

[0102]

[0103] In the formula, is the dependent variable, representing the maintenance time data; represents the mapping relationship of \(a i ; are all independent variables, representing the number of maintenance personnel and the equipment status level data before maintenance respectively;

[0104] S232. Combine with the initial production equipment maintenance time mapping equation set, and substitute each data in the historical production equipment status level data matrix and the historical maintenance personnel quantity matrix into the corresponding initial production equipment maintenance time mapping equation for mapping respectively to obtain the historical maintenance time initial mapping data matrix. As follows,

[0105]

[0106] Among them, represents the initial mapping data obtained by inputting into the j-th initial production equipment maintenance time mapping equation in the initial production equipment maintenance time mapping equation set for mapping;

[0107] S233. Set the maintenance time mapping error threshold; calculate the error data between the corresponding column data in the historical maintenance time initial mapping data matrix and the historical maintenance time data matrix to obtain the historical maintenance time mapping error data set c = {c1,..., c j ,..., c b1}, where c j represents the error data between the j-th column data in the historical maintenance time initial mapping data matrix and the historical maintenance time data matrix; the calculation formula is as follows,

[0108]

[0109] When there is historical maintenance time mapping error data greater than or equal to the maintenance time mapping error threshold in the historical maintenance time mapping error data set, adjust the initial production equipment maintenance time mapping equation corresponding to the historical maintenance time mapping error data until there is no historical maintenance time mapping error data greater than or equal to the maintenance time mapping error threshold in the historical maintenance time mapping error data set, and obtain the final production equipment maintenance time mapping equation set; otherwise, take the initial production equipment maintenance time mapping equation set as the final production equipment maintenance time mapping equation set;

[0110] The adjustment of the initial production equipment maintenance time mapping equation corresponding to the historical maintenance time mapping error data in S233 includes the following steps:

[0111] S2331. Denote the initial production equipment maintenance time mapping equation corresponding to the historical maintenance time mapping error data as the production equipment maintenance time mapping equation to be adjusted; set the value range of each constant parameter in the production equipment maintenance time mapping equation to be adjusted to obtain the constant parameter value range set As follows,

[0112]

[0113] Among them, respectively represent the lower limit and the upper limit of the value of the i-th constant parameter in the mapping equation of the maintenance time of the production equipment to be adjusted, and b1' represents the total number of constant parameters in the mapping equation of the maintenance time of the production equipment to be adjusted;

[0114] Construct a manta ray population for adjusting the mapping of the maintenance time of production equipment; set the maximum number of iterations of the manta ray population for adjusting the mapping of the maintenance time of production equipment as and the current number of iterations as which are respectively recorded as the maximum number of iterations of the maintenance time and the current number of iterations of the maintenance time; the number of dimensions of the search space of the manta ray population for adjusting the mapping of the maintenance time of production equipment is the same as b1';

[0115] S2332. Set the initial position of each manta ray in the manta ray population for adjusting the mapping of the maintenance time of production equipment according to the set of value intervals of the constant parameters to obtain the first initial position matrix c1'; as follows,

[0116]

[0117] Among them, c1' ji represents the position component of the initial position of the j-th manta ray in the manta ray population for adjusting the mapping of the maintenance time of production equipment in the i-th constant parameter dimension of the mapping equation of the maintenance time of the production equipment to be adjusted, represents the scale of the manta ray population for adjusting the mapping of the maintenance time of production equipment; the calculation formula of c1' ji is as follows,

[0118]

[0119] Among them, rand 1ji represents a random number between 0 and 1 generated for c1' ji ;

[0120] S2333. Set the fitness function c~1 of the manta ray population for adjusting the mapping of the maintenance time of production equipment; as follows,

[0121]

[0122] In the formula, d represents the error between the mapping data obtained by substituting a set of constant parameters obtained in each iteration into the mapping equation of the maintenance time of the production equipment to be adjusted and then substituting each data in the historical production equipment status level data matrix and the historical maintenance personnel number matrix in S232 into the mapping equation of the maintenance time of the production equipment to be adjusted for mapping and the actual data;

[0123] S2334. Start iteration. Before iteration, set the current iteration number of the maintenance time to 1. During the first round of iteration, use the production equipment maintenance time mapping to adjust the fitness function of the manta ray population. Calculate the fitness values of the initial positions of each manta ray in the first initial position matrix to obtain the first fitness value set. Take the maximum fitness value in the first fitness value set and the corresponding initial position of the manta ray as the first global best fitness and the first global best position respectively. Update the initial positions of each manta ray in the first initial position matrix according to the first global best fitness and the first global best position. After the update is completed, increment the current iteration number of the maintenance time by 1 and enter the next round of iteration.

[0124] During each subsequent round of iteration, use the production equipment maintenance time mapping to adjust the fitness function c of the manta ray population. Calculate the fitness values of the positions of each manta ray in the manta ray population adjusted by the production equipment maintenance time mapping updated in the previous round of iteration to obtain the second fitness value set. Take the maximum fitness value in the second fitness value set and the corresponding position of the manta ray as the second global best fitness and the second global best position respectively. Update the positions of each manta ray in the manta ray population adjusted by the production equipment maintenance time mapping updated in the previous round of iteration according to the second global best fitness and the second global best position. After the update is completed, increment the current iteration number of the maintenance time by 1 and enter the next round of iteration.

[0125] S2335. When Stop iteration to obtain the first final global best fitness and the first final global best position; otherwise, continue iteration until Take the first final global best fitness as the optimized historical maintenance time mapping error data. When the optimized historical maintenance time mapping error data is less than the maintenance time mapping error threshold, substitute each position component of the first final global best position into the production equipment maintenance time mapping equation to be adjusted to obtain the adjusted production equipment maintenance time mapping equation. Replace the corresponding initial production equipment maintenance time mapping equation in the initial production equipment maintenance time mapping equation set with the adjusted production equipment maintenance time mapping equation, and the adjustment is completed; otherwise, return to S2334 to continue iteration until the optimized historical maintenance time mapping error data is less than the maintenance time mapping error threshold.

[0126] By using the manta ray optimization algorithm to iteratively adjust multiple constant parameters of the mapping equation of the maintenance time of the production equipment to be adjusted simultaneously, and using the error between the mapping data and the actual data of the mapping equation of the maintenance time of the production equipment to be adjusted as the fitness function; therefore, as the iteration progresses, the error between the mapping data and the actual data of the mapping equation of the maintenance time of the production equipment to be adjusted becomes smaller and smaller, and finally meets the mapping requirements;

[0127] S3. Set the lower threshold of the status level of each production equipment according to the matrix of the types of production equipment to be controlled, and obtain the set of lower thresholds of the equipment status level;

[0128] Adjust the set of lower thresholds of the equipment status level according to the final set of production equipment status level mapping models, the final set of production equipment maintenance time mapping equations, the set of production stages to be controlled, the matrix of the types of production equipment to be controlled, and the matrix of the types of production equipment parameters to be controlled, so as to obtain the final set of lower thresholds of the equipment status level, and minimize the overall time consumption of the production products to be controlled;

[0129] The said S3 includes the following steps:

[0130] S31. Set the total time threshold of all stages in the set of production stages to be controlled and the overall total time consumption data of the production to be controlled, and obtain the total time threshold of the production to be controlled; then set the lower threshold of the status level of each type of production equipment in the matrix of the types of production equipment to be controlled and the number of maintenance personnel configured, and obtain the set of lower thresholds of the equipment status level and the set of the number of maintenance personnel of the production equipment to be controlled;

[0131] S32. Cooperate with the overall total time consumption data of the production to be controlled, the set of the number of maintenance personnel of the production equipment to be controlled, the set of stage time thresholds to be controlled, the final set of production equipment status level mapping models, the final set of production equipment maintenance time mapping equations, and the matrix of the types of production equipment parameters to be controlled, and adjust the set of lower thresholds of the equipment status level to obtain the final set of lower thresholds of the equipment status level;

[0132] The said S32 includes the following steps:

[0133] S321. Cooperate with the matrix of the types of production equipment to be controlled, set the current production stage and several types of production equipment in the current production stage, and obtain the set of production equipment in the current stage;

[0134] In coordination with the matrix of the parameter types of the production equipment to be controlled, the used time data of each production equipment in the current-stage production equipment set is obtained in real time, as well as the average values of various types of parameters at multiple time points in the past usage situation, so as to obtain the current used time data set and the equipment parameter matrix in the current stage; then, in coordination with the final production equipment status level mapping model set, the used time data and the parameter data set of each production equipment in the current used time data set and the equipment parameter matrix in the current stage are input into the corresponding final production equipment status level mapping model for mapping, so as to obtain the real-time status level data set of the equipment in the current stage;

[0135] S322. In coordination with the equipment status level lower limit threshold set, when there is equipment status level data in the real-time status level data set of the equipment in the current stage that is less than or equal to the corresponding equipment status level lower limit threshold, the production equipment corresponding to the equipment status level data is immediately shut down for maintenance according to the set of the number of maintenance personnel for the equipment to be controlled, and the corresponding shutdown maintenance time is calculated in coordination with the final production equipment maintenance time mapping equation set; after the maintenance is completed, the used time data corresponding to the production equipment is set to 0; otherwise, no maintenance is required; after the current production stage ends, record the total time of the current production stage; use the added value of the total time of the current production stage and the total time data of the production to be controlled as a whole to replace the total time data of the production to be controlled as a whole;

[0136] S323. After the current production stage ends, take the next stage of the current production stage as the current production stage and repeat S321 and S322 until the current production stage is the last to-be-controlled production stage in the to-be-controlled production stage set;

[0137] S324. When the total time data of the production to be controlled as a whole is greater than or equal to the total time threshold of the production to be controlled, adjust the equipment status level lower limit threshold set until the total time data of the production to be controlled as a whole is less than the total time threshold of the production to be controlled, so as to obtain the final equipment status level lower limit threshold set; otherwise, use the equipment status level lower limit threshold set as the final equipment status level lower limit threshold set;

[0138] The adjustment of the equipment status level lower limit threshold set in S324 includes the following steps:

[0139] S3241. Set the value range of each equipment status level lower limit threshold in the equipment status level lower limit threshold set according to the actual situation to obtain the equipment status level lower limit threshold value range set As follows,

[0140]

[0141] Among them, respectively represent the lower limit value and the upper limit value of the i-th lower threshold of the device status level threshold set;

[0142] Construct a manta ray population for adjusting the lower threshold of the device status level; set the maximum number of iterations of the manta ray population for adjusting the lower threshold of the device status level to be and the current number of iterations to be which are respectively recorded as the maximum number of iterations of the lower threshold and the current number of iterations of the lower threshold; the number of search space dimensions of the manta ray population for adjusting the lower threshold of the device status level is the same as b1;

[0143] S3242. Set the initial position of each manta ray in the manta ray population for adjusting the lower threshold of the device status level according to the value range set of the lower threshold of the device status level, and obtain the second initial position matrix c′2; as follows,

[0144]

[0145] where c′ 2ji represents the position component of the initial position of the j-th manta ray in the manta ray population for adjusting the lower threshold of the device status level on the i-th device status level dimension in the lower threshold set of the device status level, represents the scale of the manta ray population for adjusting the lower threshold of the device status level; the calculation formula of c′ 2ji is as follows,

[0146]

[0147] In the formula, ceil represents the rounding function; rand 2ji represents a random number between 0 and 1 generated for c′ 2ji ;

[0148] S3243. Set the fitness function of the manta ray population for adjusting the lower threshold of the device status level as follows,

[0149]

[0150] In the formula, d′ represents the total data of the overall production to be controlled corresponding to replacing the lower threshold set of the device status level in S322 with a set of lower thresholds of the device status level obtained in each round of iteration;

[0151] S3244. Start the iteration. Before the iteration, set the current number of iterations of the lower threshold to 1; in the first round of iteration, use the fitness function of the manta ray population for adjusting the lower threshold of the device status level Calculate the fitness value of the initial position of each manta ray in the second initial position matrix to obtain a third set of fitness values; take the maximum fitness value in the third set of fitness values and the corresponding initial position of the manta ray as the third global best fitness and the third global best position respectively; update the initial position of each manta ray in the second initial position matrix according to the third global best fitness and the third global best position; after the update is completed, increment the current iteration count of the lower limit threshold by 1 and enter the next iteration;

[0152] In each other iteration process, use the lower limit threshold of the equipment status level to adjust the fitness function c~2 of the manta ray population. Calculate the fitness value of the position of each manta ray in the manta ray population adjusted by the lower limit threshold of the equipment status level updated in the previous iteration process to obtain a fourth set of fitness values; take the maximum fitness value in the fourth set of fitness values and the corresponding position of the manta ray as the fourth global best fitness and the fourth global best position respectively; update the position of each manta ray in the manta ray population adjusted by the lower limit threshold of the equipment status level updated in the previous iteration process according to the fourth global best fitness and the fourth global best position; after the update is completed, increment the current iteration count of the lower limit threshold by 1 and enter the next iteration;

[0153] S3245. When Adjust the iteration to obtain the second final global best fitness and the second final global best position; otherwise, continue the iteration until Stop; take the second final global best fitness as the optimized overall total time-consuming data to be controlled for production;

[0154] When the optimized overall total time-consuming data to be controlled for production is less than the total time-consuming threshold to be controlled for production, the adjustment is completed, and take the second final global best position as the final set of lower limit thresholds for the equipment status level; otherwise, return to S3244 to continue the iteration until the optimized overall total time-consuming data to be controlled for production is less than the total time-consuming threshold to be controlled for production;

[0155] S33. Use the final set of lower limit thresholds for the equipment status level in the actual production process of the product to be controlled for production.

[0156] Embodiment 2

[0157] Please refer to Figure 1 , this embodiment discloses a production safety management system. The system can implement the method of the above embodiment, including a production parameter setting module to be controlled, a digital twin model construction module for production equipment, a production equipment status level setting module, a historical production data collection module, a status level mapping model construction module, a maintenance time-consuming mapping equation construction module, an initial setting module for the lower limit threshold of the equipment status level, and an adjustment and optimization module for the lower limit threshold of the status;

[0158] The to-be-controlled production parameter setting module is used to set several production stages, corresponding production equipment types involved, and corresponding equipment parameter types during the production of the to-be-controlled production product, so as to obtain a to-be-controlled production stage set, a to-be-controlled production equipment type matrix, and a to-be-controlled production equipment parameter type set matrix;

[0159] The production equipment digital twin model construction module is used to collect parameter data of various types of production equipment in several groups of historical production processes and construct corresponding digital twin models according to the to-be-controlled production stage set, the to-be-controlled production equipment type matrix, and the to-be-controlled production equipment parameter type set matrix, so as to obtain a to-be-controlled production equipment digital twin model set;

[0160] The production equipment status level setting module is used to set several equipment status levels for each production equipment in the to-be-controlled production equipment type matrix to obtain a production equipment status level set;

[0161] The historical production data collection module is used to collect several groups of historical current usage time data, various types of production equipment parameter data, corresponding maintenance personnel data and maintenance time data, and corresponding production equipment status level data for each to-be-controlled production equipment type according to the to-be-controlled production equipment digital twin model set, the to-be-controlled production equipment type matrix, the production equipment status level set, and the to-be-controlled production equipment parameter type set matrix, so as to obtain a historical production equipment parameter data matrix set, a historical production equipment used time data matrix, a historical production equipment status level data matrix, a historical maintenance personnel quantity matrix, and a historical maintenance time data matrix;

[0162] The status level mapping model construction module is used to construct a final production equipment status level mapping model set by using the historical production equipment parameter data matrix set, the historical production equipment used time data matrix, and the historical production equipment status level data matrix;

[0163] The maintenance time mapping equation construction module is used to construct a final production equipment maintenance time mapping equation set by using the historical production equipment status level data matrix, the historical maintenance personnel quantity matrix, and the historical maintenance time data matrix;

[0164] The equipment status level lower limit threshold initial setting module is used to set the equipment status level lower limit threshold for each production equipment according to the to-be-controlled production equipment type matrix to obtain an equipment status level lower limit threshold set;

[0165] The state lower limit threshold adjustment and optimization module is used to adjust the set of lower limit thresholds of the equipment state level according to the final production equipment state level mapping model set, the final production equipment maintenance time mapping equation set, the production stage set to be controlled, the matrix of types of production equipment to be controlled, and the matrix of types of production equipment parameter types to be controlled, so as to obtain the set of final lower limit thresholds of the equipment state level, minimizing the overall time consumption of the production products to be controlled.

[0166] In the description of this specification, the description with reference to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0167] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not elaborate all the details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principle and practical application of the invention, so that those skilled in the art can understand and utilize the invention well.

Claims

1. A production control method based on digital twins, characterized in that: The following steps are involved: S1. Set the types of production equipment and the corresponding equipment parameter types involved in several production stages when producing the product to be controlled, and obtain a matrix of production equipment types to be controlled and a matrix of production equipment parameter types to be controlled; S2. According to the production equipment type matrix to be controlled and the production equipment parameter type set matrix to be controlled, for each type of production equipment to be controlled, collect several groups of historical current usage time data, various types of production equipment parameter data, corresponding maintenance personnel data and maintenance time data, and corresponding production equipment status level data, to obtain a historical production equipment parameter data matrix set, a historical production equipment usage time data matrix, a historical production equipment status level data matrix, a historical maintenance personnel number matrix, and a historical maintenance time data matrix; and construct a final production equipment status level mapping model set and a final production equipment maintenance time mapping equation set; S3. According to the production equipment type matrix to be controlled, set the lower limit threshold of the status level of each production equipment to obtain the lower limit threshold set of the equipment status level; According to the final production equipment status level mapping model set, the final production equipment maintenance time mapping equation set, the production equipment type matrix to be controlled and the production equipment parameter type set matrix to be controlled, the equipment status level lower limit threshold set is adjusted to obtain the final equipment status level lower limit threshold set, so that the overall time consumption of the production products to be controlled is minimized.

2. A production control method based on digital twin according to claim 1, characterized in that: The S1 comprises the following steps: S11, setting the production products to be controlled; setting the production equipment types and corresponding equipment parameter types involved in each production stage, and obtaining a production equipment type matrix to be controlled and a production equipment parameter type set matrix to be controlled; the production products to be controlled are preferably safety helmets; S12. In conjunction with the production equipment type matrix to be controlled and the production equipment parameter type set matrix to be controlled, collect several groups of parameter data of various types of production equipment in the historical production process to obtain a matrix set of historical production equipment parameter data; construct a digital twin model of each type of production equipment based on the historical production equipment parameter data matrix set to obtain a digital twin model set of production equipment to be controlled.

3. A production control method based on digital twin according to claim 2, characterized in that: The S2 comprises the following steps: S21, setting a number of equipment status levels for each type of production equipment in the production equipment type matrix to be controlled, and obtaining a production equipment status level set; In conjunction with the digital twin model set of the production equipment to be controlled, the production equipment type matrix to be controlled, the production equipment status level set and the production equipment parameter type set matrix to be controlled, for each type of production equipment to be controlled, several groups of historical current time consumption data, various types of production equipment parameter data and corresponding production equipment status level data are collected to obtain a historical production equipment parameter data matrix set, a historical production equipment time consumption data matrix and a historical production equipment status level data matrix; S22, collecting maintenance personnel data and corresponding time consumption data required to maintain the production equipment corresponding to each production equipment status level data in the historical production equipment status level data matrix to the corresponding initial production equipment status level data, and obtaining a historical maintenance personnel quantity matrix and a historical maintenance time consumption data matrix; Constructing a final production equipment status level mapping model set according to the historical production equipment parameter data matrix set, the historical production equipment usage time data matrix, and the historical production equipment status level data matrix; S23, constructing a final production equipment maintenance time mapping equation set according to the production equipment status level data, the historical maintenance personnel quantity matrix and the historical maintenance time data matrix.

4. A production control method based on digital twin according to claim 3, characterized in that: The S23 comprises the following steps: S231, constructing a set of initial production equipment maintenance time mapping equations; S232, in conjunction with the initial production equipment maintenance time mapping equation set, each data in the historical production equipment status level data matrix and the historical maintenance personnel quantity matrix is ​​respectively combined and substituted into the corresponding initial production equipment maintenance time mapping equation for mapping, to obtain the initial mapping data matrix of the historical maintenance time; S233, setting a maintenance time mapping error threshold; calculating the error data between the historical maintenance time initial mapping data matrix and the corresponding column data in the historical maintenance time data matrix, to obtain a historical maintenance time mapping error data set; According to the historical maintenance time mapping error data set and the maintenance time mapping error threshold, the initial production equipment maintenance time mapping equation corresponding to the corresponding historical maintenance time mapping error data is adjusted to obtain the final production equipment maintenance time mapping equation set.

5. A production control method based on digital twin according to claim 4, characterized in that: In S233, the initial production equipment maintenance time mapping equation corresponding to the corresponding historical maintenance time mapping error data is adjusted using the manta ray optimization algorithm.

6. A production control method based on digital twin according to claim 5, characterized in that: The S3 comprises the following steps: S31, setting the total time consumption threshold of all stages and the overall total time consumption data of the production to be controlled, and obtaining the total time consumption threshold of the production to be controlled; then setting the lower limit threshold of the state level of each type of production equipment in the production equipment type matrix to be controlled and the number of maintenance personnel configured, and obtaining the lower limit threshold set of the equipment state level and the number set of maintenance personnel for the equipment to be controlled; and then adjusting the lower limit threshold set of the equipment state level in conjunction with the final production equipment state level mapping model set, the final production equipment maintenance time consumption mapping equation set and the production equipment parameter type set matrix to be controlled, and obtaining the final equipment state level lower limit threshold set; S32: Using the final equipment status level lower limit threshold set in the actual production process of the product to be controlled.

7. A production control method based on digital twin according to claim 6, characterized in that: The S32 comprises the following steps: S311. In conjunction with the production equipment type matrix to be controlled, set the current production stage and several types of production equipment in the current production stage to obtain the current stage production equipment set; and obtain in real time the time consumption data of each production equipment in the current stage production equipment set and the average values ​​of various types of parameters at multiple time points in the past, obtain the current time consumption data set and the current stage equipment parameter matrix, input them into the corresponding final production equipment status level mapping model for mapping, and obtain the current stage equipment real-time status level data set; S312, cooperate with the lower limit threshold set of the equipment status level and the real-time status level data set of the equipment in the current stage to shut down the corresponding production equipment for maintenance; then calculate the corresponding shutdown maintenance time according to the final production equipment maintenance time mapping equation set; after the maintenance is completed, set the used time data corresponding to the production equipment to 0; after the current production stage is completed, record the total time of the current production stage; use the sum of the total time of the current production stage and the total time data of the overall production to be controlled to replace the total time data of the overall production to be controlled; S313, after the current production stage ends, the next stage of the current production stage is used as the current production stage and S311 and S312 are repeated until the current production stage is the last production stage to be controlled; S314. According to the overall total time consumption data of the production to be controlled and the total time consumption threshold of the production to be controlled, the lower limit threshold set of the equipment status level is adjusted to obtain a final lower limit threshold set of the equipment status level.

8. A production control method based on digital twin according to claim 7, characterized in that: The step of adjusting the lower threshold set of the device status level in S314 includes the following steps: S3141, constructing a lower limit threshold of the device status level to adjust the manta ray population; setting the maximum number of iterations of the lower limit threshold of the device status level to adjust the manta ray population is And the current number of iterations is S3142, setting a lower limit threshold of the device status level to adjust the initial position of each manta ray in the manta ray population, and obtaining a second initial position matrix; and then setting the lower limit threshold of the device status level to adjust the fitness function of the manta ray population; S3143, start iteration, and before iteration, set the current iteration number of the lower threshold to 1; in each round of iteration, use the lower threshold of the device status level to adjust the fitness function of the manta ray population, calculate the fitness value of the position of each manta ray in the manta ray population by using the lower threshold of the device status level updated in the previous round of iteration, and update the position of each manta ray; S3144, when When , adjust the iteration to obtain the second final global optimal fitness and the second final global optimal position; otherwise, continue to iterate until The second final global optimal fitness is used as the total time-consuming data of the overall production to be controlled after optimization; When the optimized total time consumption data of the production to be controlled is less than the total time consumption threshold of the production to be controlled, the adjustment is completed; otherwise, return to S3143 to continue iteration.

9. A production safety management system that implements a production control method based on digital twins as described in any one of claims 1 to 8.

Images