Data management system and method based on intelligent manufacturing production process of steel pipe

Through genetic algorithms and order decomposition technology, the scheduling system of steel pipe manufacturing is optimized, the problem of low unit utilization is solved, scheduling efficiency and production flexibility are improved, and a more efficient steel pipe manufacturing process is achieved.

CN118521143BActive Publication Date: 2024-11-15宝信软件(南京)有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411001478.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-15
Estimated Expiration
2044-07-25

AI Technical Summary

Technical Problem

The existing scheduling systems have the problem of low unit utilization in steel pipe manufacturing. The strict upstream and downstream feeding relationships lead to the inability to fully operate some processes, and the different processing speeds lead to low scheduling efficiency.

Method used

Using an intelligent manufacturing production process data management system based on genetic algorithms, by obtaining order data, determining the fitness function, performing the first scheduling and process decomposition, performing secondary optimization based on unit utilization, and inserting the next order process to improve Utilization rate of time to wait for material.

Benefits of technology

It improves the utilization rate and scheduling efficiency of the unit, provides scientific planning and decision-making basis, and enhances production flexibility and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118521143B_ABST
    Figure CN118521143B_ABST
Patent Text Reader

Abstract

The present invention discloses a data management system and method based on intelligent manufacturing production process of steel pipes, and relates to the technical field of manufacturing production process data management, including obtaining order data, wherein the order data includes order quantity and order completion time requirement; determining a first fitness function based on the order completion time requirement, and using a genetic algorithm to schedule the order for the first time; decomposing the order into process steps, and performing secondary optimization on the process steps based on the unit utilization rate; producing and processing the product based on the second scheduling result; the present invention combines the parameter configuration of the genetic algorithm, uses the genetic algorithm, schedules the orders of the workshop, and provides a scientific basis for planning decisions; linearly transforms the fitness of the genetic algorithm to control the number of copies of the individual with the largest fitness in the next generation; decomposes the order according to the process, inserts the process of the next order in the process of waiting for materials, improves the utilization rate of the mechanism, and thus improves the scheduling efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of manufacturing production process data management, and in particular to a management system and method for intelligent manufacturing production process data of steel pipes. Background Art

[0002] With the continuous development of the manufacturing industry, multi-pass processing is widely used in many industries, such as steel pipe manufacturing. Multi-pass processing realizes the gradual shaping and improvement of products through a series of continuous or intermittent processing steps. This processing method can meet the requirements of complex product shapes and high precision. The existing scheduling system often requires the unit to have a strict upstream and downstream feeding relationship. Each process is strictly dependent on the materials or semi-finished products provided by the previous process, and its output is strictly provided to the next process on time. However, the price speed of each process is different, so there is a problem that some processes cannot be fully operated; therefore, how to improve the utilization rate of the processing unit and improve the efficiency of scheduling has become an urgent problem to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a data management system and method based on intelligent manufacturing production process of steel pipes to solve the problems raised in the above background technology.

[0004] In one aspect of the present invention, a method for managing production process data based on intelligent manufacturing of steel pipes is provided, comprising:

[0005] S11, obtaining order data, wherein the order data includes order quantity and order completion time requirement;

[0006] S12, determining a first fitness function based on the order completion time requirement, and using a genetic algorithm to schedule the order for the first time;

[0007] S13, decomposing the order into process steps, and performing secondary optimization on the process steps based on the unit utilization rate;

[0008] S14, the unit produces and processes the products based on the second scheduling results.

[0009] In step S12, the first fitness function is determined based on the order completion time requirement, and the first scheduling of the order using the genetic algorithm also includes the following steps:

[0010] S21, set the initial population size, crossover probability, mutation probability and the upper limit of the number of iterations; obtain historical order information, and determine the time required to complete each existing order and the mold change time between processing different existing orders based on the historical order information and existing order data, and encode the task based on the time required to complete each existing order, the mold change time between processing different existing orders and the order completion time requirements, and generate an initial population;

[0011] S22, calculate the fitness of each chromosome in the initial population and perform linear transformation;

[0012] S23, select chromosomes according to their fitness to obtain a new population;

[0013] S24, perform crossover and mutation operations on the new population; discard chromosomes that do not meet the constraints;

[0014] S25, return to step S21 until the number of iterations reaches a preset upper limit.

[0015] The fitness F is calculated by the following formula:

[0016] , where The time required to complete the order. The time required to complete the order, is the order delay time, a and b are the evaluation coefficients of order delivery time and the time required to complete the order, and c is the penalty coefficient of order delay time.

[0017] Since contract delays involve customer compensation, users pay more attention to contract delays, so the order delay time is added to the adaptability. , and set the corresponding penalty coefficient.

[0018] The fitness F is linearly transformed by the following steps:

[0019] , α is the linear transformation coefficient, β is the bias, α and β are determined by the following steps:

[0020] , is the ratio of the maximum fitness after linear transformation to the average fitness before linear transformation, , is the average value of fitness before linear transformation, is the maximum value of fitness before linear transformation; ; After the change is completed, all fitness values ​​are checked. If there is a fitness value less than 0, α and β are adjusted; , .

[0021] The average value of fitness must be equal to the average value of fitness after calibration to ensure that the expected number of copies of individuals with average fitness in the next generation is 1, that is, ; is the average value after linear change; the maximum value of fitness after transformation should be equal to the specified multiple of the original fitness average value to control the number of copies of the individual with the largest fitness in the next generation. Experiments show that the specified multiple can be in the range of 1.0-2.0. The coefficient of linear proportion can be determined according to the above conditions. The linear transformation method transforms the fitness distribution, maintains the diversity within the population, and is simple to calculate and easy to implement. If the fitness of some individuals in the population is far below the average, the fitness value after the transformation may be negative. Therefore, considering the conditions for ensuring that the minimum fitness value is non-negative, two sets of linear change methods are designed.

[0022] In step S13, the secondary optimization of the process steps based on the unit utilization rate also includes the following steps:

[0023] Let A i j Indicates the jth process in the i-th order, obtains the waiting time and cumulative waiting time, obtains the sum of the mold change time when the i-th order is converted to the i+1-th order and the mold change time when the i+1-th order is converted to the i-th order TH i+1 , for i=1, 2, ..., n-1, where n is the order quantity, perform the following steps S51, S52 and S53;

[0024] S51, let B i j represents the waiting time for the jth process in the i-th order, C i j It represents the cumulative waiting time of the jth process in the i-th order. When j is 1, the waiting time is the same as the cumulative waiting time, which is the time required to obtain unprocessed raw materials.

[0025] S52, in process A i n1 , A i n1+1 , …, A i n2 A i n1 For A i-1 n2 The first process of the i-th order after i n2 is the last process of the i-th order. When i is 1, all processes of the first order are set to be in A. 0 n2 After that, find out the cumulative waiting time greater than TH i+1 The process is recorded as A i k1 , A i k1+1 , …, Ai k2 , {k1, k1+1, …, k2}⊆{n1, n1+1, …, n2}, calculate the cumulative waiting time C i k With TH i+1 Difference, k∈{k1,k1+1,…,k2};

[0026] S53, process A of the i+1th order i+1 j Insert them into the found process A one by one in order i k Previously, if process A of order i+1 i+1 j Required working hours i j Greater than the difference C i k -TH i+1 , then process A of the i+1th order i+1 j Decompose according to working hours and compare with the difference C i k -TH i+1 The corresponding working hours are inserted into the found process A i k Before;

[0027] If the process of the i+1th order requires working time t i j Less than or equal to the difference C i k -TH i+1 , then process A i+1 j Insert all into process A i k Before, the i+1th order is in A i+1 j The other steps are inserted into A i+1 j With A i k Between, and the inserted working hours are C i k -TH i+1 -t i j .

[0028] Existing scheduling systems often require the unit to have a strict upstream and downstream material supply relationship. Each process is strictly dependent on the materials or semi-finished products provided by the previous process, and its output is strictly provided to the next process on time. When the processing speed of the next process is greater than that of the previous process, the next process cannot be fully operated. At this time, the process of the next order is inserted between the two processes, and the time when the next process waits for the materials of the previous process is used to improve the efficiency of the unit. When the processing speed of the next process is less than that of the previous process, no new waiting time will be generated, and the waiting time that has been generated cannot be reduced; when the waiting time is large enough, when part or all of the processes of the next order can be inserted, the waiting time has been used and the accumulated waiting time will be cleared.

[0029] The waiting time and cumulative waiting time are determined by the following steps:

[0030] S60, for i=1, 2, ...n-1, execute steps S61 to S64;

[0031] S61, set j to 1, sum j+1 Set to 0, sum j+1 For process A i j The accumulated waiting time for materials;

[0032] S62, obtaining process A i j Processing speed V i j and the quantity requirement NUM for the i-th order i The processing speed is the processing speed when the material is sufficient. i j+1 Processing speed V i j+1 Greater than process A i j Processing speed V i j , then process A i j+1 Waiting time B i j for NUM i ×(V i j+1 -V i j ), process A i j+1 The cumulative waiting time C i j+1 For B i j +sum j+1 ;

[0033] S63, determine the cumulative waiting time C i j+1 Is it greater than or equal to TH? i+1 If so, sum j+1 Set to 0, otherwise sum j+1 Set to C i j+1 ;

[0034] S64, add 1 to the value of j and return to step S62 until the accumulated waiting time of all processes of the i-th order is determined.

[0035] In another aspect of the present invention, a data management system based on the intelligent manufacturing production process of steel pipes is provided, comprising: an order management module, a data storage module, a scheduling module and a unit management module; the output end of the order management module is connected to the data storage module and the scheduling module, for obtaining processing order information; the output end of the data storage module is connected to the input end of the scheduling module, for storing historical order data and unit processing information; the scheduling module schedules the orders for the first time based on a genetic algorithm, decomposes the orders into process steps, and optimizes the process steps for the second time based on the unit utilization rate; the output end of the unit management module is connected to the data storage module and the input end of the scheduling module, for obtaining unit processing information, the unit processing information including the speed at which the unit performs different processes and the mold change time for switching between different orders.

[0036] The order management module also includes an order acquisition unit and an order data extraction unit. The order acquisition unit is used to acquire external order information; the order data extraction unit is used to extract order quantity and order completion time requirements from the order information.

[0037] The scheduling module also includes a genetic algorithm unit, a scheduling optimization unit, a waiting time determination unit, a fitness calculation unit and a linear change unit; the genetic algorithm unit sets the initial population size, crossover probability, mutation probability and upper limit of the number of iterations, and uses the genetic algorithm to perform the first scheduling of the order based on the time required to complete each existing order, the mold change time between processing different existing orders and the order completion time requirement; the scheduling optimization unit decomposes the order according to the process, and based on the material delivery time of the previous order in the first scheduling, inserts the process of the next order in the first scheduling into the process of the previous order; the waiting time determination unit is used to determine the waiting time and cumulative waiting time of each process of the order; the fitness calculation unit is used to calculate the fitness of the genetic algorithm; the linear change unit is used to perform a linear transformation on the fitness to control the number of copies of the individual with the largest fitness in the next generation during the iterative process of the genetic algorithm.

[0038] The unit management module also includes a mold change time determination unit and a processing speed determination unit; the mold change time determination unit is used to obtain the time required for the unit to switch between different order tasks; the processing speed determination unit is used to obtain the processing speed of each process of the unit when the material is sufficient.

[0039] Compared with the prior art, the beneficial effects achieved by the present invention are: considering the order content, combining the parameter configuration of the genetic algorithm, using the genetic algorithm to schedule the orders of the workshop, and providing a scientific basis for planning decisions; linearly transforming the fitness of the genetic algorithm to control the number of copies of the individual with the largest fitness in the next generation; decomposing the order according to the process, inserting the process of the next order in the process of waiting for materials, improving the utilization rate of the mechanism, and thus improving the scheduling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0041] Figure 1 It is a structural schematic diagram of a steel pipe intelligent manufacturing production process data management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] 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.

[0043] In the embodiments of the present invention, please refer to Figure 1 , provides a data management system based on the intelligent manufacturing production process of steel pipes, including: an order management module, a data storage module, a scheduling module and a unit management module; the output end of the order management module is connected to the data storage module and the scheduling module to obtain processing order information; the output end of the data storage module is connected to the input end of the scheduling module to store historical order data and unit processing information; the scheduling module schedules the order for the first time based on a genetic algorithm, decomposes the order into process steps, and optimizes the process steps for the second time based on the unit utilization rate; the output end of the unit management module is connected to the data storage module and the input end of the scheduling module to obtain unit processing information, and the unit processing information includes the speed at which the unit performs different processes and the mold change time for switching between different orders.

[0044] The order management module also includes an order acquisition unit and an order data extraction unit. The order acquisition unit is used to acquire external order information; the order data extraction unit is used to extract the order quantity and order completion time requirements from the order information. The scheduling module also includes a genetic algorithm unit, a scheduling optimization unit, a waiting time determination unit, a fitness calculation unit and a linear change unit; the genetic algorithm unit sets the initial population size, crossover probability, mutation probability and the upper limit of the number of iterations, and uses the genetic algorithm to perform the first scheduling of the order based on the time required to complete each existing order, the mold change time between processing different existing orders and the order completion time requirements; the scheduling optimization unit decomposes the order according to the process, and inserts the process of the next order in the first scheduling into the process of the previous order based on the material time of the previous order in the first scheduling; the waiting time determination unit is used to determine the waiting time and cumulative waiting time of each process of the order; the fitness calculation unit is used to calculate the fitness of the genetic algorithm; the linear change unit is used to perform a linear transformation on the fitness to control the number of copies of the individual with the largest fitness in the next generation during the iteration of the genetic algorithm. The unit management module also includes a mold change time determination unit and a processing speed determination unit; the mold change time determination unit is used to obtain the time required for the unit to switch between different order tasks; the processing speed determination unit is used to obtain the processing speed of each process of the unit when the material is sufficient.

[0045] In an embodiment of the present invention, a method for managing production process data based on intelligent manufacturing of steel pipes is provided, comprising: S11, acquiring order data, wherein the order data includes order quantity and order completion time requirements;

[0046] S12, determining a first fitness function based on the order completion time requirement, and using a genetic algorithm to schedule the order for the first time, including steps S21 to S25;

[0047] S21, set the initial population size, crossover probability, mutation probability and the upper limit of the number of iterations; obtain historical order information, and determine the time required to complete each existing order and the mold change time between processing different existing orders based on the historical order information and existing order data, and encode the task based on the time required to complete each existing order, the mold change time between processing different existing orders and the order completion time requirements, and generate an initial population;

[0048] S22, calculate the fitness of each chromosome in the initial population and perform linear transformation;

[0049] S23, select chromosomes according to their fitness to obtain a new population;

[0050] S24, perform crossover and mutation operations on the new population; discard chromosomes that do not meet the constraints;

[0051] S25, return to step S21 until the number of iterations reaches a preset upper limit.

[0052] The fitness F is calculated by the following formula:

[0053] , where The time required to complete the order. The time required to complete the order, is the order delay time, a and b are the evaluation coefficients of order delivery time and the time required to complete the order, and c is the penalty coefficient of order delay time.

[0054] The fitness F is linearly transformed by the following steps:

[0055] , α is the linear transformation coefficient, β is the bias, α and β are determined by the following steps:

[0056] , is the ratio of the maximum fitness after linear transformation to the average fitness before linear transformation, , is the average value of fitness before linear transformation, is the maximum value of fitness before linear transformation; ; After the change is completed, all fitness values ​​are checked. If there is a fitness value less than 0, α and β are adjusted; , .

[0057] S13, decompose the order into process steps, and perform secondary optimization on the process steps based on the unit utilization rate:

[0058] Let A i j Indicates the jth process in the i-th order, obtains the waiting time and cumulative waiting time, obtains the sum of the mold change time when the i-th order is converted to the i+1-th order and the mold change time when the i+1-th order is converted to the i-th order TH i+1 , for i=1, 2, ..., n-1, where n is the order quantity, perform the following steps S51, S52 and S53;

[0059] S51, let B i j represents the waiting time for the jth process in the i-th order, C i j It represents the cumulative waiting time of the jth process in the i-th order. When j is 1, the waiting time is the same as the cumulative waiting time, which is the time required to obtain unprocessed raw materials.

[0060] S52, in process A i n1 , A i n1+1 , …, A i n2 A i n1 For A i-1 n2 The first process of the i-th order after i n2 is the last process of the i-th order. When i is 1, all processes of the first order are set to be in A. 0 n2 After that, find out the cumulative waiting time greater than TH i+1 The process is recorded as A i k1 , A i k1+1 , …, A i k2 , {k1, k1+1, …, k2}⊆{n1, n1+1, …, n2}, calculate the cumulative waiting time C i k With TH i+1 Difference, k∈{k1,k1+1,…,k2};

[0061] S53, process A of the i+1th order i+1 j Insert them into the found process A one by one in order i k Previously, if process A of order i+1 i+1 j Required working hours i j Greater than the difference C i k -TH i+1 , then process A of the i+1th order i+1 j Decompose according to working hours and compare with the difference C i k -TH i+1 The corresponding working hours are inserted into the found process A i k Before;

[0062] If the process of the i+1th order requires working time t i j Less than or equal to the difference C i k -TH i+1 , then process A i+1 jInsert all into process A i k Before, the i+1th order is in A i+1 j The other steps are inserted into A i+1 j With A i k Between, and the inserted working hours are, C i k -TH i+1 -t i j .

[0063] The waiting time and cumulative waiting time are determined by the following steps:

[0064] S60, for i=1, 2, ...n-1, execute steps S61 to S64;

[0065] S61, set j to 1, sum j+1 Set to 0, sum j+1 For process A i j The accumulated waiting time for materials;

[0066] S62, obtaining process A i j Processing speed V i j and the quantity requirement NUM for the i-th order i The processing speed is the processing speed when the material is sufficient. i j+1 Processing speed V i j+1 Greater than process A i j Processing speed V i j , then process A i j+1 Waiting time B i j for NUM i ×(V i j+1 -V i j ), process A i j+1 The cumulative waiting time C i j+1 For B i j +sum j+1 ;

[0067] S63, determine the cumulative waiting time C ij+1 Is it greater than or equal to TH? i+1 If so, sum j+1 Set to 0, otherwise sum j+1 Set to C i j+1 ;

[0068] S64, add 1 to the value of j and return to step S62 until the accumulated waiting time of all processes of the i-th order is determined.

[0069] S14, the unit produces and processes the products based on the second scheduling results.

[0070] For the three existing orders, after the first scheduling, the processes of the three orders D1, D2, and D3 are A 1 1. A 1 2. A 1 3. A 2 1. A 2 2. A 2 3. A 3 1. A 3 2. A 3 3. For convenience, the number of processes in all orders can be considered the same. For orders with missing process quantities, blank processes with 0 working hours can be added to fill them. 1 1. A 1 2. A 1 3, which can represent heating and piercing, rolling, and cooling respectively;

[0071] A 1 The waiting time for material 1 is 0 days. 1 The waiting time for material 2 is 3 days, 1 When the waiting time for material 3 is 3 days, 1 The cumulative waiting time for material 2 is 3 days. 1 The cumulative waiting time for materials in 3 is 6 days;

[0072] When the mold change time for orders D1 and D2 is 1 day;

[0073] Process A 2 When the working hours of 1 are 5 days, at this time, process A of order D1 is started 1 2, you can first execute process A of order D2 2 1. Process A 2 1's 2-day work is inserted into A 1 1 and A 1 2, process A 2 1's 2-day work is inserted into A 1 2 and A 1 3, follow A 1 1. A2 1. A 1 2. A 2 1. A 1 3. A 2 1.

[0074] Process A 2 When the working hours of process 1 are 3 days, 2 1's 2-day work is inserted into A 1 1 and A 1 2, process A 2 1 day of work of 1 is inserted into A 1 2 and A 1 3, process A 2 2 1 day of work is inserted into A 1 2 and A 1 3, follow A 1 1. A 2 1. A 1 2. A 2 1. A 2 2. A 1 3. A 2 2. The process is carried out for production;

[0075] When the mold change time for orders D1 and D2 is 5 days; only in A 1 2 and A 1 3. Insert the process of D2 order between

[0076] If the D1 order still has a waiting time of 3 days for process A 1 4. A 1 4 means finishing, then A 1 After 3, the accumulated waiting time is reset to zero, that is, process A 1 The cumulative waiting time for 4 is 3 days instead of 9 days.

[0077] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0078] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data management method based on intelligent manufacturing production process of steel pipes, characterized in that: The following steps are involved: S11, obtaining order data, wherein the order data includes order quantity and order completion time requirement; S12, determining a first fitness function based on the order completion time requirement, and using a genetic algorithm to schedule the order for the first time, including the following steps: S21, set the initial population size, crossover probability, mutation probability and the upper limit of the number of iterations; obtain historical order information, and determine the time required to complete each existing order and the mold change time between processing different existing orders based on the historical order information and existing order data, and encode the task based on the time required to complete each existing order, the mold change time between processing different existing orders and the order completion time requirements, and generate an initial population; S22, calculate the fitness of each chromosome in the initial population and perform linear transformation; The fitness F is calculated by the following formula: , where The time required to complete the order. The time required to complete the order, is the order delay time, a and b are the evaluation coefficients of order delivery time and the time required to complete the order, and c is the penalty coefficient of order delay time; S23, select chromosomes according to their fitness to obtain a new population; S24, perform crossover and mutation operations on the new population; discard chromosomes that do not meet the constraints; S25, returning to step S21 until the number of iterations reaches a preset upper limit; S13, decompose the order into process steps, and perform secondary optimization on the process steps based on the unit utilization rate: Let A i j Indicates the jth process in the i-th order, obtains the waiting time and cumulative waiting time, obtains the sum of the mold change time when the i-th order is converted to the i+1-th order and the mold change time when the i+1-th order is converted to the i-th order TH i+1 , for i=1, 2, ..., n-1, where n is the order quantity, perform the following steps S51, S52 and S53; S51, let B i j represents the waiting time for the jth process in the i-th order, C i j It represents the cumulative waiting time of the jth process in the i-th order. When j is 1, the waiting time is the same as the cumulative waiting time, which is the time required to obtain unprocessed raw materials. S52, in process A i n1 , A i n1+1 , …, A i n2 A i n1 For A i-1 n2 The first process of the i-th order after i n2 is the last process of the i-th order. When i is 1, all processes of the first order are set to be in A. 0 n2 After that, find out the cumulative waiting time greater than TH i+1 The process is recorded as A i k1 , A i k1+1 , …, A i k2 , , calculate the cumulative waiting time C i k With TH i+1 Difference, ; S53, process A of the i+1th order i+1 j Insert them into the found process A one by one in order i k Previously, if process A of order i+1 i+1 j Required working hours i j Greater than the difference C i k -TH i+1 , then process A of the i+1th order i+1 j Decompose according to working hours and compare with the difference C i k -TH i+1 The corresponding working hours are inserted into the found process A i k Before; If the process time required for the i+1th order is t i j Less than or equal to the difference C i k -TH i+1 , then process A i+1 j Insert all into process A i k Before, the i+1th order is in A i+1 j The other processes are inserted into A i+1 j With A i k Between, and the inserted working hours are, C i k -TH i+1 -t i j ; S14, the unit produces and processes the products based on the second scheduling results.

2. The method for managing production process data based on intelligent manufacturing of steel pipes according to claim 1 is characterized in that: The fitness F is linearly transformed by the following steps: , α is the linear transformation coefficient, β is the bias, α and β are determined by the following steps: , is the ratio of the maximum fitness after linear transformation to the average fitness before linear transformation, , is the average value of fitness before linear transformation, is the maximum value of fitness before linear transformation; ; After the change is completed, all fitness values ​​are checked. If there is a fitness value less than 0, α and β are adjusted; , .

3. The method for managing production process data based on intelligent manufacturing of steel pipes according to claim 1 is characterized in that: The waiting time and cumulative waiting time are determined by the following steps: S60, for i=1, 2, ...n-1, execute steps S61 to S64; S61, set j to 1, sum j+1 Set to 0, sum j+1 For process A i j The accumulated waiting time for materials; S62, obtaining process A i j Processing speed V i j and the quantity requirement NUM for the i-th order i The processing speed is the processing speed when the material is sufficient. i j+1 Processing speed V i j+1 Greater than process A i j Processing speed V i j , then process A i j+1 Waiting time B i j for NUM i ×(V i j+1 -V i j ), process A i j+1 The cumulative waiting time C i j+1 For B i j +sum j+1 ; S63, determine the cumulative waiting time C i j+1 Is it greater than or equal to TH? i+1 If so, sum j+1 Set to 0, otherwise sum j+1 Set to C i j+1 ; S64, add 1 to the value of j and return to step S62 until the accumulated waiting time of all processes of the i-th order is determined.

4. Based on the steel pipe intelligent manufacturing production process data management system, the steel pipe intelligent manufacturing production process data management method according to any one of claims 1 to 3 is implemented, characterized in that: include: Order management module, data storage module, scheduling module and crew management module; The output end of the order management module is connected to the data storage module and the scheduling module for obtaining processing order information; the output end of the data storage module is connected to the input end of the scheduling module for storing historical order data and unit processing information; the scheduling module schedules the order for the first time based on the genetic algorithm, decomposes the order into process steps, and optimizes the process steps for the second time based on the unit utilization rate; the output end of the unit management module is connected to the data storage module and the input end of the scheduling module for obtaining unit processing information, and the unit processing information includes the speed at which the unit performs different processes and the mold change time for switching between different orders.

5. The data management system based on intelligent manufacturing production process of steel pipe according to claim 4 is characterized in that: The order management module also includes an order acquisition unit and an order data extraction unit. The order acquisition unit is used to acquire external order information; the order data extraction unit is used to extract order quantity and order completion time requirements from the order information.

6. The data management system based on intelligent manufacturing production process of steel pipe according to claim 4 is characterized in that: The scheduling module also includes a genetic algorithm unit, a scheduling optimization unit, a waiting time determination unit, a fitness calculation unit and a linear change unit; the genetic algorithm unit sets the initial population size, crossover probability, mutation probability and upper limit of the number of iterations, and uses the genetic algorithm to perform the first scheduling of the order based on the time required to complete each existing order, the mold change time between processing different existing orders and the order completion time requirement; the scheduling optimization unit decomposes the order according to the process, and based on the material delivery time of the previous order in the first scheduling, inserts the process of the next order in the first scheduling into the process of the previous order; the waiting time determination unit is used to determine the waiting time and cumulative waiting time of each process of the order; the fitness calculation unit is used to calculate the fitness of the genetic algorithm; the linear change unit is used to perform a linear transformation on the fitness to control the number of copies of the individual with the largest fitness in the next generation during the iterative process of the genetic algorithm.

7. The data management system based on intelligent manufacturing production process of steel pipe according to claim 6 is characterized in that: The unit management module also includes a mold change time determination unit and a processing speed determination unit; the mold change time determination unit is used to obtain the time required for the unit to switch between different order tasks; the processing speed determination unit is used to obtain the processing speed of each process of the unit when the material is sufficient.