Furniture production line intelligent order distribution method and system based on intelligent control

Abstract

The invention relates to the technical field of intelligent order distribution, in particular to a furniture production line intelligent order distribution method and system based on intelligent control. Firstly, order data and production line resource data are integrated to obtain a real-time state index, and a system is helped to quickly judge the matching degree of production resources by reflecting the state of the production line in real time; secondly, a delivery delay index, an equipment utilization index and a manual load balancing index are combined to construct a multi-objective optimization model, the multi-objective optimization model is solved by using a genetic algorithm, an optimal initial order distribution scheme is automatically generated, and the accuracy of order delivery and the utilization rate of production resources are improved; and finally, when the system encounters emergency situations of emergency order insertion and material shortage, local dynamic adjustment is carried out on an order distribution scheme through a simulated annealing algorithm, production changes are rapidly coped with, and the flexibility and high efficiency of a production plan are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent order distribution, and specifically to an intelligent order distribution method and system for a furniture production line based on intelligent control. Background Art

[0002] In the modern furniture manufacturing industry, the efficiency of production line management directly affects the company's production capacity, resource utilization and delivery accuracy. As an important part of production management, the order splitting system plays a key role in rationally allocating order tasks to various production links. An efficient order splitting system can monitor order demand and production resources in real time, optimize the scheduling of equipment and personnel, and achieve refined management of the production process. Through intelligent order splitting methods, companies can reduce production bottlenecks, improve equipment utilization, balance worker loads, and ensure on-time delivery, thereby improving overall production efficiency and customer satisfaction.

[0003] However, many traditional order splitting systems are still facing many challenges at this stage. Traditional order splitting methods mostly rely on manual or simple rule algorithms, lacking real-time monitoring and dynamic adjustment of production line resources and order requirements, resulting in resource waste, low equipment utilization and frequent production bottlenecks. In addition, in the face of emergencies such as emergency orders and material shortages, traditional systems have poor responsiveness and usually rely on manual intervention to adjust production plans, resulting in inefficient adjustments and prone to errors. Therefore, the existing order splitting system urgently needs to be optimized to adapt to the development needs of intelligent manufacturing and improve production flexibility and efficiency.

[0004] Therefore, an intelligent order splitting method and system for furniture production line based on intelligent control is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent order splitting method and system for furniture production lines based on intelligent control. The present invention obtains a real-time status index by integrating order data and production line resource data to help the system quickly determine the matching degree of production resources; secondly, the present invention combines the delivery delay index, equipment utilization index and manual load balancing index to construct a multi-objective optimization model, and uses a genetic algorithm to solve the multi-objective optimization model to automatically generate the optimal initial order splitting plan; finally, when the system encounters emergencies such as emergency insertion and material shortage, the present invention uses a simulated annealing algorithm to perform local dynamic adjustments to the order splitting plan, quickly respond to production changes, and ensure the flexibility and efficiency of the production plan.

[0006] To achieve the above object, the present invention provides the following technical solutions: An intelligent order splitting method for a furniture production line based on intelligent control, comprising: Collect order data and production line resource data in real time, establish an order vector and a production line resource vector based on the order data and the production line resource data, and calculate a real-time status index according to the order vector and the production line resource vector; A multi-objective optimization model is constructed according to the delivery delay index, the equipment utilization index and the manual load balancing index, and the objective function of the multi-objective optimization model is weighted using the real-time status index, and the weighted objective function is solved by a genetic algorithm to generate an initial order distribution plan; Detect the real-time status of the production line to determine whether the order splitting adjustment condition is triggered; if triggered, use the simulated annealing algorithm to dynamically adjust the initial order splitting plan to obtain an adjusted order splitting plan; otherwise, retain the initial order splitting plan; the order splitting adjustment conditions include emergency order insertion and material shortage; Complete order allocation according to the order splitting plan.

[0007] Furthermore, the order data includes order type, delivery date, product specifications and customer priority; the production line resource data includes equipment usage time, material inventory and worker working hours.

[0008] Furthermore, the calculation formula of the real-time status index is: ; in, represents the real-time status index, represents the order vector, represents the transpose of the order vector, represents the inner product operation between vectors, Represents the product operation between values. represents the production line resource vector, represents the transpose of the production line resource vector, represents the order weight, Indicates the resource weight.

[0009] Furthermore, the calculation formula of the weighted objective function is: ; in, represents the weighted objective function, represents the delivery delay index, represents the equipment utilization index, represents the artificial load balancing index, represents the real-time status index, represents the order vector, represents the transpose of the order vector, represents the inner product operation between vectors, Represents the product operation between values. represents the production line resource vector, represents the transposition of the production line resource vector. Further, solving the weighted objective function by genetic algorithm includes: S201: Taking the order combinations in different sorting modes as individuals, an initial population of K individuals is randomly generated; S202: Calculate the fitness of each individual according to the weighted objective function; S203: Selecting excellent individuals according to fitness and performing crossover and mutation on the excellent individuals to generate offspring individuals; S204: adding the offspring individuals to the population, and reselecting K individuals as a new population; S205: Iterate steps S202-S204 until the first termination condition is met, and select the individual with the highest fitness as the optimal combination; the first termination condition is that the maximum number of iterations is reached or the fitness change is less than a threshold.

[0010] Furthermore, dynamically adjusting the initial order splitting scheme using a simulated annealing algorithm includes: S301: setting an initial solution, an initial temperature, a cooling rate, a maximum number of iterations and a minimum temperature, and taking the initial solution as the current solution and the initial temperature as the current temperature; S302: Randomly select two production tasks in the current solution, exchange their order splitting order, and use the adjusted order splitting scheme as a set of neighborhood solutions; S303: Calculate the objective function variation between the current solution and the neighborhood solution, and accept the neighborhood solution according to the current temperature and the objective function variation; S304: adjusting the current temperature according to the cooling rate; S305: Iterate and execute steps S302-S304 until a second termination condition is reached, and generate an adjusted order splitting plan; the second termination condition is that a maximum number of iterations is reached or the current temperature is lower than a minimum temperature.

[0011] The present invention also provides an intelligent order splitting system for a furniture production line based on intelligent control, comprising: A data acquisition module, used for collecting order data and production line resource data in real time, establishing an order vector and a production line resource vector based on the order data and the production line resource data, and calculating a real-time status index according to the order vector and the production line resource vector; An initial plan generation module is used to construct a multi-objective optimization model according to the delivery delay index, the equipment utilization index and the manual load balancing index, and use the real-time status index to weight the objective function of the multi-objective optimization model, solve the weighted objective function through a genetic algorithm, and generate an initial order distribution plan; The order splitting plan adjustment module is used to detect the real-time status of the production line and determine whether the order splitting adjustment conditions are triggered; if triggered, the simulated annealing algorithm is used to dynamically adjust the initial order splitting plan to obtain an adjusted order splitting plan; otherwise, the initial order splitting plan is retained; the order splitting adjustment conditions include emergency order insertion and material shortage; The order allocation module is used to complete order allocation according to the order splitting plan.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. By converting order data and production line resource data into order vectors and production line resource vectors and calculating the real-time status index, the system can comprehensively evaluate the matching degree between order demand and production resources. The real-time status index provides the system with dynamic feedback on the current status of the production line, so that production scheduling can be adjusted more accurately according to real-time changes. This comprehensive evaluation and feedback mechanism helps to timely identify potential production bottlenecks, optimize resource allocation, improve production efficiency, and ensure that orders are delivered on time.

[0013] 2. By combining the delivery delay index, equipment utilization index and manual load balancing index to build a multi-objective optimization model, and using the real-time status index to weight the objective function, the system can comprehensively consider multiple key factors in dynamic adjustment to achieve more accurate production scheduling and resource allocation. By solving the weighted objective function through genetic algorithms, the system can generate the optimal initial order distribution plan to ensure that the equipment utilization rate is maximized and the worker load is balanced while meeting the delivery date, thereby improving production efficiency and resource utilization, and reducing delays and imbalances that may occur in the production process.

[0014] 3. By real-time detection of the production line status and determining whether the order splitting adjustment conditions are triggered, the system can flexibly respond to emergencies, such as emergency order insertion and material shortages. When the adjustment conditions are triggered, the simulated annealing algorithm is used to dynamically optimize the initial order splitting plan to ensure rapid adjustments in the event of production changes and maintain production continuity and efficiency. Otherwise, the system will retain the initial order splitting plan, reduce unnecessary intervention, ensure the stable use of resources and the smooth execution of production plans, thereby improving the responsiveness and adaptability of the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flow chart of an intelligent order splitting method for a furniture production line based on intelligent control provided by an embodiment of the present invention; Figure 2 A flow chart of using a genetic algorithm to solve a weighted objective function provided by an embodiment of the present invention; Figure 3 A flowchart of dynamically adjusting the initial order splitting scheme using a simulated annealing algorithm provided in an embodiment of the present invention; Figure 4 A structural diagram of an intelligent order distribution system for a furniture production line based on intelligent control provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] 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.

[0017] Embodiment 1: An intelligent order splitting method for furniture production line based on intelligent control, such as Figure 1 As shown, including: S100: collecting order data and production line resource data in real time, establishing an order vector and a production line resource vector based on the order data and the production line resource data, and calculating a real-time status index according to the order vector and the production line resource vector; Furthermore, the order data includes order type, delivery date, product specifications and customer priority; the production line resource data includes equipment usage time, material inventory and worker working hours.

[0018] Real-time collection of order data and production line resource data enables the system to fully understand order demand and production resource status, thereby achieving more accurate production scheduling and optimization, and improving production efficiency and order delivery accuracy.

[0019] Specifically, in a feasible embodiment, a set of order data is shown in Table 1, including order type, delivery date, product specifications and customer priority, and a set of production line resource data is shown in Table 2, including equipment usage time, material inventory and worker working hours. , each component represents order type, delivery date, product specification and customer priority, and the production line resource vector established by production line resource data , each component represents the equipment usage time, material inventory and worker working hours.

[0020] Table 1 A set of real-time collected order data

[0021] Furthermore, the calculation formula of the real-time status index is: ; in, represents the real-time status index, represents the order vector, represents the transpose of the order vector, represents the inner product operation between vectors, Represents the product operation between values. represents the production line resource vector, represents the transpose of the production line resource vector, represents the order weight, Indicates the resource weight.

[0022] Table 2 A set of real-time collected production line resource data

[0023] By establishing order vectors and production line resource vectors based on order data and production line resource data, and calculating the real-time status index, the system can comprehensively evaluate the degree of matching between order demand and production resources, thereby reflecting the status of the production line in real time, helping to optimize production scheduling and resource allocation, improve production efficiency and reduce potential production bottlenecks.

[0024] S200: constructing a multi-objective optimization model according to the delivery delay index, the equipment utilization index and the manual load balancing index, and using the real-time status index to weight the objective function of the multi-objective optimization model, solving the weighted objective function through a genetic algorithm, and generating an initial order distribution plan; Specifically, the calculation formula of the delivery delay index is: ; in, represents the delivery delay index, N represents the number of orders in a batch, Represents the index of the order, represents the maximum value function, Indicates the order completion time. Indicates the scheduled delivery date; the calculation formula of equipment utilization index is: ; in, represents the equipment utilization index, M represents the total number of equipment, Indicates the device index. Indicates the device usage time. Indicates the actual usage time of the device; the calculation formula of the artificial load balancing index is: ; in, Indicates the artificial load balancing index, represents the total number of workers, represents the worker index, Indicates that workers work long hours.

[0025] Furthermore, the calculation formula of the weighted objective function is: ; in, represents the weighted objective function, represents the delivery delay index, represents the equipment utilization index, represents the artificial load balancing index, represents the real-time status index, represents the order vector, represents the transpose of the order vector, represents the inner product operation between vectors, Represents the product operation between values. represents the production line resource vector, represents the transpose of the production line resource vector.

[0026] By using the real-time status index to weight the objective function of the multi-objective optimization model, the optimization focus can be dynamically adjusted according to the current actual status of the production line, so that each goal can be more reasonably weighted under different production conditions, thereby achieving more accurate scheduling decisions, optimizing resource allocation, improving production efficiency and ensuring the accuracy of delivery time.

[0027] Furthermore, if Figure 2 As shown, solving the weighted objective function by genetic algorithm includes: S201: Taking the order combinations in different sorting modes as individuals, an initial population of K individuals is randomly generated; S202: Calculate the fitness of each individual according to the weighted objective function; S203: Selecting excellent individuals according to fitness and performing crossover and mutation on the excellent individuals to generate offspring individuals; S204: adding the offspring individuals to the population, and reselecting K individuals as a new population; S205: Iterate steps S202-S204 until the first termination condition is met, and select the individual with the highest fitness as the optimal combination; the first termination condition is that the maximum number of iterations is reached or the fitness change is less than a threshold.

[0028] By constructing a multi-objective optimization model based on delivery delay, equipment utilization and worker load balance, and using the real-time status index to weight the objective function, the system can comprehensively consider multiple key factors for optimization, and use genetic algorithms to automatically generate initial order splitting plans to ensure that orders can be delivered on time with the optimal production resource configuration, while improving the balance between equipment utilization and worker load and improving overall production efficiency.

[0029] S300: Detect the real-time status of the production line and determine whether the order splitting adjustment condition is triggered; if triggered, use the simulated annealing algorithm to dynamically adjust the initial order splitting plan to obtain an adjusted order splitting plan; otherwise, retain the initial order splitting plan; the order splitting adjustment conditions include emergency order insertion and material shortage; Furthermore, if Figure 3 As shown, using the simulated annealing algorithm to dynamically adjust the initial order splitting plan includes: S301: setting an initial solution, an initial temperature, a cooling rate, a maximum number of iterations and a minimum temperature, and taking the initial solution as the current solution and the initial temperature as the current temperature; S302: Randomly select two production tasks in the current solution, exchange their order splitting order, and use the adjusted order splitting scheme as a set of neighborhood solutions; S303: Calculate the objective function variation between the current solution and the neighborhood solution, and accept the neighborhood solution according to the current temperature and the objective function variation; S304: adjusting the current temperature according to the cooling rate; S305: Iterate and execute steps S302-S304 until a second termination condition is reached, and generate an adjusted order splitting plan; the second termination condition is that a maximum number of iterations is reached or the current temperature is lower than a minimum temperature.

[0030] Table 3 Initial parameter settings of simulated annealing algorithm

[0031] Specifically, in a feasible embodiment, the initial parameter settings of the simulated annealing algorithm are shown in Table 3, wherein the initial order splitting scheme is the initial order splitting scheme obtained in S200, Indicates the comfort level corresponding to the initial order splitting scheme; randomly selects two production tasks in the current solution, exchanges their order splitting order, and uses the adjusted order splitting scheme as a set of neighborhood solutions; calculates the objective function variation between the current solution and the neighborhood solution, and accepts the neighborhood solution according to the current temperature and the objective function variation. The calculation formula of the objective function variation is: ; in, represents the change of the objective function, Indicates the comfort level corresponding to the initial order splitting plan, represents the objective function value of the neighborhood solution, that is, the comfort level. The neighborhood solution is accepted according to the current temperature and the change in the objective function. The calculation formula for the acceptance probability is: ; in, represents the probability of acceptance, The natural index The exponential function with base , represents the current temperature; the current temperature is adjusted according to the cooling rate, and the temperature adjustment formula is: ,in Indicates the cooling rate; iteratively execute steps S302-S304 until the second termination condition is reached, and generate an adjustment order distribution plan; the second termination condition is that the maximum number of iterations is reached or the current temperature is less than the minimum temperature.

[0032] By detecting the status of the production line in real time and determining whether the order splitting adjustment conditions are triggered, the system can dynamically use the simulated annealing algorithm to optimize the initial order splitting plan when encountering situations such as emergency orders and material shortages, thereby quickly responding to changes in the production process, ensuring the flexibility and efficiency of the production plan, avoiding delays caused by manual intervention, and improving the responsiveness of the production line and resource utilization.

[0033] S400: Complete order allocation according to the order allocation plan.

[0034] Embodiment 2: In response to the call for "intelligent manufacturing", a furniture manufacturing company A has upgraded its order splitting system and adopted the present invention to provide an intelligent order splitting system for furniture production lines based on intelligent control, such as Figure 4 As shown, including: A data acquisition module, used for collecting order data and production line resource data in real time, establishing an order vector and a production line resource vector based on the order data and the production line resource data, and calculating a real-time status index according to the order vector and the production line resource vector; An initial plan generation module is used to construct a multi-objective optimization model according to the delivery delay index, the equipment utilization index and the manual load balancing index, and use the real-time status index to weight the objective function of the multi-objective optimization model, solve the weighted objective function through a genetic algorithm, and generate an initial order distribution plan; The order splitting plan adjustment module is used to detect the real-time status of the production line and determine whether the order splitting adjustment conditions are triggered; if triggered, the simulated annealing algorithm is used to dynamically adjust the initial order splitting plan to obtain an adjusted order splitting plan; otherwise, the initial order splitting plan is retained; the order splitting adjustment conditions include emergency order insertion and material shortage; The order allocation module is used to complete order allocation according to the order splitting plan.

[0035] The comparison before and after the system upgrade is shown in Table 4. It can be seen from the table that the current order splitting system has significant advantages over the original order splitting system A. First, it significantly shortens the order delivery cycle from 7 days to 5.5 days through intelligent control and real-time data analysis, improving customer satisfaction. Secondly, the equipment utilization rate has been greatly improved from 68% to 75% to 83% to 88%, effectively improving production efficiency and reducing costs. In addition, the system can automatically respond to emergency orders, and the adjustment time is shortened from the original 2-4 hours to 8-15 minutes, greatly improving production flexibility. For material shortages, the current system can dynamically eliminate low-priority orders, affecting only 2% to 5% of orders, while the original system requires manual investigation, affecting 10% to 15% of orders, further reducing uncertainty and risk in production. Finally, the current order splitting system achieves multi-objective intelligent optimization and improves overall production efficiency by simultaneously optimizing delivery time, equipment utilization and worker load balancing.

[0036] Table 4 Performance comparison before and after system upgrade

[0037] Embodiment three: A furniture manufacturer B received 100 orders (including sofas, cabinets, and custom cabinets) in February, involving 3 production lines, 15 equipment, and 20 workers. In the order splitting process, it encountered emergency orders (customers required delivery within 24 hours) and board shortages (a certain model was insufficient in stock). Compared with the various expected processing indicators of the original order splitting system B, they were significantly improved after the current order splitting system was adopted. The processing indicators of emergency orders are shown in Table 5, and the processing indicators of board shortages are shown in Table 6. It can be seen from the table that the current order splitting system can dynamically use the simulated annealing algorithm to optimize the initial order splitting plan when encountering emergency orders and material shortages, so as to quickly respond to changes in the production process, ensure the flexibility and efficiency of the production plan, avoid delays caused by manual intervention, and improve the responsiveness and resource utilization of the production line.

[0038] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0039] Table 5 Comparison of various processing indicators under emergency order insertion

[0040] Table 6 Comparison of various processing indicators under board shortage

Claims

1. An intelligent order splitting method for a furniture production line based on intelligent control, characterized in that: include: Collect order data and production line resource data in real time, establish an order vector and a production line resource vector based on the order data and the production line resource data, and calculate a real-time status index according to the order vector and the production line resource vector; A multi-objective optimization model is constructed according to the delivery delay index, the equipment utilization index and the manual load balancing index, and the objective function of the multi-objective optimization model is weighted using the real-time status index, and the weighted objective function is solved by a genetic algorithm to generate an initial order distribution plan; Detect the real-time status of the production line and determine whether the order splitting adjustment conditions are triggered; If triggered, the initial order splitting plan is dynamically adjusted using a simulated annealing algorithm to obtain an adjusted order splitting plan; otherwise, the initial order splitting plan is retained; the order splitting adjustment conditions include emergency order insertion and material shortage; Complete order allocation according to the order splitting plan.

2. According to the intelligent order splitting method for furniture production line based on intelligent control according to claim 1, it is characterized in that: The order data includes order type, delivery date, product specifications and customer priority; the production line resource data includes equipment usage time, material inventory and worker working hours.

3. According to the intelligent order splitting method for furniture production line based on intelligent control in claim 1, it is characterized in that: The calculation formula of the real-time status index is: ； in, represents the real-time status index, represents the order vector, represents the transpose of the order vector, represents the inner product operation between vectors, Represents the product operation between values. represents the production line resource vector, represents the transpose of the production line resource vector, represents the order weight, Indicates the resource weight.

4. According to the intelligent order splitting method for furniture production line based on intelligent control according to claim 1, it is characterized in that: The calculation formula of the weighted objective function is: ； in, represents the weighted objective function, represents the delivery delay index, represents the equipment utilization index, represents the artificial load balancing index, represents the real-time status index, represents the order vector, represents the transpose of the order vector, represents the inner product operation between vectors, Represents the product operation between values. represents the production line resource vector, represents the transpose of the production line resource vector.

5. According to the intelligent order splitting method for furniture production line based on intelligent control in claim 1, it is characterized in that: Solving the weighted objective function through genetic algorithm includes: S201: Taking the order combinations in different sorting modes as individuals, an initial population of K individuals is randomly generated; S202: Calculate the fitness of each individual according to the weighted objective function; S203: Selecting excellent individuals according to fitness and performing crossover and mutation on the excellent individuals to generate offspring individuals; S204: adding the offspring individuals to the population, and reselecting K individuals as a new population; S205: Iterate steps S202-S204 until the first termination condition is met, and select the individual with the highest fitness as the optimal combination; the first termination condition is that the maximum number of iterations is reached or the fitness change is less than a threshold.

6. According to the intelligent order splitting method for furniture production line based on intelligent control in claim 1, it is characterized in that: Using the simulated annealing algorithm to dynamically adjust the initial order splitting plan includes: S301: setting an initial solution, an initial temperature, a cooling rate, a maximum number of iterations and a minimum temperature, and taking the initial solution as the current solution and the initial temperature as the current temperature; S302: Randomly select two production tasks in the current solution, exchange their order splitting order, and use the adjusted order splitting scheme as a set of neighborhood solutions; S303: Calculate the objective function variation between the current solution and the neighborhood solution, and accept the neighborhood solution according to the current temperature and the objective function variation; S304: adjusting the current temperature according to the cooling rate; S305: Iterate and execute steps S302-S304 until a second termination condition is reached, and generate an adjusted order splitting plan; the second termination condition is that a maximum number of iterations is reached or the current temperature is lower than a minimum temperature.

7. An intelligent order splitting system for furniture production line based on intelligent control, characterized in that: include: A data acquisition module, used for collecting order data and production line resource data in real time, establishing an order vector and a production line resource vector based on the order data and the production line resource data, and calculating a real-time status index according to the order vector and the production line resource vector; An initial plan generation module is used to construct a multi-objective optimization model according to the delivery delay index, the equipment utilization index and the manual load balancing index, and use the real-time status index to weight the objective function of the multi-objective optimization model, solve the weighted objective function through a genetic algorithm, and generate an initial order distribution plan; The order splitting plan adjustment module is used to detect the real-time status of the production line and determine whether the order splitting adjustment conditions are triggered; If triggered, the initial order splitting plan is dynamically adjusted using a simulated annealing algorithm to obtain an adjusted order splitting plan; otherwise, the initial order splitting plan is retained; the order splitting adjustment conditions include emergency order insertion and material shortage; The order allocation module is used to complete order allocation according to the order splitting plan.

Images