Supply chain optimization decision method and system based on artificial intelligence

Abstract

The invention relates to the technical field of supply chain management, and discloses a supply chain optimization decision-making method and system based on artificial intelligence, and the system comprises a customization service module, a data analysis module, an intelligent evaluation module and an optimization decision-making module. According to the supply chain optimization decision-making method and system based on artificial intelligence, management data of suppliers and manufacturers and demand data of automobile modified part orders are acquired in real time through a customization service module, and are classified to form a data set; the data analysis module calculates the supply coefficient and risk value of each supplier and the assembly precision and quality coefficient of each manufacturer to form a supplier ranking database and a manufacturer ranking database, and the intelligent evaluation module judges the complexity level of the automobile modified part, screens out a production line data set meeting the order requirement of the automobile modified part, and stores the production line data set in the production line data set. The intelligent configuration production line is high in flexibility, the optimization decision module monitors the actual production condition, corresponding optimization measures are taken, and the product quality is dynamically adjusted to be more stable.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain management, and in particular to a method and system for supply chain optimization decision-making based on artificial intelligence. Background Art

[0002] As the core link of enterprise operation, supply chain refers to a series of value-added activities from raw material procurement to final product delivery to consumers. Participants in the supply chain include suppliers, manufacturers, distributors, retailers and end consumers. The management process of the supply chain involves planning, procurement, production, transportation, warehousing and customer service. By optimizing the supply chain, enterprises can establish long-term cooperative relationships with high-quality suppliers and manufacturers and achieve lean production.

[0003] With the changes in the market environment and the upgrading of consumer demand, especially in the field of automotive modification parts, consumers' demand for automotive modification parts is increasingly showing the characteristics of small batches, diversification and personalization, which has brought new challenges to the traditional supply chain, but also brought opportunities for transformation and upgrading to enterprises. By introducing digital technology, optimizing production models, improving collaborative capabilities and strengthening customer interaction, enterprises can build an efficient, flexible and transparent supply chain system to better serve consumers. In the future, with the further development of technology and the continuous growth of market demand, the optimization of the automotive modification parts supply chain will become an important source of industry competitiveness.

[0004] At present, traditional supply chains are often based on large-scale production and lack the flexibility to cope with small-batch, personalized customized orders. This rigid production model can easily lead to problems such as the quality of modified parts not meeting consumer expectations and delayed delivery, making it difficult to meet consumer time requirements. In addition, in the actual operation of the supply chain, information and demand at different nodes may change rapidly. Traditional supply chains lack real-time data sharing and dynamic adjustment capabilities, resulting in the inability to update resource allocation and production plans in a timely manner, affecting the overall supply chain decision-making efficiency and consumer satisfaction. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] In view of the shortcomings of the existing technology, the present invention provides a method and system for supply chain optimization decision-making based on artificial intelligence, which has the advantages of high flexibility in intelligent configuration of production lines and more stable product quality through dynamic adjustment. It solves the problem that traditional supply chains are difficult to meet small amounts of personalized customization needs and lack dynamic adjustment capabilities.

[0007] (II) Technical solution

[0008] To achieve the above object, the present invention provides the following technical solution: a method for optimizing supply chain decision-making based on artificial intelligence, comprising the following steps:

[0009] Step 1: Connect to the supply chain management system through the network to obtain the management data of all suppliers and manufacturers, as well as the demand data of all automobile modification parts orders in real time, and classify them into supply data set, manufacturing data set and order data set;

[0010] Step 2: According to the supply data set, analyze the delivery rate JV, the change trend of the delivery rate JV and the delivery risk of each supplier, generate the corresponding supply coefficient Gyxs and risk value Fxz, and form the supplier ranking database GK;

[0011] Step 3: Based on the manufacturing data set, analyze the assembly accuracy Zujd and quality coefficient Zlxs of each manufacturer and form a manufacturer ranking database ZK;

[0012] Step 4: Based on the supply data set, manufacturing data set and order data set, analyze the differences between modified auto parts and existing products, determine the complexity level of manufacturers in producing modified auto parts orders, and whether it is necessary to adjust the production process of existing products, and then select production lines that meet the needs of modified auto parts orders from the supplier ranking database GK and the manufacturer ranking database ZK, and generate the corresponding production line data group and customization time Dzsc;

[0013] Step 5: Set a fixed range quantity threshold SLY, and then combine the order data set and the production line data set to select an appropriate number of production lines to start the automobile modification parts order, and monitor the production status of each production line during the customization time Dzsc;

[0014] Step 6: Set a fixed range of risk fluctuation threshold FXY and quality fluctuation threshold ZLY, and then combine the production situation of each production line during the customization period Dzsc to determine whether the actual production situation meets the requirements of automobile modification parts orders, and take corresponding optimization measures.

[0015] Preferably, in step 1, the expression of the supply data set is {G1 t , G2 t , G3 t ,...,Gy t}, G1 t To Gy t are the management data of the first to yth suppliers respectively. The management data of suppliers include part name, part quantity and defective quantity. t represents the delivery time of a single supplier. The expression of the manufacturing data set is {Z1 s 、Z2 s 、Z3 s 、...、Zh s}, Z1 s To Zh sare the management data of the first to the hth manufacturer, respectively. The management data of the manufacturer includes coaxiality, fatigue life, dimensional tolerance, number of process steps and yield rate. s represents the duration of a single manufacturer. The expression of the order data set is {D1 j 、D2 j 、D3 j 、...、Dn j}, D1 j To Dn j They are the demand data for the first to nth automobile modification parts orders. The management data of automobile modification parts orders include modification type, size area, material hardness, chromaticity value and customization quantity. j represents the delivery time of a single modification parts order.

[0016] Preferably, in step 2, the risk value Fxz calculation process is as follows:

[0017] S11. Extract the management data of the e-th supplier in the supply data set, and mark the name of the part provided by the e-th supplier as LM e , mark the number of parts provided by the e-th supplier as LS e , mark the unqualified quantity of the e-th supplier as LC e , mark the delivery time of the e-th supplier as e t ;

[0018] S12, each batch of parts delivered LM e Calculate the delivery rate JV of the e-th supplier when e , and its calculation formula is as follows:

[0019]

[0020] S13. Set a fixed-length monitoring period Q, count and analyze the delivery rate JV of the e-th supplier during the monitoring period Q. e The changing trend of the supply coefficient Gyxs is generated e , and its calculation formula is as follows:

[0021]

[0022] In the formula, ZJ represents the total number of deliveries by the e-th supplier during the monitoring period Q. represents the delivery rate of the e-th supplier in delivering the u-th batch of parts during the monitoring period Q, represents the average delivery rate of the e-th supplier during the monitoring period Q, According to the variance formula, the variance value obtained is the supply coefficient Gyxs of the e-th supplier. e ;

[0023] S14. Combine S11-S13 to calculate the risk value Fxz of the e-th supplier e , and its calculation formula is as follows:

[0024]

[0025] In the formula, α1 represents the evaluation weight for the supply coefficient. It represents the ratio of the number of unqualified parts to the number of parts, that is, the unqualified rate of the e-th supplier. α2 represents the evaluation weight for the unqualified rate, α1+α2=1, It means that according to the weights α1 and α2, the comprehensive supply coefficient and the unqualified rate, the risk value Fxz of the e-th supplier is obtained. At the end of a single monitoring cycle Q, the risk value Fxz will be recalculated.

[0026] Preferably, in step 2, the supplier ranking database GK establishes corresponding partitions according to different part names, and stores the management data of suppliers from low to high according to the risk value Fxz in each partition.

[0027] Preferably, in step 3, the quality coefficient Zlxs calculation process is as follows:

[0028] S21. Extract the management data of the fth manufacturer in the manufacturing data set, and mark the coaxiality of the fth manufacturer during production as TZ f , the fatigue life of the fth manufacturer is marked as PS f , mark the dimensional tolerance of the fth manufacturer as CU f , the process steps of the f-th manufacturer are marked as YB f , the yield rate of the fth manufacturer is marked as YL f ;

[0029] S22. Calculate the assembly accuracy Zujd of the fth manufacturer for each batch of products produced. f , and its calculation formula is as follows:

[0030] Zujd f =ω1×TZ f +ω2×PS f -ω3×CU f ;

[0031] In the formula, ω1 represents the evaluation weight for coaxiality, ω2 represents the evaluation weight for fatigue life, and ω3 represents the evaluation weight for dimensional tolerance. ω1+ω2+ω3=1, ω1×TZ f +ω2×PS f -ω3×CU fIt means that according to the weights of ω1, ω2 and ω3, the assembly accuracy Zujd of the fth manufacturer is obtained by combining coaxiality, fatigue life and dimensional tolerance. f ;

[0032] S23, combine S21-S22, calculate the quality coefficient Zlxs of the fth manufacturer f , and its calculation formula is as follows:

[0033]

[0034] In the formula, represents the evaluation weight for assembly accuracy, It represents the ratio of the yield rate to the number of process steps. Represents the evaluation weight for the ratio of yield rate to process steps, Indicates according to and Weight, comprehensive assembly accuracy, yield rate and process steps, the quality coefficient Zlxs of the fth manufacturer is obtained f , the update frequency of the assembly accuracy Zujd and quality coefficient Zlxs of a single manufacturer is consistent.

[0035] Preferably, in step three, the manufacturer ranking database ZK stores the management data of the manufacturers from high to low according to the quality coefficient Zlxs.

[0036] Preferably, in step 4, the calculation process of the customized duration Dzsc is as follows:

[0037] S31. Extract the demand data of the g-th automobile modification parts order in the order data set, and mark the modification type of the g-th automobile modification parts order as GL g , mark the size area of ​​the g-th car modification parts order as DC g , mark the material hardness of the g-th automobile modification parts order as GY g , mark the chromaticity value of the g-th car modification parts order as SD g , mark the customized quantity of the g-th car modification parts order as DS g , mark the delivery time of the g-th automobile modification parts order as g j ;

[0038] S32, calculate the difference data group CY of the g-th automobile modification parts order g , and its calculation formula is as follows:

[0039]

[0040] In the formula, BCH represents the standard size area when the manufacturer produces existing products, DCg -BCH represents the difference between the size area of ​​the g-th car modification parts order and the standard size area, BYD represents the standard material hardness when the manufacturer produces existing products, GY g -BYD represents the difference between the material hardness of the g-th car modification parts order and the standard material hardness, BSD represents the standard color value when the manufacturer produces existing products, SD g -BSD represents the difference between the chromaticity value of the g-th automobile modification parts order and the standard chromaticity value;

[0041] S33, according to the difference data group CY of the g-th automobile modification parts order g , determine the complexity level when the manufacturer produces the g-th automobile modification parts order, the first complexity level is higher than the second complexity level;

[0042] In the first case, the difference data set CY g If any of the values ​​is not equal to 0, it means that when the manufacturer produces the g-th automobile modification parts order, it needs to adjust the production process of the existing products to generate the first complexity level. g , while setting the delay parameter μ, generate the corresponding production line data group, where the delay parameter for performance modification is 5 days, the delay parameter for appearance modification is 4 days, the delay parameter for interior modification is 3 days, the delay parameter for functional modification is 4 days, and the delay parameter for electronic modification is 3 days;

[0043] In the second case, the difference data set CY g All values ​​in are 0, which means that when the manufacturer produces the g-th modification parts order, it does not need to adjust the manufacturer's production process to generate the second complexity level, and directly generate the corresponding production line data group;

[0044] S34. According to the management data of the g-th automobile modification parts order, set constraints, which include risk value Fxz, quality coefficient Zlxs, delivery time, construction period and logistics distance. Among the constraints, risk value Fxz and quality coefficient Zlxs have the highest priority, and delivery time and construction period have higher priority than logistics distance. Then, select production lines that meet the requirements of the g-th automobile modification parts order from the supplier ranking database GK and the manufacturer ranking database ZK, and generate a corresponding production line data group. The production line data group includes multiple production lines, and each production line includes multiple suppliers and a single manufacturer.

[0045] S35. In the first case, when generating the first complexity level, S33-S34 are combined to calculate the customization time Dzsc required for the manufacturer to produce the g-th automobile modification parts order. g , and its calculation formula is as follows:

[0046] Cxa = {Gi t ,...,Zk s},i∈y,k∈h;

[0047]

[0048] In the second case, when generating the first complexity level, S33-S34 are combined to calculate the customization time Dzsc required for the manufacturer to produce the g-th automobile modification part order. g , and its calculation formula is as follows:

[0049]

[0050] In the formula, Cx a represents the ath production line in the production line data group, including management data of multiple suppliers and a single manufacturer, b represents the total number of production lines in the production line data group, θ represents the conversion coefficient, θ×Cx a It means converting the supplier's delivery time t and the manufacturer's construction time s in the ath production line into the corresponding customization time.

[0051] Preferably, in step 5, if the delivery time of the g-th automobile modification parts order is g j Less than the customized time Dzsc g , and DS g When the quantity is lower than or included in the quantity threshold SLY, only one production line in the production line data group is selected to start the automobile modification parts order. If the delivery time of the g-th automobile modification parts order is g j Greater than or equal to the customized duration Dzsc g , and DS g When the quantity threshold SLY is exceeded, two production lines in the production line data group are selected to start the automobile modification parts order simultaneously. If the delivery time of the g-th automobile modification parts order is g j Greater than or equal to the customized duration Dzsc g , and DS g When the quantity exceeds twice the quantity threshold SLY, three production lines in the production line data group are selected to start the automobile modification parts order synchronously.

[0052] Preferably, in step six, if during the customization time Dzsc, the change in the risk value Fxz of a single supplier exceeds the risk fluctuation threshold FXY or the change in the quality coefficient Zlxs of a single manufacturer exceeds the quality fluctuation threshold ZLY, it indicates that the actual production situation no longer meets the demand for automobile modification parts orders, and it is necessary to re-screen new suppliers or manufacturers from the supplier ranking database GK and the manufacturer ranking database ZK for replacement.

[0053] Supply chain optimization decision-making system based on artificial intelligence, including customized service module, data analysis module, intelligent evaluation module and optimization decision-making module;

[0054] The customized service module is connected to the supply chain management system through the network to obtain the management data of all suppliers and manufacturers and the demand data of all automobile modification parts orders in real time, and classifies them into supply data set, manufacturing data set and order data set;

[0055] The data analysis module generates the corresponding supply coefficient Gyxs and risk value Fxz according to the supply data set, and forms a supplier ranking database GK. The data analysis module analyzes the assembly accuracy Zujd and quality coefficient Zlxs of each manufacturer according to the manufacturing data set, and forms a manufacturer ranking database ZK.

[0056] The intelligent evaluation module determines the complexity level of the manufacturer's production of automobile modification parts orders based on the supply data set, the manufacturing data set and the order data set, and then selects the production line data group that meets the automobile modification parts order requirements from the supplier ranking database GK and the manufacturer ranking database ZK, and calculates the customization time Dzsc;

[0057] The optimization decision module is set with a fixed range of quantity threshold SLY, risk fluctuation threshold FXY and quality fluctuation threshold ZLY, selects an appropriate number of production lines to start automobile modification parts orders, monitors the production situation of each production line during the customization time Dzsc, and then determines whether the actual production situation meets the requirements of automobile modification parts orders, and takes corresponding optimization measures.

[0058] Compared with the prior art, the present invention provides a method and system for supply chain optimization decision-making based on artificial intelligence, which has the following beneficial effects:

[0059] 1. The present invention connects the supply chain management system through the network through the customized service module, obtains the management data of all suppliers and manufacturers, as well as the demand data of all automobile modification parts orders in real time, and classifies them into supply data set, manufacturing data set and order data set. The data analysis module analyzes the Gyxs and risk value Fxz of each supplier, as well as the assembly accuracy Zujd and quality coefficient Zlxs of each manufacturer according to the supply data set and the manufacturing data set, and forms the supplier ranking database GK and the manufacturer ranking database ZK, ensuring that the update frequency of the database can be consistent with the information change frequency of each node in the supply chain. The intelligent evaluation module analyzes the automobile The differences between modified parts and existing products are used to judge the complexity level of manufacturers when producing automotive modified parts orders, and whether the production process of existing products needs to be adjusted. Then, production lines that meet the needs of automotive modified parts orders are screened out from the supplier ranking database GK and the manufacturer ranking database ZK, and the corresponding production line data group and customization time Dzsc are generated. When the existing production line cannot meet the complex needs of automotive modified parts, the most suitable production line is automatically matched from the supplier ranking database GK and the manufacturer ranking database ZK, reducing manual judgment and order delays, improving the response speed and efficiency of the entire production process, and the intelligent configuration of production lines is highly flexible.

[0060] 2. The present invention selects an appropriate number of production lines to start automobile modification parts orders through an optimization decision module, and monitors the production situation of each production line during the customization time Dzsc, and then determines whether the actual production situation meets the requirements of automobile modification parts orders, and performs corresponding optimization measures. If during the customization time Dzsc, the change in the risk value Fxz of a single supplier exceeds the risk fluctuation threshold FXY or the change in the quality coefficient Zlxs of a single manufacturer exceeds the quality fluctuation threshold ZLY, it means that the actual production situation no longer meets the requirements of automobile modification parts orders, which may easily lead to problems such as the quality of modified parts not meeting the order requirements or delayed delivery time. It is necessary to re-screen new suppliers or manufacturers from the supplier ranking database GK and the manufacturer ranking database ZK for replacement, and dynamically adjust the product quality to be more stable. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a step diagram of the method of the present invention;

[0062] Figure 2 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0063] 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.

[0064] Example 1

[0065] See also Figure 1 The present invention provides a method for optimizing supply chain decision-making based on artificial intelligence, comprising the following steps:

[0066] Step 1: Connect to the supply chain management system through the network to obtain the management data of all suppliers and manufacturers, as well as the demand data of all automobile modification parts orders in real time, and classify them into supply data set, manufacturing data set and order data set;

[0067] Step 2: According to the supply data set, analyze the delivery rate JV, the change trend of the delivery rate JV and the delivery risk of each supplier, generate the corresponding supply coefficient Gyxs and risk value Fxz, and form the supplier ranking database GK;

[0068] Step 3: Based on the manufacturing data set, analyze the assembly accuracy Zujd and quality coefficient Zlxs of each manufacturer and form a manufacturer ranking database ZK;

[0069] Step 4: Based on the supply data set, manufacturing data set and order data set, analyze the differences between modified auto parts and existing products, determine the complexity level of manufacturers in producing modified auto parts orders, and whether it is necessary to adjust the production process of existing products, and then select production lines that meet the needs of modified auto parts orders from the supplier ranking database GK and the manufacturer ranking database ZK, and generate the corresponding production line data group and customization time Dzsc;

[0070] Step 5: Set a fixed range quantity threshold SLY, and then combine the order data set and the production line data set to select an appropriate number of production lines to start the automobile modification parts order, and monitor the production status of each production line during the customization time Dzsc;

[0071] Step 6: Set a fixed range of risk fluctuation threshold FXY and quality fluctuation threshold ZLY, and then combine the production situation of each production line during the customization period Dzsc to determine whether the actual production situation meets the requirements of automobile modification parts orders, and take corresponding optimization measures.

[0072] In this embodiment, SQL query technology is used to obtain the management data of all suppliers and manufacturers and the demand data of all automobile modification parts orders from the supply chain management system in real time, and the data is classified into supply data sets, manufacturing data sets and order data sets. It helps artificial intelligence to obtain the required content more quickly and accurately when retrieving multi-terminal information. According to the supply data set, the delivery rate JV, the change trend of the delivery rate JV and the delivery risk of each supplier are analyzed, and the corresponding supply coefficient Gyxs and risk value Fxz are generated, and the supplier ranking database GK is formed. According to the manufacturing data set, the assembly accuracy Zujd and quality coefficient Zlxs of each manufacturer are analyzed, and the manufacturer ranking database ZK is formed. Based on the supply chain management system, two databases with ranking mechanisms are established. When the information and demand of each node in the supply chain change rapidly, the update frequency of the supplier ranking database GK and the manufacturer ranking database ZK can also be synchronized with the node changes. Analyze the differences between modified auto parts and existing products, determine the complexity level of manufacturers when producing modified auto parts orders, and whether it is necessary to adjust the production process of existing products, and then select production lines that meet the needs of modified auto parts orders from the supplier ranking database GK and the manufacturer ranking database ZK, and generate corresponding production line data groups and customization time Dzsc. When the existing production line cannot meet the complex needs of modified auto parts, the most suitable production line is automatically matched from the supplier ranking database GK and the manufacturer ranking database ZK, reducing manual judgment and order delays, and improving the response speed and efficiency of the entire production process. Select the appropriate number of production lines to start modified auto parts orders, and monitor the production status of each production line during the customization time Dzsc, determine whether the actual production situation meets the needs of modified auto parts orders, and take corresponding optimization measures to achieve the optimal allocation of supply chain resources and effectively avoid product quality problems.

[0073] Example 2

[0074] This embodiment is an explanation of the embodiment 1. Specifically, the original data in the supply chain management system is subjected to denoising, classification and labeling operations. The denoising process can avoid duplicate information in suppliers, manufacturers and automobile modification parts orders. The data is then classified and labeled according to the supplier company name. The expression of the supply data set is {G1 t , G2 t , G3 t ,...,Gy t}, G1 t To Gy t are the management data of the first to yth suppliers respectively. The management data of each supplier includes the part name, part quantity and defective quantity. t represents the delivery time of a single supplier. The management data is classified and marked according to the manufacturer's company name. The expression of the manufacturing data set is {Z1s 、Z2 s 、Z3 s 、...、Zh s}, Z1 s To Zh s are the management data of the first to the hth manufacturer, respectively. The management data of each manufacturer includes coaxiality, fatigue life, dimensional tolerance, number of process steps and yield rate. s represents the duration of a single manufacturer. According to the order time of automobile modification parts, the demand data are arranged from early to late and marked in sequence. The expression of the order data set is {D1 j 、D2 j 、D3 j 、...、Dn j}, D1 j To Dn j are the demand data of the first to nth car modification parts orders, and the management data of each car modification parts order includes modification type, size area, material hardness, color value and customized quantity. j represents the delivery time of a single modification parts order. The classified and marked supply data set and manufacturing data set represent the supply side of the market supply and demand relationship, while the order data set represents the demand side of the market supply and demand relationship.

[0075] Example 3

[0076] This embodiment is an explanation of the embodiment 1. Specifically, the risk value Fxz calculation process is as follows:

[0077] S11. Extract the management data of the e-th supplier in the supply data set, and mark the name of the part provided by the e-th supplier as LM e , mark the number of parts provided by the e-th supplier as LS e , mark the unqualified quantity of the e-th supplier as LC e , mark the delivery time of the e-th supplier as e t ;

[0078] S12, each batch of parts delivered LM e Calculate the delivery rate JV of the e-th supplier when e , and its calculation formula is as follows:

[0079]

[0080] S13. Set a fixed-length monitoring period Q, count and analyze the delivery rate JV of the e-th supplier during the monitoring period Q. e The changing trend of the supply coefficient Gyxs is generated e , and its calculation formula is as follows:

[0081]

[0082] In the formula, ZJ represents the total number of deliveries by the e-th supplier during the monitoring period Q. represents the delivery rate of the e-th supplier in delivering the u-th batch of parts during the monitoring period Q, represents the average delivery rate of the e-th supplier during the monitoring period Q, According to the variance formula, the variance value obtained is the supply coefficient Gyxs of the e-th supplier. e ;

[0083] S14. Combine S11-S13 to calculate the risk value Fxz of the e-th supplier e , and its calculation formula is as follows:

[0084]

[0085] In the formula, α1 represents the evaluation weight for the supply coefficient. It represents the ratio of the number of unqualified parts to the number of parts, that is, the unqualified rate of the e-th supplier. α2 represents the evaluation weight for the unqualified rate, α1+α2=1, It means that the risk value Fxz of the e-th supplier is obtained according to the weights of α1 and α2, the comprehensive supply coefficient and the non-conformity rate. At the end of a single monitoring period Q, the risk value Fxz will be recalculated;

[0086] Specific numerical examples:

[0087] A supplier producing wheel hub bearings is selected as the experimental object. The calculation process of the risk value Fxz of this supplier is as follows:

[0088] S11. The number of parts provided by the supplier is 100, the number of unqualified parts of the supplier is 3, and the delivery time of the supplier is 5 days;

[0089] S12. The supplier's delivery rate JV for each batch of wheel hub bearings delivered e The calculation formula is as follows:

[0090]

[0091] S13. Set the fixed monitoring period Q to 20 days. During the monitoring period Q, the supplier's delivery rate JV e The supply coefficient of this supplier is Gyxs, which is 20, 18, 16, 22 and 19 units per day respectively. e The calculation formula is as follows:

[0092]

[0093] In the formula, ZJ means that during the monitoring period Q, the total number of deliveries by the supplier is 5. It means that during the monitoring period Q, the supplier's delivery rate for the uth batch of parts is 20 per day. It means that during the monitoring period Q, the average delivery rate of the supplier is 19 per day. According to the variance formula, the variance value 4 is the supply coefficient Gyxs of the supplier. e ;

[0094] S14. Combine S11-S13 to calculate the risk value Fxz of the supplier e , and its calculation formula is as follows:

[0095]

[0096] In the formula, 0.6 represents the evaluation weight for the supply coefficient. It represents the ratio of the number of unqualified parts to the number of parts, that is, the supplier's unqualified rate. 0.4 represents the evaluation weight for the unqualified rate. 0.6+0.4=1. It means that according to the α1 and α2 weights, the comprehensive supply coefficient and the non-conformity rate, the risk value Fxz of the supplier is 2.412. At the end of a single monitoring period Q, the risk value Fxz will be recalculated;

[0097] In this embodiment, each supplier has a corresponding risk value Fxz. The higher the risk value Fxz, the worse the stability of the supplier's normal delivery of parts. The supplier ranking database GK establishes corresponding partitions according to different part names, such as wheel hub bearing partition, wheel hub cover partition, wheel hub bolt partition, etc. In each partition, the ranking mechanism stores the management data of suppliers from low to high according to the risk value Fxz.

[0098] Example 4

[0099] This embodiment is an explanation of the embodiment 3. Specifically, the quality coefficient Zlxs calculation process is as follows:

[0100] S21. Extract the management data of the fth manufacturer in the manufacturing data set, and mark the coaxiality of the fth manufacturer during production as TZ f , the fatigue life of the fth manufacturer is marked as PS f , mark the dimensional tolerance of the fth manufacturer as CU f , the process steps of the f-th manufacturer are marked as YB f , the yield rate of the fth manufacturer is marked as YL f ;

[0101] S22. Calculate the assembly accuracy Zujd of the fth manufacturer for each batch of products produced. f , and its calculation formula is as follows:

[0102] Zujd f =ω1×TZ f +ω2×PS f -ω3×CU f ;

[0103] In the formula, ω1 represents the evaluation weight for coaxiality, ω2 represents the evaluation weight for fatigue life, and ω3 represents the evaluation weight for dimensional tolerance. ω1+ω2+ω3=1, ω1×TZ f +ω2×PS f -ω3×CU f It means that according to the weights of ω1, ω2 and ω3, the assembly accuracy Zujd of the fth manufacturer is obtained by combining coaxiality, fatigue life and dimensional tolerance. f ;

[0104] S23, combine S21-S22, calculate the quality coefficient Zlxs of the fth manufacturer f , and its calculation formula is as follows:

[0105]

[0106] In the formula, represents the evaluation weight for assembly accuracy, It represents the ratio of the yield rate to the number of process steps. Represents the evaluation weight for the ratio of yield rate to process steps, Indicates according to and Weight, comprehensive assembly accuracy, yield rate and process steps, the quality coefficient Zlxs of the fth manufacturer is obtained f , the update frequency of assembly accuracy Zujd and quality coefficient Zlxs of a single manufacturer is consistent;

[0107] Specific numerical examples:

[0108] The manufacturer of assembled wheel hubs was selected as the experimental object. The calculation process of the manufacturer's quality coefficient Zlxs is as follows:

[0109] S21, obtaining that the coaxiality of the wheel hub assembled by the manufacturer is 0.05 mm, the fatigue life of the wheel hub assembled by the manufacturer is 50,000 kilometers, the dimensional tolerance of the wheel hub assembled by the manufacturer is 0.02 mm, the number of process steps of the wheel hub assembled by the manufacturer is 5 steps, and the yield rate of the wheel hub assembled by the manufacturer is 95%;

[0110] S22. Calculate the manufacturer’s assembly accuracy Zujd for each batch of products produced. f , and its calculation formula is as follows:

[0111] Zujd f =0.3×0.05+0.4×5-0.3×0.02=1.999;

[0112] In the formula, 0.3 represents the evaluation weight for coaxiality, 0.4 represents the evaluation weight for fatigue life, and 0.3 represents the evaluation weight for dimensional tolerance. 0.3+0.4+0.3=1, ω1×TZ f +ω2×PS f -ω3×CU f It means that according to the weights of ω1, ω2 and ω3, the manufacturer's assembly accuracy Zujd is obtained by combining coaxiality, fatigue life and dimensional tolerance. f is 1.999;

[0113] S23, combine S21-S22 to calculate the manufacturer's quality factor Zlxs f , and its calculation formula is as follows:

[0114]

[0115] In the formula, 0.6 represents the evaluation weight for assembly accuracy. represents the ratio of yield rate to process steps, 0.4 represents the evaluation weight for the ratio of yield rate to process steps, 0.6+0.4=1, Indicates according to and Weight, comprehensive assembly accuracy, yield rate and process steps, to obtain the manufacturer's quality coefficient Zlxs f It is 1.2754, and the update frequency of the assembly accuracy Zujd and the quality coefficient Zlxs of a single manufacturer is consistent;

[0116] In this embodiment, each manufacturer has a corresponding quality coefficient Zlxs. The higher the quality coefficient Zlxs is, the better the quality of the products produced by the manufacturer is. The manufacturer ranking database ZK stores the management data of the manufacturer from high to low according to the quality coefficient Zlxs.

[0117] Example 5

[0118] This embodiment is an explanation of the embodiment 4. Specifically, the calculation process of the customized duration Dzsc is as follows:

[0119] S31. Extract the demand data of the g-th automobile modification parts order in the order data set, and mark the modification type of the g-th automobile modification parts order as GL g, mark the size area of ​​the g-th car modification parts order as DC g , mark the material hardness of the g-th automobile modification parts order as GY g , mark the chromaticity value of the g-th car modification parts order as SD g , mark the customized quantity of the g-th car modification parts order as DS g , mark the delivery time of the g-th automobile modification parts order as g j ;

[0120] S32, calculate the difference data group CY of the g-th automobile modification parts order g , and its calculation formula is as follows:

[0121]

[0122] In the formula, BCH represents the standard size area when the manufacturer produces existing products, DC g -BCH represents the difference between the size area of ​​the g-th car modification parts order and the standard size area, BYD represents the standard material hardness when the manufacturer produces existing products, GY g -BYD represents the difference between the material hardness of the g-th car modification parts order and the standard material hardness, BSD represents the standard color value when the manufacturer produces existing products, SD g -BSD represents the difference between the chromaticity value of the g-th automobile modification parts order and the standard chromaticity value;

[0123] S33, according to the difference data group CY of the g-th automobile modification parts order g , determine the complexity level when the manufacturer produces the g-th automobile modification parts order, the first complexity level is higher than the second complexity level;

[0124] In the first case, the difference data set CY g If any of the values ​​is not equal to 0, it means that when the manufacturer produces the g-th automobile modification parts order, it needs to adjust the production process of the existing products to generate the first complexity level. g , while setting the delay parameter ω, generate the corresponding production line data group, where the delay parameter for performance modification is 5 days, the delay parameter for appearance modification is 4 days, the delay parameter for interior modification is 3 days, the delay parameter for functional modification is 4 days, and the delay parameter for electronic modification is 3 days;

[0125] In the second case, the difference data set CY g All values ​​in are 0, which means that when the manufacturer produces the g-th modification parts order, it does not need to adjust the manufacturer's production process to generate the second complexity level, and directly generate the corresponding production line data group;

[0126] S34. According to the management data of the g-th automobile modification parts order, set constraints, which include risk value Fxz, quality coefficient Zlxs, delivery time, construction period and logistics distance. Among the constraints, risk value Fxz and quality coefficient Zlxs have the highest priority, and delivery time and construction period have higher priority than logistics distance. Then, select production lines that meet the requirements of the g-th automobile modification parts order from the supplier ranking database GK and the manufacturer ranking database ZK, and generate a corresponding production line data group. The production line data group includes multiple production lines, and each production line includes multiple suppliers and a single manufacturer.

[0127] S35. In the first case, when generating the first complexity level, S33-S34 are combined to calculate the customization time Dzsc required for the manufacturer to produce the g-th automobile modification parts order. g , and its calculation formula is as follows:

[0128] Cx a = {Gi t ,...,Zk s},i∈y,k∈h;

[0129]

[0130] In the second case, when generating the first complexity level, S33-S34 are combined to calculate the customization time Dzsc required for the manufacturer to produce the g-th automobile modification part order. g , and its calculation formula is as follows:

[0131]

[0132] In the formula, Cx a represents the ath production line in the production line data group, including management data of multiple suppliers and a single manufacturer, b represents the total number of production lines in the production line data group, θ represents the conversion coefficient, θ×Cx a It means that the supplier's delivery time t and the manufacturer's construction time s in the a-th production line are converted into the corresponding customization time;

[0133] Specific numerical examples:

[0134] The wheel hub modification parts are selected as the experimental objects. The wheel hub modification parts belong to the performance modification. The calculation process of the production line data group and the customization time Dzsc of the wheel hub modification parts order is as follows:

[0135] S31. Obtain the size, area, material hardness, color value and customized quantity of each wheel hub modification part in the automobile modification parts order. The delivery time of the automobile modification parts order is uniformly 5 days.

[0136] S32, calculate the difference data group CY of the automobile modification parts orderg , and its calculation formula is as follows:

[0137]

[0138] In the formula, BCH represents the standard size area when the manufacturer produces existing products, which is 254in 2 , D.C. g -BCH represents the difference between the size and area of ​​the modified car parts order and the standard size and area, BYD represents the standard material hardness of the manufacturer's existing products, which is 90HB, GY g -BYD represents the difference between the material hardness of the modified car parts order and the standard material hardness. BSD represents the standard color value when the manufacturer produces existing products, which is RGB (169, 169, 169). SD g -BSD represents the difference between the chromaticity value of the g-th automobile modification parts order and the standard chromaticity value;

[0139] S33, please refer to Table 1, according to the difference data group CY of the automobile modification parts order g , determine the complexity level of the manufacturer when producing the g-th automobile modification parts order;

[0140] In the first case, the difference data set CY g If any of the values ​​is not equal to 0, it means that when the manufacturer produces the g-th automobile modification parts order, it needs to adjust the production process of the existing products to generate the first complexity level. The modification type GL of this automobile modification parts order g The corresponding delay parameter h is 5 days, and the corresponding production line data group is generated;

[0141] In the second case, the difference data set CY g All values ​​in are 0, which means that when the manufacturer produces the g-th modification parts order, it does not need to adjust the manufacturer's production process to generate the second complexity level, and directly generate the corresponding production line data group;

[0142]

[0143] Table 1

[0144] S34. Refer to Table 2. According to the management data of the automobile modification parts order, set constraints. The constraints include risk value Fxz, quality coefficient Zlxs, delivery time, construction period and logistics distance. Among the constraints, risk value Fxz and quality coefficient Zlxs have the highest priority, and delivery time and construction period have higher priority than logistics distance. Then, select the production line that meets the requirements of the g-th automobile modification parts order from the supplier ranking database GK and the manufacturer ranking database ZK, and generate the corresponding production line data group. The production line data group includes multiple production lines, and each production line includes multiple suppliers and a single manufacturer.

[0145]

[0146] Table 2

[0147] Specifically, when the risk value Fxz and the quality coefficient Zlxs are given priority, the quality coefficient Zlxs of line 4 is the highest, the risk value is low, and the delivery time and construction period are moderate. Line 4 is the production line with the best configuration. When the delivery time and construction period are considered secondarily, the quality coefficient of line 1 is high, the risk value is low, and the delivery time and construction period are moderate. The defect is that the logistics distance is long, which is suitable for processing non-urgent orders. When the logistics distance is considered secondarily, although the risk value Fxz and the quality coefficient Zlxs of line 2 are relatively low, the delivery time and construction period are short, and the logistics distance is relatively short, which is suitable for processing urgent orders with low complexity level;

[0148] S35. Please refer to Table 3 and combine S33-S34 to calculate the customization time Dzsc required for the manufacturer to produce this automobile modification part order. g , and its calculation formula is as follows:

[0149] If the manufacturer produces this car modification parts order, it needs to adjust the production process of the existing products, and the processing is highly complex.

[0150] Cx a = {Gi t ,...,Zk s},i∈y,k∈h;

[0151]

[0152] If the manufacturer produces this modified parts order, there is no need to adjust the manufacturer's production process, and the processing complexity is low.

[0153]

[0154] In the formula, Cx arepresents the ath production line in the production line data group, including the management data of multiple suppliers and a single manufacturer, b represents the total number of production lines in the production line data group, θ represents the conversion coefficient, which is derived from the logistics delivery speed at the current time point. The faster the logistics delivery speed, the smaller the conversion coefficient. θ×Cx a It means that the supplier's delivery time t and the manufacturer's construction time s in the a-th production line are converted into the corresponding customization time;

[0155] When the conversion coefficient θ at the current time point is 0.8, the customization time of each wheel hub modification part in the car modification part order is calculated. Among them, the customization time of wheel hub modification part 2 and wheel hub modification part 3 requires an additional delay parameter μ, and the delay parameter μ is 5 days;

[0156]

[0157] Table 3

[0158] Example 6

[0159] This embodiment is an explanation of the embodiment 5. Specifically, the quantity threshold SLY is derived from the upper limit of the assembly of a single batch of the production line, the risk fluctuation threshold FXY is derived from the enterprise's evaluation criteria for suppliers, and the quality fluctuation threshold ZLY is derived from the enterprise's evaluation criteria for manufacturers. If the delivery time of the automobile modification parts order is g j Less than the customized time Dzsc g , and DS g When the quantity is lower than or included in the quantity threshold SLY, only one production line in the production line data group is selected to start the automobile modification parts order. If the delivery time of the g-th automobile modification parts order is g j Greater than or equal to the customized duration Dzsc g , and DS g When the quantity threshold SLY is exceeded, two production lines in the production line data group are selected to start the automobile modification parts order simultaneously. If the delivery time of the g-th automobile modification parts order is g j Greater than or equal to the customized duration Dzsc g , and DS g When the quantity exceeds twice the threshold value SLY, three production lines in the production line data group are selected to start the automobile modification parts order synchronously;

[0160] While the production line synchronously starts the automobile modification parts order, it will also monitor the production situation of each production line during the customization time Dzsc through the supply chain management system, judge in real time whether the actual production situation meets the automobile modification parts order requirements, and take corresponding optimization measures. If during the customization time Dzsc, the change in the risk value Fxz of a single supplier exceeds the risk fluctuation threshold FXY or the change in the quality coefficient Zlxs of a single manufacturer exceeds the quality fluctuation threshold ZLY, it means that the actual production situation no longer meets the automobile modification parts order requirements, and it is necessary to re-screen new suppliers or manufacturers from the supplier ranking database GK and the manufacturer ranking database ZK for replacement.

[0161] Example 7

[0162] See also Figure 2 , the supply chain optimization decision-making system based on artificial intelligence includes a customized service module, a data analysis module, an intelligent evaluation module and an optimization decision-making module;

[0163] The customized service module connects to the supply chain management system through the network, obtains the management data of all suppliers and manufacturers, as well as the demand data of all automobile modification parts orders in real time, and classifies them into supply data sets, manufacturing data sets and order data sets;

[0164] The data analysis module generates the corresponding supply coefficient Gyxs and risk value Fxz based on the supply data set, and forms the supplier ranking database GK. The data analysis module analyzes the assembly accuracy Zujd and quality coefficient Zlxs of each manufacturer based on the manufacturing data set, and forms the manufacturer ranking database ZK.

[0165] The intelligent evaluation module determines the complexity level of the manufacturer's production of automobile modification parts orders based on the supply data set, manufacturing data set and order data set, and then selects the production line data group that meets the requirements of automobile modification parts orders from the supplier ranking database GK and the manufacturer ranking database ZK, and calculates the customization time Dzsc;

[0166] The optimization decision module is set with a fixed range of quantity threshold SLY, risk fluctuation threshold FXY and quality fluctuation threshold ZLY. It selects an appropriate number of production lines to start automobile modification parts orders, monitors the production situation of each production line during the customization time Dzsc, and then determines whether the actual production situation meets the requirements of automobile modification parts orders, and takes corresponding optimization measures.

[0167] In this embodiment, the manufacturer ranking database ZK and the manufacturer ranking database ZK are established to provide more accurate data support for production line configuration, and also eliminate the information barriers between multiple nodes of the supply management system. The intelligent configuration production line is highly flexible. According to the supply data set, the manufacturing data set and the order data set, the complexity level of the manufacturer when producing the automobile modification parts order is judged, and then the production line data group that meets the automobile modification parts order requirements is screened out from the supplier ranking database GK and the manufacturer ranking database ZK, and the customization time Dzsc is calculated. Different types of modified parts correspond to different complexity level judgment conditions. For example, for appearance modified parts, the judgment conditions are coating thickness, surface roughness, etc. The intelligent configuration production line is highly flexible. After selecting an appropriate number of production lines to start the automobile modification parts order, the production situation of each production line during the customization time Dzsc is monitored to determine whether the actual production situation meets the automobile modification parts order requirements, and corresponding optimization measures are taken. When the quality of the modified parts does not meet the order requirements or the delivery time is delayed, the supplier and manufacturer can be replaced in time, and the product quality can be dynamically adjusted to be more stable.

[0168] 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.

Claims

1. A method for optimizing supply chain decisions based on artificial intelligence, characterized in that: The following steps are involved: Step 1: Connect to the supply chain management system through the network to obtain the management data of all suppliers and manufacturers, as well as the demand data of all automobile modification parts orders in real time, and classify them into supply data set, manufacturing data set and order data set; Step 2: According to the supply data set, analyze the delivery rate JV, the change trend of the delivery rate JV and the delivery risk of each supplier, generate the corresponding supply coefficient Gyxs and risk value Fxz, and form the supplier ranking database GK; Step 3: Based on the manufacturing data set, analyze the assembly accuracy Zujd and quality coefficient Zlxs of each manufacturer and form a manufacturer ranking database ZK; Step 4: Based on the supply data set, manufacturing data set and order data set, analyze the differences between modified auto parts and existing products, determine the complexity level of manufacturers in producing modified auto parts orders, and whether it is necessary to adjust the production process of existing products, and then select production lines that meet the needs of modified auto parts orders from the supplier ranking database GK and the manufacturer ranking database ZK, and generate the corresponding production line data group and customization time Dzsc; Step 5: Set a fixed range quantity threshold SLY, and then combine the order data set and the production line data set to select an appropriate number of production lines to start the automobile modification parts order, and monitor the production status of each production line during the customization time Dzsc; Step 6: Set a fixed range of risk fluctuation threshold FXY and quality fluctuation threshold ZLY, and then combine the production situation of each production line during the customization period Dzsc to determine whether the actual production situation meets the requirements of automobile modification parts orders, and take corresponding optimization measures.

2. The method for optimizing supply chain decisions based on artificial intelligence according to claim 1, characterized in that: In step 1, the expression of the supplied data set is {G1 t , G2 t 、G3 t ,...,Gy t }, G1 t To Gy t are the management data of the first to yth suppliers respectively. The management data of suppliers include part name, part quantity and defective quantity. t represents the delivery time of a single supplier. The expression of the manufacturing data set is {Z1 s 、Z2 s 、Z3 s 、...、Zh s }, Z1 s To Zh s are the management data of the first to the hth manufacturer, respectively. The management data of the manufacturer includes coaxiality, fatigue life, dimensional tolerance, number of process steps and yield rate. s represents the duration of a single manufacturer. The expression of the order data set is {D1 j 、D2 j 、D3 j 、...、Dn j }, D1 j To Dn j They are the demand data for the first to nth automobile modification parts orders. The management data of automobile modification parts orders include modification type, size area, material hardness, chromaticity value and customization quantity. j represents the delivery time of a single modification parts order.

3. The method for optimizing supply chain decision-making based on artificial intelligence according to claim 2, characterized in that: In step 2, the risk value Fxz calculation process is as follows: S11. Extract the management data of the e-th supplier in the supply data set, and mark the name of the part provided by the e-th supplier as LM e , mark the number of parts provided by the e-th supplier as LS e , mark the unqualified quantity of the e-th supplier as LC e , mark the delivery time of the e-th supplier as e t ; S12, each batch of parts delivered LM e Calculate the delivery rate JV of the e-th supplier when e , and its calculation formula is as follows: S13. Set a fixed-length monitoring period Q, count and analyze the delivery rate JV of the e-th supplier during the monitoring period Q. e The changing trend of the supply coefficient Gyxs is generated e , and its calculation formula is as follows: In the formula, ZJ represents the total number of deliveries by the e-th supplier during the monitoring period Q. represents the delivery rate of the e-th supplier in delivering the u-th batch of parts during the monitoring period Q, represents the average delivery rate of the e-th supplier during the monitoring period Q, According to the variance formula, the variance value obtained is the supply coefficient Gyxs of the e-th supplier. e ; S14. Combine S11-S13 to calculate the risk value Fxz of the e-th supplier e , and its calculation formula is as follows: In the formula, α1 represents the evaluation weight for the supply coefficient. It represents the ratio of the number of unqualified parts to the number of parts, that is, the unqualified rate of the e-th supplier. α2 represents the evaluation weight for the unqualified rate, α1+α2=1, It means that according to the weights α1 and α2, the comprehensive supply coefficient and the unqualified rate, the risk value Fxz of the e-th supplier is obtained. At the end of a single monitoring cycle Q, the risk value Fxz will be recalculated.

4. The method for optimizing supply chain decision-making based on artificial intelligence according to claim 3 is characterized by: In the step 2, the supplier ranking database GK establishes corresponding partitions according to different part names, and stores the management data of suppliers from low to high according to the risk value Fxz in each partition.

5. The method for optimizing supply chain decision-making based on artificial intelligence according to claim 4, characterized in that: In step 3, the quality coefficient Zlxs calculation process is as follows: S21. Extract the management data of the fth manufacturer in the manufacturing data set, and mark the coaxiality of the fth manufacturer during production as TZ f , the fatigue life of the fth manufacturer is marked as PS f , mark the dimensional tolerance of the fth manufacturer as CU f , mark the process steps of the f-th manufacturer as YB f , the yield rate of the fth manufacturer is marked as YL f ; S22. Calculate the assembly accuracy Zujd of the fth manufacturer for each batch of products produced. f , and its calculation formula is as follows: Zujd f =ω1×TZ f +ω2×PS f -ω3×CU f ; In the formula, ω1 represents the evaluation weight for coaxiality, ω2 represents the evaluation weight for fatigue life, and ω3 represents the evaluation weight for dimensional tolerance. ω1+ω2+ω3=1, ω1×TZ f +ω2×PS f -ω3×CU f It means that according to the weights of ω1, ω2 and ω3, the assembly accuracy Zujd of the fth manufacturer is obtained by combining coaxiality, fatigue life and dimensional tolerance. f ; S23, combine S21-S22, calculate the quality coefficient Zlxs of the fth manufacturer f , and its calculation formula is as follows: In the formula, represents the evaluation weight for assembly accuracy, It represents the ratio of yield rate to process steps. Represents the evaluation weight for the ratio of yield rate to process steps, Indicates according to and Weight, comprehensive assembly accuracy, yield rate and process steps, to obtain the quality coefficient Zlxs of the fth manufacturer f , the update frequency of the assembly accuracy Zujd and quality coefficient Zlxs of a single manufacturer is consistent.

6. The method for optimizing supply chain decision-making based on artificial intelligence according to claim 3, characterized in that: In the step three, the manufacturer ranking database ZK stores the management data of the manufacturers from high to low according to the quality coefficient Zlxs.

7. The method for optimizing supply chain decision-making based on artificial intelligence according to claim 3, characterized in that: In step 4, the calculation process of the customized duration Dzsc is as follows: S31. Extract the demand data of the g-th automobile modification parts order in the order data set, and mark the modification type of the g-th automobile modification parts order as GL g , mark the size area of ​​the g-th car modification parts order as DC g , mark the material hardness of the g-th automobile modification parts order as GY g , mark the chromaticity value of the g-th car modification parts order as SD g , mark the customized quantity of the g-th car modification parts order as DS g , mark the delivery time of the g-th automobile modification parts order as g j ; S32, calculate the difference data group CY of the g-th automobile modification parts order g , and its calculation formula is as follows: In the formula, BCH represents the standard size area when the manufacturer produces existing products, DC g -BCH represents the difference between the size area of ​​the g-th car modification parts order and the standard size area, BYD represents the standard material hardness when the manufacturer produces existing products, GY g -BYD represents the difference between the material hardness of the g-th car modification parts order and the standard material hardness, BSD represents the standard color value when the manufacturer produces existing products, SD g -BSD represents the difference between the chromaticity value of the g-th automobile modification parts order and the standard chromaticity value; S33, according to the difference data group CY of the g-th automobile modification parts order g , determine the complexity level when the manufacturer produces the g-th automobile modification parts order, the first complexity level is higher than the second complexity level; In the first case, the difference data set CY g If any of the values ​​is not equal to 0, it means that when the manufacturer produces the g-th automobile modification parts order, it needs to adjust the production process of the existing products to generate the first complexity level. g , while setting the delay parameter μ, generate the corresponding production line data group, where the delay parameter for performance modification is 5 days, the delay parameter for appearance modification is 4 days, the delay parameter for interior modification is 3 days, the delay parameter for functional modification is 4 days, and the delay parameter for electronic modification is 3 days; In the second case, the difference data set CY g All values ​​in are 0, which means that when the manufacturer produces the g-th modification parts order, it does not need to adjust the manufacturer's production process to generate the second complexity level, and directly generate the corresponding production line data group; S34. According to the management data of the g-th automobile modification parts order, set constraints, which include risk value Fxz, quality coefficient Zlxs, delivery time, construction period and logistics distance. Among the constraints, risk value Fxz and quality coefficient Zlxs have the highest priority, and delivery time and construction period have higher priority than logistics distance. Then, select production lines that meet the requirements of the g-th automobile modification parts order from the supplier ranking database GK and the manufacturer ranking database ZK, and generate a corresponding production line data group. The production line data group includes multiple production lines, and each production line includes multiple suppliers and a single manufacturer. S35. In the first case, when generating the first complexity level, S33-S34 are combined to calculate the customization time Dzsc required for the manufacturer to produce the g-th automobile modification parts order. g , and its calculation formula is as follows: Cx a ={Gi t ,...,Zk s },i∈y,k∈h; In the second case, when generating the first complexity level, S33-S34 are combined to calculate the customization time Dzsc required for the manufacturer to produce the g-th automobile modification part order. g , and its calculation formula is as follows: In the formula, Cx a represents the ath production line in the production line data group, including management data of multiple suppliers and a single manufacturer, b represents the total number of production lines in the production line data group, θ represents the conversion coefficient, θ×Cx a It means converting the supplier's delivery time t and the manufacturer's construction time s in the ath production line into the corresponding customization time.

8. The method for optimizing supply chain decision-making based on artificial intelligence according to claim 3 is characterized by: In step 5, if the delivery time of the g-th automobile modification parts order is g j Less than the customized time Dzsc g , and the customized quantity DS of the g-th automobile modification parts order g When the quantity is lower than or included in the quantity threshold SLY, only one production line in the production line data group is selected to start the automobile modification parts order. If the delivery time of the g-th automobile modification parts order is g j Greater than or equal to the customized duration Dzsc g , and the customized quantity DS of the g-th automobile modification parts order g When the quantity threshold SLY is exceeded, two production lines in the production line data group are selected to start the automobile modification parts order simultaneously. If the delivery time of the g-th automobile modification parts order is g j Greater than or equal to the customized duration Dzsc g , and the customized quantity DS of the g-th automobile modification parts order g When the quantity exceeds twice the quantity threshold SLY, three production lines in the production line data group are selected to start the automobile modification parts order synchronously.

9. The method for optimizing supply chain decision-making based on artificial intelligence according to claim 8, characterized in that: In step six, if during the customization time Dzsc, the change in the risk value Fxz of a single supplier exceeds the risk fluctuation threshold FXY or the change in the quality coefficient Zlxs of a single manufacturer exceeds the quality fluctuation threshold ZLY, it means that the actual production situation no longer meets the demand for automobile modification parts orders, and it is necessary to re-screen new suppliers or manufacturers from the supplier ranking database GK and the manufacturer ranking database ZK for replacement.

10. A supply chain optimization decision system based on artificial intelligence, applied to a supply chain optimization decision method based on artificial intelligence as claimed in any one of claims 1 to 9, characterized in that: Including customized service module, data analysis module, intelligent evaluation module and optimized decision module; The customized service module is connected to the supply chain management system through the network to obtain the management data of all suppliers and manufacturers and the demand data of all automobile modification parts orders in real time, and classifies them into supply data set, manufacturing data set and order data set; The data analysis module generates the corresponding supply coefficient Gyxs and risk value Fxz according to the supply data set, and forms a supplier ranking database GK. The data analysis module analyzes the assembly accuracy Zujd and quality coefficient Zlxs of each manufacturer according to the manufacturing data set, and forms a manufacturer ranking database ZK. The intelligent evaluation module determines the complexity level of the manufacturer's production of automobile modification parts orders based on the supply data set, the manufacturing data set and the order data set, and then selects the production line data group that meets the automobile modification parts order requirements from the supplier ranking database GK and the manufacturer ranking database ZK, and calculates the customization time Dzsc; The optimization decision module is set with a fixed range of quantity threshold SLY, risk fluctuation threshold FXY and quality fluctuation threshold ZLY, selects an appropriate number of production lines to start automobile modification parts orders, monitors the production situation of each production line during the customization time Dzsc, and then determines whether the actual production situation meets the requirements of automobile modification parts orders, and takes corresponding optimization measures.

Images