Intelligent warehouse management system of automobile supply chain KD import part

Abstract

The invention relates to the technical field of warehouse management, in particular to an intelligent warehouse management system of an automobile supply chain KD import part. Through the particle swarm optimization algorithm, automatic warehousing scheduling is achieved, storage position distribution is optimized, manual intervention is reduced, the warehouse space utilization rate is increased, and the optimal efficiency of goods storage and taking is ensured. Through the combination of the RFID technology and the environment sensor, accurate inventory tracking and state monitoring are realized, and the accuracy and real-time performance of inventory management are further improved. The ex-warehouse management system is optimized, transportation equipment task allocation is performed based on the minimum operation cost, and ex-warehouse efficiency is effectively improved. The warehouse-out task is automatically generated and optimized allocation is carried out based on the inventory state and the availability of the transportation tool, so that timely response to the warehouse-out demand is ensured, the transportation path and mode can be dynamically adjusted according to the actual condition of the transportation tool, the transportation cost is reduced, the resource allocation is optimized, and the overall logistics efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse management, and in particular to an intelligent warehouse management system for KD imported parts in an automobile supply chain. Background Art

[0002] The automotive supply chain refers to the entire process from raw material procurement, parts production, assembly, transportation to final sales. Since automobile manufacturing requires a large number of parts, technology and raw materials, its supply chain is extremely complex, involving multiple industrial links and multinational companies. KD imported parts (Knocked-Down parts) refer to a collection of disassembled auto parts. Unlike fully assembled imported vehicles, KD parts are assembled locally for final assembly production.

[0003] With the increasing complexity of the global automotive supply chain and the increasing demand, traditional warehouse management systems can no longer meet the modern automotive industry's requirements for efficient, accurate and flexible management. As a common form of logistics, KD imported parts in automobile manufacturing contain multiple parts and accessories. Its accurate inventory management and efficient scheduling system are crucial to the smooth operation of the entire supply chain.

[0004] However, most of the existing KD import parts warehouse management systems rely on manual management and traditional calculation methods, which leads to waste of storage space, inefficiency in the warehousing process, and untimely response to emergencies. The existence of these problems not only affects the efficiency of warehouse management, but also increases the cost of inventory management, thus affecting the smooth operation of the entire supply chain.

[0005] In view of the above problems, it is necessary to propose an intelligent warehouse management system for KD imported parts in the automobile supply chain. Summary of the invention

[0006] The purpose of the present invention is to solve the problems existing in the background technology and to propose an intelligent warehouse management system for KD imported parts in the automobile supply chain.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An intelligent warehouse management system for KD imported parts in an automobile supply chain includes a data collection module, a warehousing scheduling module, a tracking and management module, a warehouse delivery management module and an interaction module.

[0009] The data collection module obtains the arrival information of each batch of KD imported parts, including the unique identifier i of the KD imported parts, the type identifier Type_i, the quantity Quantity_i, the specification Size_i and the arrival date Date_i.

[0010] As a preferred embodiment of the present invention, a unique corresponding RFID tag is matched for each batch of imported parts: {i, Type_i, Quantity_i, Size_i, Date_i}.

[0011] The RFID tag is attached to each KD import part for subsequent tracking and management.

[0012] The warehouse scheduling module allocates the best storage location based on inventory status, item type and demand. The particle swarm algorithm analyzes the current inventory status and expected demand, and automatically allocates each batch of incoming KD imported parts to the most suitable storage location.

[0013] The particle swarm algorithm is specifically:

[0014] Carry out problem modeling; obtain the number of batches of KD imported parts to be stored in the warehouse at every preset time interval t; obtain the total number of currently available storage locations m, and obtain the number of each storage location, the number symbol is j; j = 1, 2, 3, ..., m;

[0015] Establish an m-dimensional solution space, and establish n×m particles in the solution space. Each particle has an n-dimensional position vector X={x1, x2, ..., xn}; the value range of each xi is 1, 2, ..., m, representing the storage location number j assigned to the i-th cargo. Each particle represents a storage location allocation scheme. Number the particles, and the number symbol is w; w=1, 2, 3, ..., n×m.

[0016] Subsequently, three fitness functions are set to quantify the quality of the storage solution represented by each particle, including:

[0017] Space utilization fitness function:

[0018] Among them C j is the maximum capacity of storage location j, that is, the maximum volume of items allowed to be stored; i is the storage space where KD imported part i is located; where β(x i =j) is an indicator function, which indicates the allocation of KD imported part i to storage location j. When KD imported part i is allocated to storage location j, β(x i =j) is 1, otherwise it is 0.

[0019] Access time fitness function:

[0020] Where d(x i) is the access distance of KD imported part i, that is, the distance from the storage location coordinates (xi, yi, zi) of KD imported part i to the outbound location coordinates (x0, y0, z0); where fi is the access frequency coefficient of KD imported part i, representing its access frequency; where W distance (Type_i, d) is the access time weighting coefficient of KD import part i, representing its corresponding type identifier Type_i and access distance d(x i )’s impact on shipping time.

[0021] Load balancing fitness function: Where L j is the transport capacity load of storage location j, that is, the total batch quantity of KD imported parts allocated to this location.

[0022] As a preferred method of the present invention, a comprehensive fitness function is established:

[0023] LoadUtilization = λ1×SpaceUtilization+λ2×TimeUtilization+λ3×LoadUtilization, where λ1, λ2 and λ3 are preset weight coefficients; by adjusting the three coefficients, the three requirements of space utilization, access time and load balancing can be dynamically adjusted.

[0024] As a preferred embodiment of the present invention, the velocity of the particle group is initialized, the initial velocity of all particles is set to v0, and the fitness function value LoadUtilization is calculated according to their current positions.

[0025] As a preferred embodiment of the present invention, the speed and position of the particle are updated according to the calculation result of the fitness function value LoadUtilization, and the update rule is set: in and are the particle velocities of the w-th particle in the k+1th and kth operations respectively; and are the particle positions of the wth particle in the k+1th and kth operations respectively; k is the operation number; c1 and c2 are the preset learning factors that control the particle's dependence on its own experience and group experience. i * is the personal optimal position of particle i, that is, the particle position that has been found to minimize the fitness function value LoadUtilization during the search process of particle i; is the global optimal position, that is, the particle position that all particles have ever found to minimize the fitness function value LoadUtilization. It is the optimal solution among all the particles' personal optimal positions and represents the optimal solution currently found by the entire particle swarm. Both rand1 and rand2 are random numbers in the range [0, 1].

[0026] As a preferred embodiment of the present invention, the operation termination conditions are set as follows: Termination condition 1: the number of operations k is greater than the maximum number of iterations kmax; Termination condition 2: in the operation exceeding kmin times, the global optimal position The change of the fitness function value LoadUtilization in each operation is less than the preset threshold ε. When condition 1 or termination condition 2 is met, the operation ends and the global optimal position is output And it serves as the most appropriate allocation location plan for KD imported part i.

[0027] The tracking and management module obtains inventory status and space location in real time.

[0028] At every preset time interval t, the spatial position coordinates (xi, yi, zi) of each batch of KD imported parts i are obtained. At every preset time interval t, the inventory status of each batch of KD imported parts i is obtained through RFID technology. The inventory status includes: allocated orders, pending orders, in stock, pending in stock, pending out, in storage, in outbound, scrapped, in quality inspection, and in transfer.

[0029] Whenever the inventory status of KD imported part i is detected to change, the location of KD imported part i is updated through RFID technology. The update formula is: P i (t) = P i (t-1)+ΔP i Where P i (t-1) is the spatial position coordinate of KD import part i before time interval t, where ΔP i is the change in spatial position coordinates of KD import part i from time interval t to the current moment.

[0030] As a preferred embodiment of the present invention, the warehouse environment is monitored in real time by environmental sensors to ensure that the storage conditions of all KD imported parts are in compliance with regulations.

[0031] The temperature Ti, humidity Hi and light intensity Li of the environment where each batch of KD imported parts i is located are obtained through sensors, and a preset inventory state vector (u1, u2, u3) is assigned according to the inventory state of each batch of KD imported parts i. Among them, u1, u2 and u3 represent the condition requirements of the current inventory state for the ambient temperature, ambient humidity and ambient light intensity respectively.

[0032] By formula Calculate the environmental anomaly factor Ei of KD imported part i. Where Tmax is the preset maximum temperature threshold, Tmin is the preset minimum temperature threshold; where Hmax is the preset maximum humidity threshold, Hmin is the preset minimum humidity threshold; where Lmax is the preset maximum light intensity threshold, Lmin is the preset minimum light intensity threshold;

[0033] If there is an environmental anomaly factor Ei of a KD imported part i that is greater than the preset threshold Emax, it is determined that the environment in which it is located is lower than the minimum requirement.

[0034] The outbound management module automatically generates outbound tasks and allocates corresponding KD import parts according to outbound demand and outbound order information, and completes the task allocation of transportation equipment based on the minimum computing cost. It analyzes the outbound transportation volume and the availability and inventory status of transportation tools through algorithms, optimizes the allocation of transportation tools, and improves outbound efficiency. The specific process is as follows:

[0035] The outbound task information in the outbound order is obtained through natural language processing technology to generate an outbound task vector Tout = {i, Qd, xi}, where i is the unique identifier of the KD import part; Qd is the demand in the outbound order, and xi is the storage location of the KD import part i.

[0036] As a preferred embodiment of the present invention, the transport means at the storage location xi=j is obtained and numbered, and the numbering symbol is q, q=1, 2, 3, ..., p. p is the number of all transport means at the storage location j. The moving cost Cost(q), the maximum transport quantity Quantity(q), the remaining power Battery(q) and the position coordinates (xq, yq, zq) of each transport means q are obtained, and the formula Calculate the transportation cost Cost, where Enabled_q is the enabled status symbol of the transport tool q, and its value is 1 when the transport tool is enabled, otherwise its value is 0; where γq is the unit cost of the transport tool q, and where dq is the required moving distance of the transport tool q;

[0037] Set the cost minimization objective function: MinCost.

[0038] Set the constraints of the objective function:

[0039] Demand Constraint: The demand Qd of each order must be met, but in actual applications, the demand fluctuates, that is, Where δQd is the allowable fluctuation range.

[0040] Enabled state constraint: The enabled state of a vehicle is affected by the battery power. The enabled state symbol can only be 1 when the power condition is met, that is, Batterymin is the minimum threshold of battery power. If the power is lower than this value, the transportation tool cannot be used.

[0041] Path selection constraints: The actual speed, path conditions and traffic conditions of different transportation tools should be considered when selecting a path. Where L j is the transport capacity load of storage location j, that is, the total batches of KD imported parts allocated to this location; where L j Max is the maximum capacity load threshold.

[0042] The interactive module outputs data and alarm information through touch screens, mobile terminals, voice recognition, etc., making it convenient for staff to operate and manage the warehouse.

[0043] Provide staff with real-time information about system operation, including inventory status, transportation task allocation, and environmental monitoring data, through touch screens, mobile terminals, or voice recognition devices;

[0044] When it is identified that the environmental abnormality factor Ei of the KD imported part i is greater than the preset threshold Emax, it is determined that the environment in which it is located is lower than the minimum requirement. The KD imported part i is highlighted at the current location P i (t), automatically issue alarms and provide abnormal information to staff;

[0045] Through the interactive interface, key information such as task execution progress, inventory changes, equipment activation status, and transportation tool status are displayed to staff.

[0046] As a preferred embodiment of the present invention, the interactive module has a voice recognition function, which recognizes the voice commands issued by the staff through natural language processing technology, allowing the staff to query the inventory status, the status of the transportation tools, the progress of the outbound task and other information through voice, and return corresponding voice or text feedback.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention automates warehousing scheduling through particle swarm optimization algorithm, optimizes storage location allocation, reduces manual intervention, improves warehouse space utilization, and ensures optimal efficiency of goods storage and access. The combination of RFID technology and environmental sensors realizes accurate inventory tracking and status monitoring, further improving the accuracy and real-time performance of inventory management;

[0049] 2. The present invention provides a convenient operation platform for warehouse staff, supporting multiple interaction modes such as touch screen, mobile terminal and voice recognition. Staff can obtain warehouse operation data in real time, monitor inventory status, transportation task progress and environmental conditions, handle abnormal situations in a timely manner, and improve the visualization level of warehouse management. In addition, the voice recognition function enables staff to query information more conveniently, further improving work efficiency and response speed;

[0050] 3. The present invention optimizes the outbound management system and allocates transportation equipment tasks based on the minimum computing cost, effectively improving outbound efficiency. Automatically generating outbound tasks and optimizing allocation based on inventory status and the availability of transportation tools not only ensures timely response to outbound demand, but also dynamically adjusts transportation routes and methods according to the actual conditions of transportation tools, reducing transportation costs, optimizing resource allocation, and improving overall logistics efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings:

[0052] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0053] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. 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.

[0054] See also Figure 1 As shown, an intelligent warehouse management system for KD imported parts in an automobile supply chain includes a data collection module, a warehousing scheduling module, a tracking and management module, an outbound management module and an interaction module.

[0055] The data collection module obtains the arrival information of each batch of KD imported parts, including the unique identifier i of the KD imported parts, the type identifier Type_i, the quantity Quantity_i, the specification Size_i and the arrival date Date_i.

[0056] Furthermore, a unique corresponding RFID tag is matched for each batch of imported parts: {i, Type_i, Quantity_i, Size_i, Date_i}.

[0057] The RFID tag is attached to each KD import part for subsequent tracking and management.

[0058] The warehouse scheduling module allocates the best storage location based on inventory status, item type and demand. The particle swarm algorithm analyzes the current inventory status and expected demand, and automatically allocates each batch of incoming KD imported parts to the most suitable storage location.

[0059] The particle swarm algorithm is specifically:

[0060] Carry out problem modeling; obtain the number of batches of KD imported parts to be stored in the warehouse at every preset time interval t; obtain the total number of currently available storage locations m, and obtain the number of each storage location, the number symbol is j; j = 1, 2, 3, ..., m;

[0061] Establish an m-dimensional solution space, and establish n×m particles in the solution space. Each particle has an n-dimensional position vector X={x1, x2, ..., xn}; the value range of each xi is 1, 2, ..., m, representing the storage location number j assigned to the i-th cargo. Each particle represents a storage location allocation scheme. Number the particles, and the number symbol is w; w=1, 2, 3, ..., n×m.

[0062] Subsequently, three fitness functions are set to quantify the quality of the storage solution represented by each particle, including:

[0063] Space utilization fitness function:

[0064] Among them C j is the maximum capacity of storage location j, that is, the maximum volume of items allowed to be stored; i is the storage space where KD imported part i is located; where β(x i =j) is an indicator function, which indicates the allocation of KD imported part i to storage location j. When KD imported part i is allocated to storage location j, β(x i =j) is 1, otherwise it is 0.

[0065] Access time fitness function:

[0066] Where d(x i ) is the access distance of KD imported part i, that is, the distance from the storage location coordinates (xi, yi, zi) of KD imported part i to the outbound location coordinates (x0, y0, z0); where fi is the access frequency coefficient of KD imported part i, representing its access frequency; where W distance (Type_i, d) is the access time weighting coefficient of KD import part i, representing its corresponding type identifier Type_i and access distance d(x i )’s impact on shipping time.

[0067] Load balancing fitness function: Where L j is the transport capacity load of storage location j, that is, the total batch quantity of KD imported parts allocated to this location.

[0068] Furthermore, a comprehensive fitness function is established:

[0069] LoadUtilization = λ1×SpaceUtilization+λ2×TimeUtilization+λ3×LoadUtilization, where λ1, λ2 and λ3 are preset weight coefficients; by adjusting the three coefficients, the three requirements of space utilization, access time and load balancing can be dynamically adjusted.

[0070] Furthermore, the velocity of the particle swarm is initialized, the initial velocity of all particles is set to v0, and the fitness function value LoadUtilization is calculated according to their current positions.

[0071] Furthermore, the speed and position of the particle are updated according to the calculation result of the fitness function value LoadUtilization, and the update rules are set: in and are the particle velocities of the w-th particle in the k+1th and kth operations respectively; and are the particle positions of the wth particle in the k+1th and kth operations respectively; k is the operation number; c1 and c2 are the preset learning factors that control the particle's dependence on its own experience and group experience. i * is the personal optimal position of particle i, that is, the particle position that has been found to minimize the fitness function value LoadUtilization during the search process of particle i; is the global optimal position, that is, the particle position that all particles have ever found to minimize the fitness function value LoadUtilization. It is the optimal solution among all the particles' personal optimal positions and represents the optimal solution currently found by the entire particle swarm. Both rand1 and rand2 are random numbers in the range [0, 1].

[0072] Furthermore, the termination conditions are set: Termination condition 1: the number of operations k is greater than the maximum number of iterations kmax; Termination condition 2: in the number of operations exceeding kmin, the global optimal position The change of the fitness function value LoadUtilization in each operation is less than the preset threshold ε. When condition 1 or termination condition 2 is met, the operation ends and the global optimal position is output And it serves as the most appropriate allocation location plan for KD imported part i.

[0073] It should be noted that the particle swarm optimization algorithm PSO simulates the foraging behavior of bird flocks and is suitable for continuous optimization problems. Each particle represents a potential solution and continuously adjusts its position and speed to find the path to the optimal solution. The optimal solution recorded by each particle in the process of finding the optimal solution is recorded as the personal optimal position, and the group optimal solution recorded by the particle swarm composed of all particles in the process of finding the optimal solution is recorded as the global optimal position. The speed and position of each particle are adjusted through the personal optimal position and the global optimal position, thereby simulating the flight of particles in the solution space and exploring the solution space to find the optimal solution.

[0074] The tracking and management module obtains inventory status and space location in real time.

[0075] At every preset time interval t, the spatial position coordinates (xi, yi, zi) of each batch of KD imported parts i are obtained. At every preset time interval t, the inventory status of each batch of KD imported parts i is obtained through RFID technology. The inventory status includes: allocated orders, pending orders, in stock, pending in stock, pending out, in storage, in outbound, scrapped, in quality inspection, and in transfer.

[0076] Whenever the inventory status of KD imported part i is detected to change, the location of KD imported part i is updated through RFID technology. The update formula is: P i (t) = P i (t-1)+ΔP i Where P i (t-1) is the spatial position coordinate of KD import part i before time interval t, where ΔP i is the change in spatial position coordinates of KD import part i from time interval t to the current moment.

[0077] Furthermore, environmental sensors are used to monitor the warehouse environment in real time to ensure that the storage conditions of parts are in compliance with regulations.

[0078] The temperature Ti, humidity Hi and light intensity Li of the environment where each batch of KD imported parts i is located are obtained through sensors, and a preset inventory state vector (u1, u2, u3) is assigned according to the inventory state of each batch of KD imported parts i. Among them, u1, u2 and u3 represent the condition requirements of the current inventory state for the ambient temperature, ambient humidity and ambient light intensity respectively.

[0079] By formula Calculate the environmental anomaly factor Ei of KD imported part i. Where Tmax is the preset maximum temperature threshold, Tmin is the preset minimum temperature threshold; where Hmax is the preset maximum humidity threshold, Hmin is the preset minimum humidity threshold; where Lmax is the preset maximum light intensity threshold, Lmin is the preset minimum light intensity threshold;

[0080] If there is an environmental anomaly factor Ei of a KD imported part i that is greater than the preset threshold Emax, it is determined that the environment in which it is located is lower than the minimum requirement.

[0081] The outbound management module automatically generates outbound tasks and allocates corresponding KD import parts according to outbound demand and outbound order information, and completes the task allocation of transportation equipment based on the minimum computing cost. It analyzes the outbound transportation volume and the availability and inventory status of transportation tools through algorithms, optimizes the allocation of transportation tools, and improves outbound efficiency. The specific process is as follows:

[0082] The outbound task information in the outbound order is obtained through natural language processing technology to generate an outbound task vector Tout = {i, Qd, xi}, where i is the unique identifier of the KD import part; Qd is the demand in the outbound order, and xi is the storage location of the KD import part i.

[0083] Further, the transport means at the storage location xi=j is obtained and numbered, the number symbol is q, q=1, 2, 3, ..., p. p is the number of all transport means at the storage location j. The moving cost Cost(q), the maximum transport quantity Quantity(q), the remaining battery Battery(q) and the position coordinates (xq, yq, zq) of each transport means q are obtained, and the formula Calculate the transportation cost Cost, where Enabled_q is the enabled status symbol of the transport tool q, and its value is 1 when the transport tool is enabled, otherwise its value is 0; where γq is the unit cost of the transport tool q, and where dq is the required moving distance of the transport tool q;

[0084] Set the cost minimization objective function: MinCost.

[0085] Set the constraints of the objective function:

[0086] Demand Constraint: The demand Qd of each order must be met, but in actual applications, the demand fluctuates, that is, Where δQd is the allowable fluctuation range.

[0087] Enabled state constraint: The enabled state of a vehicle is affected by the battery power. The enabled state symbol can only be 1 when the power condition is met, that is, Batterymin is the minimum threshold of battery power. If the power is lower than this value, the transportation tool cannot be used.

[0088] Path selection constraints: When selecting a path, it is necessary to consider the actual speed, path conditions and traffic conditions of different means of transportation, that is, Where L j is the transport capacity load of storage location j, that is, the total batches of KD imported parts allocated to this location; where L j Max is the maximum capacity load threshold.

[0089] The interactive module outputs data and alarm information through touch screens, mobile terminals, voice recognition, etc., making it convenient for staff to operate and manage the warehouse.

[0090] Provide staff with real-time information about system operation, including inventory status, transportation task allocation, and environmental monitoring data, through touch screens, mobile terminals, or voice recognition devices;

[0091] When it is identified that the environmental abnormality factor Ei of the KD imported part i is greater than the preset threshold Emax, it is determined that the environment in which it is located is lower than the minimum requirement. The KD imported part i is highlighted at the current location P i (t), automatically issue alarms and provide abnormal information to staff;

[0092] Through the interactive interface, key information such as task execution progress, inventory changes, equipment activation status, and transportation tool status are displayed to staff.

[0093] Furthermore, the interactive module supports voice recognition function, which recognizes the voice commands issued by the staff through natural language processing technology, allowing the staff to query the inventory status, the status of the transportation tools, the progress of the outbound task and other information through voice, and return the corresponding voice or text feedback.

[0094] It should be understood that the terms “include” and “comprising” used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0095] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and the claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and the claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations;

[0096] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent warehouse management system for KD imported parts in the automobile supply chain, including a data acquisition module, a warehousing scheduling module and a warehouse-out management module, characterized in that: The data collection module obtains the arrival information of each batch of KD imported parts and integrates it into RFID tags and attaches them to each KD imported part for subsequent tracking and management; The warehousing scheduling module obtains the batch number n of KD imported parts to be stored, the KD imported part number i, the total number of currently available storage locations m and the storage location number j according to the inventory status, item type and demand; where i = 1, 2, ..., n; Where j = 1, 2, ..., m; automatically allocate the optimal storage location for each batch of KD imported parts, and perform data analysis through particle swarm algorithm to determine the most suitable storage location; The outbound management module automatically generates outbound tasks and allocates corresponding KD imported parts based on outbound demand and outbound order information. It calculates the optimal transportation tool allocation plan based on the moving cost of the transportation tool, the maximum transportation quantity, the remaining power and other conditions to minimize the transportation cost.

2. According to claim 1, the intelligent warehouse management system for KD imported parts in the automobile supply chain is characterized in that: It also includes a tracking and management module and an interaction module; The tracking and management module obtains inventory status and space location in real time; At every preset time interval t, the inventory status and location of each batch of KD imported parts i are tracked in real time through RFID technology. The inventory status includes: assigned orders, pending orders, warehoused, pending warehoused, pending outbound, in storage, in outbound, scrapped, in quality inspection, and in transfer. The spatial position coordinates (xi, yi, zi) and inventory status of KD imported parts i are updated in real time through the update formula; the warehouse environment is monitored in real time through environmental sensors, the storage conditions of KD imported parts are quantified, and whether the storage conditions are compliant is determined; The interactive module provides data output and alarm information through touch screens, mobile terminals or voice recognition devices, providing real-time information related to system operation to staff, such as inventory status, transportation task allocation and environmental monitoring data; The voice recognition function recognizes the staff's voice commands, allowing inquiries into inventory status, transportation tool status, outbound task progress, etc., and returns corresponding voice or text feedback.

3. According to claim 1, the intelligent warehouse management system for KD imported parts in the automobile supply chain is characterized in that: The arrival information and RFID tag are specifically: The arrival information includes the unique identifier i of the KD imported part, the type identifier Type_i, the quantity Quantity_i, the specification Size_i and the arrival date Date_i; Each batch of KD imports is matched with a unique corresponding RFID tag: {i, Type_i, Quantity_i, Size_i, Date_i}.

4. According to claim 1, the intelligent warehouse management system for KD imported parts in the automobile supply chain is characterized in that: The specific process of using the particle swarm algorithm to analyze data and determine the most appropriate storage location is as follows: Carry out problem modeling; obtain the number of batches of KD imported parts to be stored in the warehouse at every preset time interval t; obtain the total number of currently available storage locations m, and obtain the number of each storage location, the number symbol is j; j = 1, 2, 3, ..., m; Establish an m-dimensional solution space, establish n×m particles in the solution space, each particle has an n-dimensional position vector X={x1, x2, ..., xn}; the value range of each xi is 1, 2, ..., m, representing the storage location number j assigned to the i-th cargo; each particle represents a storage location allocation plan; number the particles, the numbering symbol is w; w=1, 2, 3, ..., n×m; Three fitness functions are set to quantify the quality of the storage solution represented by each particle; Based on the fitness function, the speed and position of the particles are updated, the minimum computing cost is calculated, the allocation plan of the storage position is optimized, and a comprehensive fitness function is established. The three fitness functions are comprehensively considered, the speed of the particle group is initialized, the initial speed of all particles is set to v0, and the fitness function value is calculated according to its current position; the speed and position of the particles are updated in combination with the comprehensive fitness function, and the operation is terminated when the set operation termination condition is reached, and the most suitable allocation position plan is output.

5. According to claim 4, the intelligent warehouse management system for KD imported parts in the automobile supply chain is characterized in that: The three fitness functions are specifically: Space utilization fitness function: Among them C j is the maximum capacity of storage location j, that is, the maximum volume of items allowed to be stored; i is the storage space where KD imported part i is located; where β(x i =j) is an indicator function, which indicates the allocation of KD imported part i to storage location j. When KD imported part i is allocated to storage location j, β(x i =j) is 1, otherwise it is 0; Access time fitness function: Where d(x i ) is the access distance of KD imported part i, that is, the distance from the storage location coordinates (xi, yi, zi) of KD imported part i to the outbound location coordinates (x0, y0, z0); where fi is the access frequency coefficient of KD imported part i, representing its access frequency; where W distance (Type_i, d) is the access time weighting coefficient of KD import part i, representing its corresponding type identifier Type_i and access distance d(x i ) Impact on transportation time; Load balancing fitness function: Where L j is the transport capacity load of storage location j, that is, the total batch quantity of KD imported parts allocated to this location.

6. The intelligent warehouse management system for KD imported parts in the automobile supply chain according to claim 4 is characterized in that: The specific process of updating the particle speed and position based on the fitness function, calculating the minimum computing cost, and optimizing the allocation of storage locations is as follows: Establish a comprehensive fitness function: LoadUtilization = λ1×SpaceUtilization+λ2×TimeUtilization+λ3×LoadUtilization, where λ1, λ2 and λ3 are preset weight coefficients; Initialize the speed of the particle swarm, set the initial speed of all particles to v0, and calculate the fitness function value LoadUtilization according to their current position; Update the particle's velocity and position according to the calculation result of the fitness function value LoadUtilization, and set the update rules: in and are the particle velocities of the w-th particle in the k+1th and kth operations respectively; and are the particle positions of the wth particle in the k+1th and kth operations respectively; k is the operation number; c1 and c2 are the preset learning factors that control the particle's dependence on its own experience and group experience; P i * is the personal optimal position of particle i, that is, the particle position that has been found to minimize the fitness function value LoadUtilization during the search process of particle i; is the global optimal position, that is, the particle position that all particles have ever found to minimize the fitness function value LoadUtilization. It is the optimal solution among all the particles' personal optimal positions and represents the optimal solution currently found by the entire particle swarm. Both rand1 and rand2 are random numbers in the range of [0, 1]. Set the operation termination conditions: Termination condition 1: the number of operations k is greater than the maximum number of iterations kmax; Termination condition 2: in the operation with more than kmin times, the global optimal position The fitness function value LoadUtilization changes in each operation less than the preset threshold ε; when condition 1 or termination condition 2 is met, the operation ends and the global optimal position is output And it serves as the most appropriate allocation location plan for KD imported part i.

7. The intelligent warehouse management system for KD imported parts in the automobile supply chain according to claim 1 is characterized in that: The specific process of calculating the optimal transportation tool allocation plan and minimizing transportation costs is as follows: The outbound task information in the outbound order is obtained through natural language processing technology, and the outbound task vector Tout={i, Qd, xi} is generated; wherein i is the unique identifier of the KD imported part; wherein Qd is the demand in the outbound order, and wherein xi is the storage location of the KD imported part i; Get the transport at storage location xi=j and number it, the number symbol is q, q=1, 2, 3, ..., p; p is the number of all transports at storage location j; get the moving cost Cost(q), maximum transport quantity Quantity(q), remaining power Battery(q) and position coordinates (xq, yq, zq) of each transport q, and use the formula Calculate the transportation cost Cost, where Enabled_q is the enabled status symbol of the transport tool q, and its value is 1 when the transport tool is enabled, otherwise its value is 0; where γq is the unit cost of the transport tool q, and where dq is the required moving distance of the transport tool q; Set the cost minimization objective function: MinCost; Set the constraints of the objective function: Demand Constraint: The demand Qd of each order must be met, but in actual applications, the demand fluctuates, that is, Among them, δQd is the allowable fluctuation range; Enabled state constraint: The enabled state of a vehicle is affected by the battery power. The enabled state symbol can only be 1 when the power condition is met, that is, Among them, batterymin is the minimum threshold of battery power; Path selection constraints: When selecting a path, it is necessary to consider the actual speed, path conditions and traffic conditions of different means of transportation, that is, Where L j is the transport capacity load of storage location j, that is, the total batches of KD imported parts allocated to this location; where L j Max is the maximum capacity load threshold.

8. The intelligent warehouse management system for KD imported parts in the automobile supply chain according to claim 2 is characterized in that: The specific process of real-time tracking of the inventory status and location of each batch of KD imported parts i through RFID technology is as follows: At every preset time interval t, the spatial position coordinates (xi, yi, zi) of each batch of KD imported parts i are obtained; at every preset time interval t, the inventory status of each batch of KD imported parts i is obtained through RFID technology; the inventory status includes: allocated orders, pending orders, in stock, pending in stock, pending out, in storage, in outbound, scrapped, in quality inspection and in transfer; Whenever the inventory status of KD imported part i is detected to change, the location of KD imported part i is updated through RFID technology. The update formula is: P i (t) = P i (t-1)+ΔP i Where P i (t-1) is the spatial position coordinate of KD import part i before time interval t, where ΔP i is the change in spatial position coordinates of KD import part i from time interval t to the current moment.

9. The intelligent warehouse management system for KD imported parts in the automobile supply chain according to claim 2 is characterized in that: The specific process of monitoring the warehouse environment in real time through environmental sensors and quantifying the storage conditions of KD imported parts is as follows: The temperature Ti, humidity Hi and light intensity Li of the environment where each batch of KD imported parts i is located are obtained through sensors, and a preset inventory state vector (u1, u2, u3) is assigned according to the inventory state of each batch of KD imported parts i; where u1, u2 and u3 represent the condition requirements of the current inventory state for the ambient temperature, ambient humidity and ambient light intensity respectively; By formula Calculate the environmental anomaly factor Ei of KD imported part i; where Tmax is the preset maximum temperature threshold, Tmin is the preset minimum temperature threshold; where Hmax is the preset maximum humidity threshold, Hmin is the preset minimum humidity threshold; where Lmax is the preset maximum light intensity threshold, Lmin is the preset minimum light intensity threshold; If there is an environmental anomaly factor Ei of a KD imported part i that is greater than the preset threshold Emax, it is determined that the environment in which it is located is lower than the minimum requirement.

Images