Intelligent scheduling method and system for cold chain transportation

Abstract

The invention relates to the technical field of cold-chain logistics, in particular to an intelligent scheduling method and system for cold-chain transportation, and the method comprises the steps: achieving the precise scheduling and matching of vehicles and resources according to the information and resource integration of transportation vehicles; carrying out vehicle transportation path planning according to the determined target order; formulating an emergency response mechanism based on the real-time health state of the transport vehicle; according to the invention, through integration of transport vehicle information and resource data, optimization matching is carried out by using an intelligent calling algorithm, and accurate scheduling of vehicles and resources is realized. The resource waste and the unnecessary transportation cost are effectively avoided, and the improvement of the transportation efficiency is ensured; particle swarm optimization is adopted for path planning, and two-step operation of preliminary path generation and dynamic path optimization is combined, so that high efficiency and reliability in the cold chain transportation process are ensured; on the basis of real-time monitoring and historical data, potential faults of vehicles and equipment can be recognized in advance, and quick response can be achieved when abnormity occurs.

Description

Technical Field

[0001] The present invention relates to the technical field of cold chain logistics, and specifically to an intelligent scheduling method and system for cold chain transportation. Background Art

[0002] Cold chain transport scheduling refers to the management and optimization of the transportation process in the cold chain logistics system to ensure that temperature-sensitive goods (such as food, medicine, vaccines, etc.) are kept within a suitable temperature range during transportation; effective scheduling can reduce energy consumption, shorten transportation time, and ensure the quality and safety of goods. At present, the following challenges are faced in the cold chain transport scheduling problem:

[0003] The cooling system and temperature sensors of cold chain transportation equipment such as refrigerated trucks may malfunction, causing the temperature to be out of control and affecting the quality of goods. Temperature monitoring equipment may have data delays or sensor errors, resulting in the inability to detect temperature anomalies in a timely manner, affecting the accuracy of scheduling decisions;

[0004] In addition, cold chain transportation scheduling needs to consider multiple variables, such as temperature control, transportation time, road conditions, traffic jams, etc., which makes route planning complicated and susceptible to interference. It is difficult to adjust the route in real time during transportation to deal with emergencies (such as weather changes, traffic accidents, etc.), resulting in an increased risk of delays or temperature out of control.

[0005] Secondly, many cold chain transportation companies do not have a complete emergency response mechanism. When equipment failure, traffic accidents or temperature abnormalities occur, they are unable to take effective measures in time, resulting in cargo loss. Even if there is an emergency plan, the lag and uncertainty in the implementation process will affect the safety of the cargo. Summary of the invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent scheduling method for cold chain transportation, comprising the following steps:

[0008] Based on the transport vehicle information and resource integration, accurate scheduling and matching of vehicles and resources can be achieved;

[0009] Plan the vehicle transportation route according to the determined target order;

[0010] Develop emergency response mechanisms based on the real-time health status of transport vehicles.

[0011] As a preferred solution of the intelligent scheduling method for cold chain transportation described in the present invention, the accurate scheduling and matching of vehicles and resources is achieved by integrating resources, building a dynamic database, and optimizing the matching of vehicles and the dynamic database by using an intelligent calling algorithm, as follows:

[0012] Collect data on cold chain transport vehicles and assign a unique number V to each vehicle i , where i represents the vehicle number index, and a vehicle information database is established to record the specific parameter information of each vehicle, then,

[0013] V i ={C i ,W i ,P i}

[0014] Among them, V i represents the unique number of the i-th vehicle, C i represents the cooling capacity of the i-th vehicle, W i represents the loading capacity of the i-th vehicle, P i represents the driving performance of the i-th vehicle;

[0015] Integrate the vehicle number with inventory, order quantity, and warehouse location resource information to build a dynamic database, then we have:

[0016] D(t)={V i ,S j (t),O k (t),L m (t)}

[0017] Among them, V i represents the unique number of the i-th vehicle, S j (t) represents the inventory status of the jth warehouse at time t, O k (t) represents the demand state of the kth order at time t, L m (t) represents the position of the mth warehouse at time t;

[0018] Based on the constructed dynamic database, the target optimization function is formulated, then,

[0019]

[0020] Among them, f(V i ,S j ,O k ,L m ) represents the objective optimization function, which is used to calculate the optimal scheduling plan for each vehicle, d(V i ,O k) represents the path cost from the i-th vehicle to the k-th order point, E(V i ,S j ) represents the resource matching degree between the i-th vehicle and the j-th warehouse, α and β represent the path cost weight and resource matching weight respectively.

[0021] As a preferred solution of the intelligent dispatching method for cold chain transportation described in the present invention, the optimization matching of vehicles and dynamic databases by using intelligent calling algorithms is specifically as follows:

[0022] The path cost optimization between vehicles and order points is to calculate the comprehensive cost of the i-th vehicle from the matching warehouse to reach the k-th order delivery point, then,

[0023] d(V i ,O k )=α1·D ik +α2·T ik +α3·F ik +α4·C ik +α5·W ik

[0024] α1+α2+α3+α4+α5=1

[0025] Among them, D ik is the distance cost, which indicates the driving distance of the current vehicle to reach the order point, T ik represents the time cost during driving, F ik represents the fuel cost to complete the order, C ik represents the road cost to complete the order, W ik It represents the economic consumption cost of completing the order. α1, α2, α3, α4, and α5 represent the weight coefficients of each item, which are set by the implementer according to the actual application scenario.

[0026] The optimization of the matching degree between vehicles and warehouse resources is to calculate the matching degree between the i-th vehicle and the j-th warehouse resource, then,

[0027] E(V i ,S j )=β1·M ij +β2·L ij +β3·H ij

[0028] β1+β2+β3=1

[0029] Among them, M ij Indicates the matching degree between the vehicle load and the weight of the cargo to be transported, L ij Indicates the matching degree between vehicle cooling capacity and cargo temperature requirement, H ijIt represents the matching degree between the current position of the vehicle and the warehouse position, and β1, β2, and β3 represent the weight coefficients of each item.

[0030] As a preferred solution of the intelligent scheduling method for cold chain transportation described in the present invention, the matching degree between the vehicle load and the weight of the goods to be transported is obtained by calculating the ratio of the total weight of the goods to be transported and the loading capacity of the current vehicle, then,

[0031]

[0032] Among them, W i Indicates the current vehicle loading capacity, W j Indicates the total weight of the goods to be transported, M ij Indicates the matching degree between the vehicle load and the weight of the goods to be transported. The calculation result satisfies 0≤M ij ≤1, the specific matches are as follows:

[0033] When the vehicle loading capacity and the total weight of the goods to be transported satisfy the formula W i <W j When , it means that the current vehicle loading capacity cannot meet the transportation requirements and does not match the weight of the goods to be transported;

[0034] When the vehicle loading capacity and the total weight of the goods to be transported satisfy the formula W i ≥W j When , it means that the current vehicle loading capacity meets the transportation requirements, and a secondary analysis is performed on the matching degree of the weight of the goods to be transported, as follows:

[0035] When the calculation result satisfies the formula M ij →When it is 1, it means that the current vehicle has a higher matching degree with the weight of the cargo to be transported;

[0036] When the calculation result satisfies the formula M ij →0, it means that the matching degree between the current vehicle and the weight of the cargo to be transported is lower.

[0037] As a preferred solution of the intelligent scheduling method for cold chain transportation described in the present invention, the path planning for vehicle transportation according to the determined target order is to use a particle swarm algorithm to plan the transportation path for vehicles that match the order, including preliminary path generation and dynamic path planning.

[0038] As a preferred solution of the intelligent scheduling method for cold chain transportation described in the present invention, the preliminary path generation is specifically as follows:

[0039] Initialize the transportation network as a directed graph G = (N, R), where N represents the node set in the directed graph, which is each warehouse point in the transportation network, and R represents the edge set in the directed graph, which is the connection path between each location in the transportation network;

[0040] Set the order destination as the starting point S p , and will start from the starting point S p The distances to all other nodes are initialized to infinity, but S p The distance of itself is set to 0, and an unprocessed node set Q containing the node set N is set;

[0041] Randomly select a node u from the unprocessed node set Q and calculate the distance from node u to the starting point S p The distance, and remove the node u currently participating in the calculation from the unprocessed node set Q, then,

[0042] R u =argmin u∈Q d(S,u)

[0043] Among them, d(S,u) represents the shortest distance from node u to the starting point S, R u Represents the shortest path from node u to starting point S;

[0044] For a random node u, using the neighbor node v of node u, calculate the shortest distance from node u to the starting point S after passing through the neighbor node v, then we have:

[0045] R u ′=min(d(S,v),d(S,u)+d(u,v))

[0046] Among them, d(S,v) represents the shortest distance from node v to the starting point S, d(S,u) represents the shortest distance from node u to the starting point S, d(u,v) represents the shortest distance from node u to the starting point v, R u ′ represents the shortest path from node u to the starting point S after passing through the neighbor node v;

[0047] By comparing the sizes of the two paths and retaining the shortest path of the two paths, we have:

[0048] If the comparison result satisfies the formula R u ≥R u ′, retain the path R u ′, otherwise the path R is retained u , repeatedly execute the shortest path from a random node in the unprocessed node set Q to the starting point S until the unprocessed node set Q is an empty set, and combine all paths into a preliminary path set P.

[0049] As a preferred solution of the intelligent scheduling method for cold chain transportation described in the present invention, the dynamic path planning is specifically as follows:

[0050] Set it as particle swarm I, and use the paths in the preliminary path set P as particles in the particle swarm. By updating the position and speed of the particles, the order of the nodes in the path is adjusted, and then the path set P is optimized to achieve dynamic path planning. The specific planning is as follows:

[0051] Initialize the position of the particle in the particle swarm I0 = x i (0), represents the node order in the preliminary path set P, is the transportation path of the transportation vehicle for the current order, and initializes the particle update speed v i (0), represents the rate of node order adjustment;

[0052] Set the value used to evaluate the particle's current position x i The objective function Z(x) of the path quality of (t) satisfies the formula Z(x) = d(V i ,P), where d(V i ,P) represents the comprehensive cost of the i-th vehicle during the driving path. By updating the position of the particles, the objective function is minimized, and then the optimal path planning for cold chain transportation is realized. Then,

[0053] The particle velocity is updated as follows:

[0054]

[0055] The particle position is updated as follows:

[0056] x i (t+1)=x i (t)+v i (t+1)·(t+1)

[0057] Among them, v i (t) represents the velocity of the ith particle at time t, x i (t) represents the position of the i-th particle at time t, represents the best historical position of the i-th particle individual, which is the vehicle with the lowest comprehensive cost among the historical vehicles corresponding to the current path, g best represents the global optimal position of the entire particle swarm, which is the vehicle corresponding to the historical path with the destination corresponding to the current order as the starting point, and the vehicle with the lowest comprehensive cost. c1 and c2 represent learning factors, which control the particle to the historical optimal position respectively. and the global optimal position g best Move, x i(t+1) represents the updated particle position, which is the position of the i-th particle at time t+1, v i (t+1) represents the updated particle velocity, which is the velocity of the i-th particle at time t+1;

[0058] The constructed objective function is optimized according to the updated particle position and velocity, as follows:

[0059] Calculate the updated position x of each particle i (t+1) corresponds to the objective function value Z(x i (t+1)), and optimize according to the calculated objective function value, then we have:

[0060] Based on the optimization of the historical best position of individual particles, we have:

[0061]

[0062] Among them, Z(x i (t+1)) indicates the particle position is x i The corresponding objective function value at (t+1) is, Indicates the objective function value corresponding to the historical best position of the particle individual. By comparing the two, the objective function is optimized. Specifically:

[0063] When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When the current particle position x i (t+1) is updated to the best historical position of the individual particle;

[0064] When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When , the best historical position of the current individual particle remains unchanged;

[0065] The optimization of the global best position based on the particle swarm is to optimize the historical best position of the updated individual particles, then,

[0066]

[0067] Among them, Z(g best ) represents the objective function value corresponding to the particle position being the global optimal position of the particle swarm. Indicates the objective function value corresponding to the historical best position of the particle individual. By comparing the two, the objective function is optimized. Specifically:

[0068] When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When , the historical best position of the current individual particle is updated to the global best position of the particle swarm;

[0069] When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When , the global optimal position of the current particle swarm remains unchanged;

[0070] Finally, according to the updated global optimal position g of the particle swarm best , determine the best path for current cold chain transportation.

[0071] As a preferred solution of the intelligent scheduling system for cold chain transportation described in the present invention, it includes: a transport vehicle and resource matching module, a transport path planning module and an emergency response mechanism formulation module; the transport vehicle and resource matching module realizes accurate scheduling and matching of vehicles and resources according to the transport vehicle information and resource integration; the transport path planning module is used to dynamically plan the transport path of the transport vehicle; the emergency response mechanism formulation module is used to formulate an emergency response mechanism according to the health status of the transport vehicle.

[0072] Beneficial effects of the present invention: The present invention integrates transport vehicle information and resource data, and uses intelligent call algorithms for optimization matching to achieve accurate scheduling of vehicles and resources. It effectively avoids waste of resources and unnecessary transportation costs, and ensures improved transportation efficiency; it uses a particle swarm algorithm for path planning, combined with preliminary path generation and dynamic path optimization, effectively reducing the complexity and uncertainty in path planning, and ensuring high efficiency and reliability in the cold chain transportation process; based on real-time monitoring and historical data, it can identify potential failures of vehicles and equipment in advance, and respond quickly when abnormalities occur. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0074] Figure 1 The figure is a schematic diagram of the overall method steps of an intelligent scheduling method for cold chain transportation of the present invention.

[0075] Figure 2 A schematic diagram of logic judgment for precise scheduling and matching of vehicles and resources in an intelligent scheduling method for cold chain transportation of the present invention.

[0076] Figure 3A schematic diagram of logic judgment for vehicle transport route planning of an intelligent scheduling method for cold chain transport according to the present invention. DETAILED DESCRIPTION

[0077] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0078] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0079] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0080] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0081] Meanwhile, in the description of the present invention, it should be noted that the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0082] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0083] Example 1

[0084] Reference Figure 1 to Figure 3 , which is the first embodiment of the present invention, provides an intelligent scheduling method for cold chain transportation, comprising the following steps:

[0085] S1: Based on the transport vehicle information and resource integration, accurate scheduling and matching of vehicles and resources can be achieved.

[0086] Specifically, the precise scheduling and matching of vehicles and resources is achieved by integrating resources, building a dynamic database, and optimizing the matching of vehicles and the dynamic database using intelligent calling algorithms, as follows:

[0087] Collect data on cold chain transport vehicles and assign a unique number V to each vehicle i , where i represents the vehicle number index, and a vehicle information database is established to record the specific parameter information of each vehicle, then,

[0088] V i ={C i ,W i ,P i}

[0089] Among them, V i represents the unique number of the i-th vehicle, C i represents the cooling capacity of the i-th vehicle, W i represents the loading capacity of the i-th vehicle, P i represents the driving performance of the i-th vehicle;

[0090] Integrate the vehicle number with inventory, order quantity, and warehouse location resource information to build a dynamic database, then we have:

[0091] D(t)={V i ,S j (t),O k (t),L m (t)}

[0092] Among them, V i represents the unique number of the i-th vehicle, S j (t) represents the inventory status of the jth warehouse at time t, O k (t) represents the demand state of the kth order at time t, L m (t) represents the position of the mth warehouse at time t;

[0093] Based on the constructed dynamic database, the target optimization function is formulated, then,

[0094]

[0095] Among them, f(V i ,S j ,O k ,L m ) represents the objective optimization function, which is used to calculate the optimal scheduling plan for each vehicle, d(Vi ,O k ) represents the path cost from the i-th vehicle to the k-th order point, E(V i ,S j ) represents the resource matching degree between the i-th vehicle and the j-th warehouse, α and β represent the path cost weight and resource matching weight, respectively, which are set by real-time personnel according to the actual application scenario.

[0096] Furthermore, the intelligent calling algorithm is used to optimize the matching between vehicles and dynamic databases by designing a multi-objective optimization algorithm to optimize the target optimization function and determine the optimal matching between vehicles and resources. Then,

[0097] The multi-objective optimization algorithm optimizes the path cost between the vehicle and the order point and the matching degree between the vehicle and the warehouse resources, as follows:

[0098] The path cost optimization of vehicles and order points is to calculate the comprehensive cost of the i-th vehicle matching the warehouse to reach the k-th order delivery point, then,

[0099] d(V i ,O k )=α1·D ik +α2·T ik +α3·F ik +α4·C ik +α5·W ik

[0100] α1+α2+α3+α4+α5=1

[0101] Among them, D ik is the distance cost, which indicates the driving distance of the current vehicle to reach the order point, T ik represents the time cost during driving, F ik represents the fuel cost to complete the order, C ik represents the road cost to complete the order, W ik It represents the economic consumption cost of completing the order. α1, α2, α3, α4, and α5 represent the weight coefficients of each item, which are set by the implementer according to the actual application scenario.

[0102] The optimization of the matching degree between vehicles and warehouse resources is to calculate the matching degree between the i-th vehicle and the j-th warehouse resource, then,

[0103] E(V i ,S j )=β1·M ij +β2·L ij +β3·H ij

[0104] β1+β2+β3=1

[0105] Among them, M ij Indicates the matching degree between the vehicle load and the weight of the cargo to be transported, L ij Indicates the matching degree between vehicle cooling capacity and cargo temperature requirement, H ij It indicates the matching degree between the current position of the vehicle and the warehouse position. β1, β2, and β3 represent the weight coefficients of each item, which are set by the implementer according to the actual application scenario.

[0106] Furthermore, the matching degree between the vehicle load and the weight of the goods to be transported is obtained by calculating the ratio of the total weight of the goods to be transported and the current vehicle loading capacity, then,

[0107]

[0108] Among them, W i Indicates the current vehicle loading capacity, W j Indicates the total weight of the goods to be transported, M ij Indicates the matching degree between the vehicle load and the weight of the goods to be transported. The calculation result satisfies 0≤M ij ≤1, the specific matches are as follows:

[0109] When the vehicle loading capacity and the total weight of the goods to be transported satisfy the formula W i <W j When , it means that the current vehicle loading capacity cannot meet the transportation requirements and does not match the weight of the goods to be transported;

[0110] When the vehicle loading capacity and the total weight of the goods to be transported satisfy the formula W i ≥W j When , it means that the current vehicle loading capacity meets the transportation requirements, and a secondary analysis is performed on the matching degree of the weight of the goods to be transported, as follows:

[0111] When the calculation result satisfies the formula M ij →When it is 1, it means that the current vehicle has a higher matching degree with the weight of the cargo to be transported;

[0112] When the calculation result satisfies the formula M ij →0, it means the matching degree between the current vehicle and the weight of the cargo to be transported is lower;

[0113] The matching degree between the vehicle cooling capacity and the cargo temperature requirement is obtained by calculating the ratio of the current vehicle cooling capacity to the cargo temperature requirement. Then,

[0114]

[0115] Among them, C i Indicates the cooling capacity of the current vehicle, C j represents the temperature requirement of the goods to be transported, Cmax , C min They represent the highest cooling temperature and the lowest cooling temperature of all vehicles in cold chain transportation, L ij Indicates the matching degree between the current vehicle and cargo temperature requirements. The specific matching is as follows:

[0116] When the vehicle cooling capacity and cargo temperature requirements meet the formula C i <C j When , it means that the current vehicle cooling capacity cannot meet the transportation requirements and does not match the cargo temperature requirements;

[0117] When the vehicle cooling capacity and cargo temperature requirements meet the formula W i ≥W j When , it means that the current vehicle cooling capacity meets the transportation requirements, and a secondary analysis is conducted on the matching degree with the cargo temperature requirements, as follows:

[0118] When the calculation result satisfies the formula L ij →When it is 1, it means that the current vehicle cooling capacity is more compatible with the cargo temperature requirement;

[0119] When the calculation result satisfies the formula L ij →0, it means that the current vehicle cooling capacity is less compatible with the cargo temperature requirement;

[0120] The matching degree between the current position of the vehicle and the warehouse position is obtained by calculating the distance ratio between the current vehicle position and the warehouse, then,

[0121]

[0122] Among them, D ij Indicates the actual distance between the current vehicle and the warehouse, D max H represents the farthest distance from the warehouse among all vehicles in cold chain transportation. ij Indicates the matching degree between the vehicle's current location and the warehouse location. The specific matching degree is as follows:

[0123] When the calculation result satisfies the formula H ij →1, it means the match between the current vehicle position and the warehouse position is higher;

[0124] When the calculation result satisfies the formula H ij →0, it means that the matching degree between the current position of the vehicle and the warehouse position is lower.

[0125] It should be noted that for the matching degree E(V i ,S j ), the implementer sets a minimum matching threshold E according to the actual application scenario minWhen the matching degree between the vehicle and warehouse resources is greater than the minimum matching degree threshold, it means that the current vehicle matches the warehouse resources, and the transportation task can be assigned. The matching degree between all available vehicles and warehouse resources in cold chain transportation is calculated, and the vehicle to perform the transportation task is selected according to the calculated matching degree to achieve the optimal configuration of resources.

[0126] S2: Plan the vehicle transportation route according to the determined target order.

[0127] Specifically, the path planning for vehicle transportation according to the determined target order is to use the particle swarm algorithm to plan the transportation path for the vehicles that match the order completion, including preliminary path generation and dynamic path planning.

[0128] Furthermore, the initial path generation uses a graph algorithm to generate the initial shortest path between the vehicle and the order. This is done by taking the order destination as a single source point and expanding it to the shortest paths of all other points in sequence, and then finding the shortest path from the single source point to all nodes, as follows:

[0129] Initialize the transportation network as a directed graph G = (N, R), where N represents the node set in the directed graph, which is each warehouse point in the transportation network, and R represents the edge set in the directed graph, which is the connection path between each location in the transportation network;

[0130] Set the order destination as the starting point S p , and will start from the starting point S p The distances to all other nodes are initialized to infinity, but S p The distance of itself is set to 0, and an unprocessed node set Q containing the node set N is set;

[0131] Randomly select a node u from the unprocessed node set Q and calculate the distance from node u to the starting point S p The distance, and remove the node u currently participating in the calculation from the unprocessed node set Q, then,

[0132] R u =argmin u∈Q d(S,u)

[0133] Among them, d(S,u) represents the shortest distance from node u to the starting point S, R u Represents the shortest path from node u to starting point S;

[0134] For a random node u, using the neighbor node v of node u, calculate the shortest distance from node u to the starting point S after passing through the neighbor node v, then we have:

[0135] R u ′=min(d(S,v),d(S,u)+d(u,v))

[0136] Among them, d(S,v) represents the shortest distance from node v to the starting point S, d(S,u) represents the shortest distance from node u to the starting point S, d(u,v) represents the shortest distance from node u to the starting point v, R u ′ represents the shortest path from node u to the starting point S after passing through the neighbor node v;

[0137] By comparing the sizes of the two paths and retaining the shortest path of the two paths, we have:

[0138] If the comparison result satisfies the formula R u ≥R u ′, retain the path R u ′, otherwise the path R is retained u , repeatedly execute the shortest path from a random node in the unprocessed node set Q to the starting point S until the unprocessed node set Q is an empty set, and combine all paths into a preliminary path set P.

[0139] Dynamic path planning is to dynamically optimize the preliminary path set through particle swarm algorithm to determine the optimal cold chain transportation route, as follows:

[0140] Set it as particle swarm I, and use the paths in the preliminary path set P as particles in the particle swarm. By updating the position and speed of the particles, the order of the nodes in the path is adjusted, and then the path set P is optimized to achieve dynamic path planning. The specific planning is as follows:

[0141] Initialize the position of the particle in the particle swarm I0 = x i (0), represents the node order in the preliminary path set P, is the transportation path of the transportation vehicle for the current order, and initializes the particle update speed v i (0), represents the rate of node order adjustment;

[0142] Set the value used to evaluate the particle's current position x i The objective function Z(x) of the path quality of (t) satisfies the formula Z(x) = d(V i ,P), where d(V i ,P) represents the comprehensive cost of the i-th vehicle during the driving path. By updating the position of the particles, the objective function is minimized, and then the optimal path planning for cold chain transportation is realized. Then,

[0143] The particle velocity is updated as follows:

[0144]

[0145] The particle position is updated as follows:

[0146] xi (t+1)=x i (t)+v i (t+1)·(t+1)

[0147] Among them, v i (t) represents the velocity of the ith particle at time t, x i (t) represents the position of the i-th particle at time t, represents the best historical position of the i-th particle individual, which is the vehicle with the lowest comprehensive cost among the historical vehicles corresponding to the current path, g best represents the global optimal position of the entire particle swarm, which is the vehicle corresponding to the historical path with the destination corresponding to the current order as the starting point, and the vehicle with the lowest comprehensive cost. c1 and c2 represent learning factors, which control the particle to the historical optimal position respectively. and the global optimal position g best Move, x i (t+1) represents the updated particle position, which is the position of the i-th particle at time t+1, v i (t+1) represents the updated particle velocity, which is the velocity of the i-th particle at time t+1;

[0148] The constructed objective function is optimized according to the updated particle position and velocity, as follows:

[0149] Calculate the updated position x of each particle i (t+1) corresponds to the objective function value Z(x i (t+1)), and optimize according to the calculated objective function value, then we have:

[0150] Based on the optimization of the historical best position of individual particles, we have:

[0151]

[0152] Among them, Z(x i (t+1)) indicates the particle position is x i The corresponding objective function value at (t+1) is, Indicates the objective function value corresponding to the historical best position of the particle individual. By comparing the two, the objective function is optimized. Specifically:

[0153] When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When the current particle position x i (t+1) is updated to the best historical position of the individual particle;

[0154] When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When , the best historical position of the current individual particle remains unchanged;

[0155] The optimization of the global best position based on the particle swarm is to optimize the historical best position of the updated individual particles, then,

[0156]

[0157] Among them, Z(g best ) represents the objective function value corresponding to the particle position being the global optimal position of the particle swarm. Indicates the objective function value corresponding to the historical best position of the particle individual. By comparing the two, the objective function is optimized. Specifically:

[0158] When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When , the historical best position of the current individual particle is updated to the global best position of the particle swarm;

[0159] When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When , the global optimal position of the current particle swarm remains unchanged;

[0160] Finally, according to the updated global optimal position g of the particle swarm best , determine the best path for current cold chain transportation.

[0161] It should be noted that for the optimization of the objective function, the upper limit of optimization is set based on the number of individual particles until all particles participate in the optimization, indicating that the optimization of the objective function reaches the upper limit. At this time, the corresponding global optimal position is the optimal path.

[0162] S3: Develop emergency response mechanisms based on the real-time health status of transport vehicles.

[0163] Specifically, the emergency response mechanism is formulated based on the real-time health status of the transport vehicle by monitoring the transport vehicle age parameter information in the vehicle dynamic database in real time, and formulating the emergency response mechanism according to the changes in the parameter information, as follows:

[0164] Extract the parameter information of the transport vehicle from the dynamic database, then we have:

[0165] V i ={C i ,W i ,P i}

[0166] Among them, V i represents the unique number of the i-th vehicle, C irepresents the cooling capacity of the i-th vehicle, W i represents the loading capacity of the i-th vehicle, P i represents the driving performance of the i-th vehicle;

[0167] The vehicle health status prediction model is constructed using machine learning algorithms to predict the health status of transport vehicles. At the same time, the historical health data of transport vehicles is used as observation data and input into the vehicle health status prediction model for the formulation of subsequent emergency response mechanisms.

[0168] When the health status prediction result of the transport vehicle V t+k With the observation result V ob The comparison satisfies the formula V t+k <V ob When the vehicle is in an abnormal state, it indicates that the health status of the current vehicle is abnormal. The relevant personnel are notified to replace the transport vehicle, and the abnormal state of the current transport vehicle is recorded in the database for subsequent health analysis.

[0169] When the health status prediction result of the transport vehicle V t+k With the observation result V ob The comparison satisfies the formula V t+k ≥V ob When , it indicates that the health status of the current vehicle is normal, the current vehicle is maintained to perform the transportation task, and the health status of the current transportation vehicle is monitored in real time.

[0170] It should be noted that the real-time monitoring of the health status of transport vehicles is to monitor the parameter information of transport vehicles in real time, including the cooling capacity of transport vehicles, the loading capacity of transport vehicles and the driving performance of transport vehicles.

[0171] The cooling capacity of transport vehicles is measured by real-time monitoring of the health status of the temperature control equipment inside the transport vehicles to reflect the cooling capacity of the current transport vehicles.

[0172] For the loading capacity of transport vehicles, the loading capacity of the current transport vehicles can be reflected by real-time monitoring of the status of the loading space of the transport vehicles;

[0173] As for the driving performance of the vehicle, the health status of the transport vehicle itself and the fuel status during driving are monitored in real time, thereby reflecting the current driving performance of the transport vehicle.

[0174] Example 2

[0175] A second embodiment of the present invention provides an intelligent scheduling system for cold chain transportation, including a transportation vehicle and resource matching module, a transportation route planning module, and an emergency response mechanism formulation module;

[0176] Specifically, the transport vehicle and resource matching module realizes accurate scheduling and matching of vehicles and resources based on transport vehicle information and resource integration; the transport route planning module is used to dynamically plan the transport routes of transport vehicles; and the emergency response mechanism formulation module is used to formulate emergency response mechanisms based on the health status of transport vehicles.

[0177] Furthermore, the transport vehicle and resource matching module collects the key parameters of each transport vehicle in real time, including cooling capacity, load capacity, driving performance, and establishes a vehicle information database through sensors and Internet of Things technology; at the same time, it matches the vehicle information with the inventory, order volume, and warehouse location in the dynamic resource database, and uses a multi-objective optimization algorithm to calculate the optimal scheduling plan for each vehicle. The optimization objectives include path cost, resource matching, etc., to ensure the reasonable scheduling of each vehicle; and provide the best matching vehicle and resource combination for the transport route planning module, making the subsequent route planning more targeted and effective.

[0178] The transport path planning module uses graph algorithms to generate a preliminary path set based on the vehicle and resource combination provided by the vehicle and resource matching module, and provides a path candidate set for subsequent dynamic path optimization to ensure that the best path can be selected under the influence of various variables. At the same time, the particle swarm optimization algorithm is used to dynamically optimize the preliminary path set to ensure that the transport vehicles are transported along the optimal path in actual operations, providing a stable transportation environment for the emergency response mechanism.

[0179] The emergency response mechanism formulation module monitors the cooling system, temperature status and operating performance of transport vehicles in real time according to the numbering system. It uses machine learning models to predict the health status of vehicles and determines whether it is necessary to activate emergency plans based on real-time monitoring data. Through real-time monitoring and prediction of transport vehicles, it ensures rapid response in the event of equipment failure or abnormality to reduce the risk of transport interruption. When a failure or temperature abnormality is detected, the system automatically generates an emergency plan, including dispatching spare vehicles, adjusting routes, or remotely controlling the vehicle's cooling system. Combined with the optimized route output by the route planning module, it re-plans the transport route of spare vehicles to ensure uninterrupted cold chain transportation.

[0180] It should be noted that through the interconnection of various modules, the transport vehicle and resource matching module provides the best vehicle and resource combination for the path planning module, the path planning module provides the optimized path and transportation strategy for the emergency response mechanism formulation module, and the emergency response mechanism module uses the outputs of the first two modules to perform effective fault handling and emergency dispatch; through the coordinated operation of the entire system, accurate matching of vehicles and resources and dynamic path optimization are achieved, which reduces transportation costs and improves transportation efficiency. When equipment failure or temperature abnormality occurs, the system can quickly adjust the transportation plan to ensure the safety of the goods and the continuity of the cold chain system and reduce potential losses. The data sharing and collaborative work between the modules within the system have greatly improved the management level of cold chain transportation and ensured the safety, stability and efficiency of the entire transportation process.

[0181] Furthermore, if the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0182] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0183] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0184] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0185] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, the development effort will be a routine task of design, fabrication, and production without undue experimentation.

[0186] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent scheduling method for cold chain transportation, characterized in that: The following steps are included: According to the transport vehicle information and resource integration, the scheduling and matching of vehicles and resources can be realized; Plan vehicle transportation routes based on determined target orders; Develop emergency response mechanisms based on the real-time health status of transport vehicles.

2. The intelligent scheduling method for cold chain transportation according to claim 1, characterized in that: The scheduling and matching of vehicles and resources is to integrate resources, build a dynamic database, and use intelligent calling algorithms to optimize the matching of vehicles and the dynamic database, as follows: Collect data on cold chain transport vehicles and assign a unique number V to each vehicle i , where i represents the vehicle number index, and a vehicle information database is established to record the specific parameter information of each vehicle, then, V i ={C i ,W i ,P i } Among them, V i represents the unique number of the i-th vehicle, C i represents the cooling capacity of the i-th vehicle, W i represents the loading capacity of the i-th vehicle, P i represents the driving performance of the i-th vehicle; Integrate the vehicle number with inventory, order quantity, and warehouse location resource information to build a dynamic database, then we have: D(t)={V i ,S j (t),O k (t),L m (t)} Among them, V i represents the unique number of the i-th vehicle, S j (t) represents the inventory status of the jth warehouse at time t, O k (t) represents the demand state of the kth order at time t, L m (t) represents the position of the mth warehouse at time t; Based on the constructed dynamic database, the target optimization function is formulated, then, Among them, f(V i ,S j ,O k ,L m ) represents the objective optimization function, which is used to calculate the optimal scheduling plan for each vehicle, d(V i ,O k ) represents the path cost from the i-th vehicle to the k-th order point, E(V i ,S j ) represents the resource matching degree between the i-th vehicle and the j-th warehouse, α and β represent the path cost weight and resource matching weight respectively.

3. The intelligent scheduling method for cold chain transportation according to claim 2, characterized in that: The use of intelligent calling algorithm to optimize the matching of vehicles and dynamic database is specifically as follows: The path cost optimization of vehicles and order points is to calculate the comprehensive cost of the i-th vehicle matching the warehouse to reach the k-th order delivery point, then, d(V i ,O k )=α1·D ik +α2·T ik +α3·F ik +α4·C ik +α5·W ik α1+α2+α3+α4+α5＝1 Among them, D ik is the distance cost, T ik represents the time cost during driving, F ik represents the fuel cost to complete the order, C ik represents the road cost to complete the order, W ik represents the economic consumption cost of completing the order, α1, α2, α3, α4, and α5 represent the weight coefficients of each item; The optimization of the matching degree between vehicles and warehouse resources is to calculate the matching degree between the i-th vehicle and the j-th warehouse resource, then, E(V i ,S j )=β1·M ij +β2·L ij +β3·H ij β1+β2+β3＝1 Among them, M ij Indicates the matching degree between the vehicle load and the weight of the cargo to be transported, L ij Indicates the matching degree between vehicle cooling capacity and cargo temperature requirement, H ij It represents the matching degree between the current position of the vehicle and the warehouse position, and β1, β2, and β3 represent the weight coefficients of each item.

4. The intelligent scheduling method for cold chain transportation according to claim 3, characterized in that: The matching degree between the vehicle load and the weight of the goods to be transported is obtained by calculating the ratio of the total weight of the goods to be transported and the current vehicle loading capacity. Then, Among them, W i Indicates the current vehicle loading capacity, W j Indicates the total weight of the goods to be transported, M ij Indicates the matching degree between the vehicle load and the weight of the goods to be transported. The calculation result satisfies 0≤M ij ≤1, the specific matches are as follows: When the vehicle loading capacity and the total weight of the goods to be transported satisfy the formula W i <W j When , it means that the current vehicle loading capacity cannot meet the transportation requirements and does not match the weight of the goods to be transported; When the vehicle loading capacity and the total weight of the goods to be transported satisfy the formula W i ≥W j When , it means that the current vehicle loading capacity meets the transportation requirements, and a secondary analysis is performed on the matching degree of the weight of the goods to be transported, as follows: When the calculation result satisfies the formula M ij →When it is 1, it means that the current vehicle has a higher matching degree with the weight of the cargo to be transported; When the calculation result satisfies the formula M ij →0, it means that the matching degree between the current vehicle and the weight of the cargo to be transported is lower.

5. The intelligent scheduling method for cold chain transportation according to claim 4, characterized in that: The vehicle transportation route planning according to the determined target order is to use the particle swarm algorithm to plan the transportation route for the vehicle that matches the order completion. Including, preliminary path generation and dynamic path planning.

6. An intelligent scheduling method for cold chain transportation according to claim 5, characterized in that: The preliminary path generation is specifically as follows: Initialize the transportation network as a directed graph G = (N, R), where N represents the node set in the directed graph, which is each warehouse point in the transportation network, and R represents the edge set in the directed graph, which is the connection path between each location in the transportation network; Set the order destination as the starting point S p , and will start from the starting point S p The distances to all other nodes are initialized to infinity, but S p The distance of itself is set to 0, and an unprocessed node set Q containing the node set N is set; Randomly select a node u from the unprocessed node set Q and calculate the distance from node u to the starting point S p The distance, and remove the node u currently participating in the calculation from the unprocessed node set Q, then, R u =argmin u∈Q d(S,u) Among them, d(S,u) represents the shortest distance from node u to the starting point S, R u Represents the shortest path from node u to starting point S; For a random node u, using the neighbor node v of node u, calculate the shortest distance from node u to the starting point S after passing through the neighbor node v, then we have: R u ′=min(d(S,v),d(S,u)+d(u,v)) Among them, d(S,v) represents the shortest distance from node v to the starting point S, d(S,u) represents the shortest distance from node u to the starting point S, d(u,v) represents the shortest distance from node u to the starting point v, R u ′ represents the shortest path from node u to the starting point S after passing through the neighbor node v; By comparing the sizes of the two paths and retaining the shortest path of the two paths, we have: If the comparison result satisfies the formula R u ≥R u ′, retain the path R u ′, otherwise the path R is retained u , repeatedly execute the shortest path from a random node in the unprocessed node set Q to the starting point S until the unprocessed node set Q is an empty set, and combine all paths into a preliminary path set P.

7. An intelligent scheduling method for cold chain transportation according to claim 6, characterized in that: The dynamic path planning is specifically as follows: Set it as particle swarm I, and use the paths in the preliminary path set P as particles in the particle swarm. By updating the position and speed of the particles, the order of the nodes in the path is adjusted, and then the path set P is optimized to achieve dynamic path planning. The specific planning is as follows: Initialize the position of the particle in the particle swarm I0 = x i (0), represents the node order in the preliminary path set P, is the transportation path of the transportation vehicle for the current order, and initializes the particle update speed v i (0), represents the rate of node order adjustment; Set the value used to evaluate the particle's current position x i The objective function Z(x) of the path quality of (t) satisfies the formula Z(x) = d(V i ,P), where d(V i ,P) represents the comprehensive cost of the i-th vehicle during the driving path. By updating the position of the particles, the objective function is minimized and the optimal path planning for cold chain transportation is formed. Then, The particle velocity is updated as follows: The particle position is updated as follows: x i (t+1)=x i (t)+v i (t+1)·(t+1) Among them, v i (t) represents the velocity of the ith particle at time t, x i (t) represents the position of the i-th particle at time t, represents the best historical position of the i-th particle individual, which is the vehicle with the lowest comprehensive cost among the historical vehicles corresponding to the current path, g best represents the global optimal position of the entire particle swarm, which is the vehicle corresponding to the historical path with the destination corresponding to the current order as the starting point, and the vehicle with the lowest comprehensive cost. c1 and c2 represent learning factors, which control the particle to the historical optimal position respectively. and the global optimal position g best Move, x i (t+1) represents the updated particle position, which is the position of the i-th particle at time t+1, v i (t+1) represents the updated particle velocity, which is the velocity of the i-th particle at time t+1; The constructed objective function is optimized according to the updated particle position and velocity, as follows: Calculate the updated position x of each particle i (t+1) corresponds to the objective function value Z(x i (t+1)), and optimize according to the calculated objective function value, then we have: Based on the optimization of the historical best position of individual particles, we have: Among them, Z(x i (t+1)) indicates the particle position is x i The corresponding objective function value at (t+1) is, It indicates the objective function value corresponding to the historical best position of the particle individual. The objective function is optimized through judgment, specifically: When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When the current particle position x i (t+1) is updated to the best historical position of the individual particle; When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When , the best historical position of the current individual particle remains unchanged; The optimization of the global best position based on the particle swarm is to optimize the historical best position of the updated individual particles, then, Among them, Z(g best ) represents the objective function value corresponding to the particle position being the global optimal position of the particle swarm. It indicates the objective function value corresponding to the historical best position of the particle individual. The objective function is optimized through judgment, specifically: When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When , the historical best position of the current individual particle is updated to the global best position of the particle swarm; When the objective function value is compared with the function value corresponding to the historical best position of the particle individual, the formula is satisfied. When , the global optimal position of the current particle swarm remains unchanged; Finally, according to the updated global optimal position g of the particle swarm best , determine the best path for current cold chain transportation.

8. A system using the intelligent scheduling method for cold chain transportation as claimed in any one of claims 1 to 7, characterized in that: Including, transportation vehicle and resource matching module, transportation route planning module and emergency response mechanism formulation module; The transport vehicle and resource matching module realizes accurate scheduling and matching of vehicles and resources based on transport vehicle information and resource integration; The transport path planning module is used to dynamically plan the transport path of the transport vehicle; The emergency response mechanism formulation module is used to formulate an emergency response mechanism according to the health status of the transport vehicle.

Images