CN108108855B - Conveying line path planning method - Google Patents
Conveying line path planning method Download PDFInfo
- Publication number
- CN108108855B CN108108855B CN201810024946.XA CN201810024946A CN108108855B CN 108108855 B CN108108855 B CN 108108855B CN 201810024946 A CN201810024946 A CN 201810024946A CN 108108855 B CN108108855 B CN 108108855B
- Authority
- CN
- China
- Prior art keywords
- path
- conveying line
- node
- conveying
- conveyor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000005540 biological transmission Effects 0.000 claims abstract description 18
- 238000012546 transfer Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 239000003016 pheromone Substances 0.000 claims description 3
- 206010063385 Intellectualisation Diseases 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000010420 art technique Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Control Of Conveyors (AREA)
Abstract
A path planning method for a conveying line is characterized by comprising the following steps: the method comprises the following steps: obtaining the type, length and connection relation of a conveyor in a conveying line, and establishing a topological structure model of the conveying line; step two, extracting an inlet, a load moving and an outlet as nodes, evaluating the path length through the equivalent sum of standard conveyors among the nodes, and further simplifying a topological structure model of the conveying line; step three, solving the path planning of the conveying lines of different scales by adopting a Dijkstra algorithm and an improved ant colony algorithm; and step four, improving the path planning algorithm in the step three according to two constraint conditions that the transmission line generally passes through certain nodes and certain road sections to be jammed in practical application. The invention provides an effective solution for solving the optimal path planning of the conveying line in practical application, improves the intellectualization and conveying capacity of the conveying line, and reduces the workload of operators.
Description
Technical Field
The invention relates to a transportation route planning technology, in particular to a workshop and logistics transportation route technology, and specifically relates to a transportation route planning method.
Background
The conveying line mainly has the function of completing the tasks of conveying, sorting and the like of articles. In production workshops, logistics centers and other transmission scenes, complete and orderly conveying chains which are formed by various conveyors and complete specific functions are adopted and are called conveying lines. With the development of modern logistics systems and industrial production lines, the demands of conveying lines are more complicated and diversified, and path planning faces more challenges. The conveyors in a conveying line form a complex topological relation, a plurality of paths may appear from a certain inlet to a certain outlet, and different paths have different advantages and disadvantages according to conveying distance, conveying time, certain constraint and the like. How to select the optimal feasible conveying path becomes an important research content for planning the conveying path.
Disclosure of Invention
The invention aims to provide a method for finding an optimal feasible conveying path according to conveying requirements in the running process of a conveying line.
The technical scheme of the invention is as follows:
a method for planning a conveying line path is characterized by comprising the following steps:
the method comprises the following steps: obtaining the type, the conveying length and the connection relation of a conveyor in a conveying line, and establishing a topological structure model of the conveying line;
step two, extracting an inlet, a load moving and an outlet as nodes, evaluating the path length through the equivalent sum of standard conveyors among the nodes, and further simplifying a topological structure model of the conveying line;
step three, solving the path planning of the conveying lines of different scales by adopting a Dijkstra algorithm and an improved ant colony algorithm;
and step four, improving the path planning algorithm in the step three according to two constraint conditions that the transmission line generally passes through certain nodes and certain paths are congested in practical application.
The establishment of the transmission line topological structure model comprises the following steps:
taking various conveyors as basic units, disassembling a conveying line into a series of modules, recording the conveying length of each module, and constructing the relationship among the modules by adopting a data structure of a directed graph;
assuming that the conveyor line has n modules, n vertices constituting graph G ═ (V, E), i.e., V ═ V0,v1,...,vn-1The relationship between the vertices in G can be represented by an n × n matrix A, and the elements of the matrix are
A [ i ] [ j ] is equal to 1, which indicates that the module i and the module j are connected, and the connection direction is from the module i to the module j; a [ i ] [ j ] is equal to 0, which means that the module i and the module j are not connected in any direction.
The simplified conveying line topological structure model comprises:
(1) extracting core nodes, and simplifying the structure;
only the transfer conveyor module in the conveying line can complete the path selection in three or four directions; the conveyor module as an inlet or outlet is a structural boundary of the entire conveyor line; other modules only have a transmission function, the interconnecting paths are unique, and path selection does not exist; according to the characteristics, the transfer conveyors in the inlet, the outlet and the three or four directions are used as nodes, and the connection of other conveyors among the nodes is used as a weighting path, so that the structure of the conveying line graph is simplified;
(2) a weighted path length calculation method;
calculating the weighted path length by adopting the equivalent total number of the standard conveyor, wherein the calculating method comprises the following steps:
Qijfor a standard conveyor equivalent total on the path from inode to j, m is the total number of conveyor types, k (1,2,3 …, m) is the conveyor type designation, q is the conveyor type numberkFor the number of class k conveyors in the path, fkAnd taking the linear conveying conveyor as a reference standard to obtain the equivalent conversion coefficient of the kth conveyor, and adjusting the equivalent conversion coefficient according to the actual condition.
A conveyor line path planning algorithm comprising:
for the conveying line with smaller scale, the Dijkstra algorithm is applied to solve the shortest path of the conveying line;
for a conveying line with a large scale, solving the shortest path of the conveying line by adopting an improved ant colony algorithm; the heuristic function of the traditional ant colony algorithm is improved, the influence of the target node on the selection of the next node is increased, and the improved heuristic function is as follows:
ηij(t)＝1/(dij+djg)
in the formula (d)ijIs the path length from node i to node j, djgThe path length from the node j to the target node; and then the probability that the ant k is transferred from the node i to the node j at the moment t is obtained as follows:
in the formula, τij(t) is the amount of information on the path (i, j) at time t, α is the pheromone heuristic, β is the expected heuristic, allowedkA set of nodes may be selected for ant k.
The adjusting strategy of the conveying line path planning algorithm under the constraint of the actual working condition comprises the following steps:
(1) the planning strategy under the constraint of certain nodes is used;
assuming that the path must include a certain node N, the following strategy correction is carried out on the transmission line path planning algorithm: firstly, solving the shortest path and the length from a starting point to a node N, then solving the shortest path and the length from the node N to an end point, and finally carrying out splicing combination; the processing strategy can be expanded to be applied to a path planning problem which must contain a plurality of nodes;
(2) planning strategies under the constraint of certain path congestion;
assuming that a path P (i, j) on the shortest path searched currently is congested, the following strategy correction is carried out on the transmission line path planning algorithm: the path length of the path P (i, j) can be increased by appropriate weights according to the congestion situation; the processing strategy can improve the probability of selecting other unobstructed paths, thereby achieving the purpose of correcting the shortest path.
The invention has the following beneficial effects:
1. the invention completes the model establishment of the topological structure of the conveying line, and adopts the equivalent sum of the standard conveyor to measure the path length, simplifies the structural model and lays a foundation for solving the related problems of the path planning of the conveying line;
2. the method solves the path planning of the large-scale conveying line by using the improved ant colony algorithm, avoids the problem that the complete greedy rule of the traditional ant colony algorithm falls into local optimization, and greatly improves the quality of the path planning;
3. aiming at two constraint conditions that a transmission line generally passes through certain nodes and certain paths to be blocked in practical application, the algorithm is corrected by adopting two adjustment strategies of sectional splicing and path length weighting, so that the intellectualization and the adaptability of the transmission line are improved.
Drawings
FIG. 1 is a flow chart of a transmission line path planning algorithm of the present invention.
Detailed Description
The invention is further described below with reference to the figures and examples.
As shown in fig. 1.
A method for planning a conveying line path comprises the following steps:
the method comprises the following steps: obtaining the type, the conveying length and the connection relation of a conveyor in a conveying line, and establishing a topological structure model of the conveying line;
step two, extracting an inlet, a load moving and an outlet as nodes, evaluating the path length through the equivalent sum of standard conveyors among the nodes, and further simplifying and improving a topological structure model of the conveying line;
step three, solving the path planning of the conveying lines of different scales by adopting a Dijkstra algorithm and an improved ant colony algorithm;
and step four, improving the path planning algorithm in the step three according to two constraint conditions that the transmission line generally passes through certain nodes and certain paths are congested in practical application.
Wherein: the establishment of the transmission line topological structure model refers to the following steps:
the method comprises the steps of taking various conveyors as basic units, disassembling a conveying line into a series of modules, recording the conveying length of each module, and constructing the relationship among the modules by adopting a data structure of a directed graph.
Assuming that the conveyor line has n modules, n vertices constituting graph G ═ (V, E), i.e., V ═ V0,v1,...,vn-1The relationship between the vertices in G can be represented by an n × n matrix a, and the elements of the matrix are:
wherein, A [ i ] [ j ] is equal to 1, which indicates that the module i and the module j are connected, and the connection direction is from the module i to the module j; a [ i ] [ j ] is equal to 0, which means that the module i and the module j are not connected in any direction.
Simplification of a conveyor line topology model, comprising:
(1) core node extraction and structure simplification
Only the transfer conveyor module in the conveying line can complete the path selection in three or four directions; the conveyor module as an inlet or outlet is a structural boundary of the entire conveyor line; and other modules only have a transmission function, the interconnecting path is unique, and no path selection exists. According to the above features, the transfer conveyors in the entrance, the exit, and the three or four directions are used as nodes, and the other conveyor connections between the nodes are used as weighted paths, thereby simplifying the structure of the transfer line graph.
(2) Weighted path length calculation method
Calculating the weighted path length by adopting the equivalent total number of the standard conveyor, wherein the calculating method comprises the following steps:
wherein Q isijFor a standard conveyor equivalent total on the path from inode to j, m is the total number of conveyor types, k (1,2,3 …, m) is the conveyor type designation, q is the conveyor type numberkFor the number of class k conveyors in the path, fkThe equivalent conversion coefficient of the kth conveyor is obtained by taking the linear conveying conveyor as a reference standard, and the equivalent conversion coefficient can be adjusted according to actual conditions.
The path planning algorithm of the conveying lines with different scales comprises the following steps:
and for the conveying line with smaller scale, the Dijkstra algorithm is applied to solve the shortest path of the conveying line.
And for the conveying line with larger scale, solving the shortest path of the conveying line by adopting an improved ant colony algorithm. The heuristic function of the traditional ant colony algorithm is improved, the influence of the target node on the selection of the next node is increased, and the improved heuristic function is as follows:
ηij(t)＝1/(dij+djg)
wherein d isijIs the path length from node i to node j, djgIs the path length between node j to the destination node. And then the probability that the ant k is transferred from the node i to the node j at the moment t is obtained as follows:
wherein, tauij(t) is the amount of information on the path (i, j) at time t, α is the pheromone heuristic, β is the expected heuristic, allowedkA set of nodes may be selected for ant k.
The adjusting strategy of the conveying line path planning algorithm under the constraint of the actual working condition comprises the following steps:
(1) planning strategy under certain node constraint
Assuming that the path must contain a certain node N, the algorithm in step three is modified as follows: and solving the shortest path and length from the starting point to the node N, solving the shortest path and length from the node N to the end point, and finally performing splicing combination. The processing strategy can be extended to be applied to a path planning problem which must contain a plurality of nodes.
(2) Planning strategy under constraint of certain path congestion
Assuming that a path P (i, j) on the shortest path searched currently is relatively congested, the algorithm modification strategy is as follows: the path length of the path P (i, j) can be increased by appropriate weights according to the congestion situation. The processing strategy can improve the probability of selecting other unobstructed paths, thereby achieving the purpose of correcting the shortest path.
The specific application method of the invention comprises the following steps:
firstly, a topological structure model of the conveying line is established and simplified, and then, aiming at each conveying task, the optimal feasible path is obtained by adopting the path planning method provided by the invention. The process is as follows:
firstly, judging whether the conveying requirement is a general shortest path planning problem without any constraint;
if not, performing segmented splicing improvement on the constraint which is bound to pass through certain points, and performing path length weighted improvement on the path congestion constraint; if yes, continuing;
initializing the segment number of the optimal path to be solved, and starting to solve;
if the number of nodes of the current solving section is larger, an improved ant colony algorithm is preferentially adopted for solving; otherwise, adopting Dijkstra algorithm to solve;
if the optimal path can be obtained, judging whether the current solving section is the last section of the path planning or not;
if not, solving the next section in a circulating way; if yes, continuing;
and finally, combining the optimal paths of all the sections to obtain a final result.
The present invention is not concerned with parts which are the same as or can be implemented using prior art techniques.
Claims (1)
1. A method for planning a conveying line path is characterized by comprising the following steps:
the method comprises the following steps: obtaining the type, the conveying length and the connection relation of a conveyor in a conveying line, and establishing a topological structure model of the conveying line;
step two, extracting an inlet, a load moving and an outlet as nodes, evaluating the path length through the equivalent sum of standard conveyors among the nodes, and further simplifying and improving a topological structure model of the conveying line;
step three, solving the path planning of the conveying lines of different scales by adopting a Dijkstra algorithm and an improved ant colony algorithm;
step four, improving a path planning algorithm in the step three according to two constraint conditions that the transmission line generally passes through certain nodes and certain paths are jammed in practical application;
the establishment of the transmission line topological structure model comprises the following steps:
taking various conveyors as basic units, disassembling a conveying line into a series of modules, recording the conveying length of each module, and constructing the relationship among the modules by adopting a data structure of a directed graph;
assuming that the conveyor line has n modules, n vertices constituting graph G ═ (V, E), i.e., V ═ V0,v1,...,vn-1The relationship between the vertices in G can be represented by an n × n matrix A, and the elements of the matrix are
A[i][j]Equal to 1, indicating that there is a connection between module i and module j, and the connection direction is from module i to module j; a [ i ]][j]Equal to 0, it means that module i and module j are not connected in any direction; v denotes a vertex, V0,v1…,vn-1Representing n vertices;
the improved conveying line topological structure model comprises:
(1) extracting core nodes, and simplifying the structure;
only the transfer conveyor module in the conveying line can complete the path selection in three or four directions; the conveyor module as an inlet or outlet is a structural boundary of the entire conveyor line; other modules only have a transmission function, the interconnecting paths are unique, and path selection does not exist; according to the characteristics, the transfer conveyors in the inlet, the outlet and the three or four directions are used as nodes, and the connection of other conveyors among the nodes is used as a weighting path, so that the structure of the conveying line graph is simplified;
(2) a weighted path length calculation method;
calculating the weighted path length by adopting the equivalent total number of the standard conveyor, wherein the calculating method comprises the following steps:
Qijfor a standard conveyor equivalent total on the path from node i to node j, m is the conveyor type totalNumber k is the conveyor type number, k is 1,2,3 …, m, qkFor the number of class k conveyors in the path, fkTaking the linear conveying conveyor as a reference standard to obtain a value of the equivalent conversion coefficient of the kth conveyor, and adjusting the value according to the actual condition;
a conveyor line path planning algorithm comprising:
for the conveying line with smaller scale, the Dijkstra algorithm is applied to solve the shortest path of the conveying line;
for a conveying line with a large scale, solving the shortest path of the conveying line by adopting an improved ant colony algorithm; the heuristic function of the traditional ant colony algorithm is improved, the influence of the target node on the selection of the next node is increased, and the improved heuristic function is as follows:
ηij(t)＝1/(dij+djg)
in the formula (d)ijIs the path length from node i to node j, djgThe path length from the node j to the target node; and then the probability that the ant k is transferred from the node i to the node j at the moment t is obtained as follows:
in the formula, τij(t) is the amount of information on path ij at time t, α is the pheromone heuristic, β is the expected heuristic, allowedkSelecting a set s of nodes as nodes for the ant k;
the adjusting strategy of the conveying line path planning algorithm under the constraint of the actual working condition comprises the following steps:
(1) the planning strategy under the constraint of certain nodes is used;
assuming that a path must pass through a certain node N, the following strategy is modified for the transmission line path planning algorithm: firstly, solving the shortest path and the path length from a starting point to a node N, then solving the shortest path and the path length from the node N to an end point, and finally carrying out splicing combination; the planning strategy can be applied to a path planning problem which needs to pass through a plurality of nodes in an expanded mode;
(2) planning strategies under the constraint of certain path congestion;
assuming that a path ij from a node i to a node j on the currently searched shortest path is relatively congested, the following strategy correction is performed on the transmission line path planning algorithm: increasing the path length of the path ij by appropriate weight according to the congestion condition; the processing strategy can improve the probability of selecting other unobstructed paths, thereby achieving the purpose of correcting the shortest path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810024946.XA CN108108855B (en) | 2018-01-11 | 2018-01-11 | Conveying line path planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810024946.XA CN108108855B (en) | 2018-01-11 | 2018-01-11 | Conveying line path planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108108855A CN108108855A (en) | 2018-06-01 |
| CN108108855B true CN108108855B (en) | 2021-09-28 |
Family
ID=62219840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810024946.XA Active CN108108855B (en) | 2018-01-11 | 2018-01-11 | Conveying line path planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108108855B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840625B (en) * | 2019-01-10 | 2021-03-30 | 华南理工大学 | Courier group path navigation method |
| CN110276539A (en) * | 2019-06-13 | 2019-09-24 | 新奥数能科技有限公司 | Method for building up and method for solving, the device of energy shipping model |
| CN110530101B (en) * | 2019-08-26 | 2020-03-31 | 南京艾数信息科技有限公司 | Household cold chain system with central ice warehouse as core and layout method thereof |
| KR20220100975A (en) * | 2019-11-25 | 2022-07-18 | 상하이 일렉트릭 윈드 파워 그룹 컴퍼니 리미티드 | Cable route planning methods, systems, media and electronic devices in wind farms |
| CN111426330B (en) * | 2020-03-24 | 2022-03-15 | 江苏徐工工程机械研究院有限公司 | Path generation method and device, unmanned transportation system and storage medium |
| CN111970586B (en) * | 2020-08-13 | 2022-08-02 | 电信科学技术第五研究所有限公司 | Rapid optical network path routing calculation method and device under constraint condition and computer medium |
| CN113704934B (en) * | 2021-07-28 | 2023-05-26 | 长江勘测规划设计研究有限责任公司 | Multi-cable path planning method based on graph theory |
| CN114313851A (en) * | 2022-01-11 | 2022-04-12 | 浙江柯工智能系统有限公司 | Modular chemical fiber material transferring platform and method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503789A (en) * | 2016-11-08 | 2017-03-15 | 西安电子科技大学宁波信息技术研究院 | Loop-free shortest path searching method based on Di Jiesitela and minimax ant colony |
| CN106647754A (en) * | 2016-12-20 | 2017-05-10 | 安徽农业大学 | Path planning method for orchard tracked robot |
-
2018
- 2018-01-11 CN CN201810024946.XA patent/CN108108855B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503789A (en) * | 2016-11-08 | 2017-03-15 | 西安电子科技大学宁波信息技术研究院 | Loop-free shortest path searching method based on Di Jiesitela and minimax ant colony |
| CN106647754A (en) * | 2016-12-20 | 2017-05-10 | 安徽农业大学 | Path planning method for orchard tracked robot |
Non-Patent Citations (2)
| Title |
|---|
| 动态路径规划中的改进蚁群算法;周明秀等;《计算机科学》;20130131;第40卷(第1期);第314-316页 * |
| 基于蚁群算法的拥堵交通最短路径研究;杨浩雄等;《计算机仿真》;20150331;第32卷(第3期);第186-191页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108108855A (en) | 2018-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108108855B (en) | Conveying line path planning method | |
| WO2020181761A1 (en) | Sdn enhanced path allocation device and method employing bin-packing technique | |
| CN109039942B (en) | Network load balancing system and balancing method based on deep reinforcement learning | |
| CN105938572B (en) | A kind of more automatic guided vehicle paths planning methods of the pre- anti-interference of logistics storage system | |
| CN106842901B (en) | For the method for train automated driving system formation speed control command | |
| CN104914835A (en) | Flexible job-shop scheduling multi-objective method | |
| CN103971160B (en) | particle swarm optimization method based on complex network | |
| CN105260785B (en) | Logistics distribution vehicle path optimization method based on improved cuckoo algorithm | |
| CN108809839A (en) | Wireless Mesh backbone network network flow control methods and device | |
| CN101482876B (en) | Weight-based link multi-attribute entity recognition method | |
| CN109919532A (en) | Logistics node determination method and device | |
| CN111191918A (en) | Service route planning method and device for smart power grid communication network | |
| CN111988225A (en) | Multi-path routing method based on reinforcement learning and transfer learning | |
| CN105871724A (en) | Method and system for optimizing power communication network circuit | |
| CN108764805A (en) | A kind of multi-model self-adapting recommendation method and system of collaborative logistics Services Composition | |
| CN102163300A (en) | Method for optimizing fault diagnosis rules based on ant colony optimization algorithm | |
| CN105743804A (en) | Data flow control method and system | |
| CN111885493B (en) | Micro-cloud deployment method based on improved cuckoo search algorithm | |
| CN107483355B (en) | Data center-oriented online scene low-bandwidth overhead traffic scheduling scheme | |
| CN101359382A (en) | Dynamic partner selecting method based on ant colony algorithm | |
| CN112629537B (en) | Method and system for dynamically selecting conveying route | |
| CN115062868B (en) | Pre-polymerization type vehicle distribution path planning method and device | |
| CN116629734A (en) | Method, device, equipment and medium for planning article picking path of warehouse system | |
| CN102456073A (en) | Partial extremum inquiry method | |
| CN113988570A (en) | Multi-objective evolutionary algorithm-based tourism bus scheduling optimization method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |