CN106527373A - Workshop automatic scheduling system and method based on mutli-intelligent agent - Google Patents
Workshop automatic scheduling system and method based on mutli-intelligent agent Download PDFInfo
- Publication number
- CN106527373A CN106527373A CN201611100675.9A CN201611100675A CN106527373A CN 106527373 A CN106527373 A CN 106527373A CN 201611100675 A CN201611100675 A CN 201611100675A CN 106527373 A CN106527373 A CN 106527373A
- Authority
- CN
- China
- Prior art keywords
- workpiece
- production
- equipment
- intelligent
- agent
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000004519 manufacturing process Methods 0.000 claims abstract description 274
- 238000007726 management method Methods 0.000 claims description 54
- 238000012545 processing Methods 0.000 claims description 44
- 238000011156 evaluation Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000003754 machining Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000002567 autonomic effect Effects 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 241000196324 Embryophyta Species 0.000 description 6
- 230000002068 genetic effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
Abstract
The invention relates to a workshop scheduling system and method, specifically to a workshop automatic scheduling system and method based on mutli-intelligent agent. In order to realize automatic workshop scheduling, the workshop automatic scheduling system comprises a production information database, an equipment information database, a workpiece intelligent agent group, an equipment intelligent agent group and a logistics intelligent agent, wherein the logistics intelligent agent is configured to execute a received instruction sent by the workpiece intelligent agent group, and can monitor the working state of the corresponding logistics tools on a real-time basis. The intelligent agents cover all workpieces, equipment and logistics tools, and data during a production process can be conveniently collected. Production state and equipment operation can be monitored, and alarm can be given timely when a fault occurs. Automatic adjustment can be made according to the change of workshop environment, thereby improving the robustness and reliability of a system.
Description
Technical Field
The invention relates to a workshop scheduling system and method, in particular to a workshop autonomous scheduling system and method based on multiple intelligent agents.
Background
The workshop scheduling is the key for realizing high production efficiency and high flexibility. The workshop scheduling generally comprises a task set to be processed, a processing equipment set and a performance index set, and aims to select a scheduling rule on the basis of the existing processing equipment according to the processing requirement of an object to be processed, so that the performance index set (comprising one or more performance indexes) is optimal. Objects to be processed in the workshop scheduling problem generally need to be processed by one or more processing devices according to a certain sequence, one device can only process one processed part at a certain time point, one processed part can only be processed by one processing device at a certain time point, and the scheduling scheme problem for solving and optimizing performance indexes such as shortest time, lowest cost and the like belongs to an NP (Non-Deterministic Polynomial) problem.
As a research hotspot in the field of artificial intelligence, a multi-agent system is a collection of multiple agents, whose goal is to build large and complex systems into small, easily manageable systems that communicate and coordinate with each other. The agents in the multi-agent system have adaptivity, learning ability and the ability to interact with the environment and other agents, and the multi-agent system is obtained by organizing the agents through a proper structure. The agents in a multi-agent system play different roles, coordinate with each other, and cooperate with each other to accomplish complex tasks.
As the scale of the workshop is enlarged and the constraint conditions are increased, the dynamic complexity of the workshop scheduling is more and more prominent. At present, when a multi-agent system is applied to workshop scheduling, a three-layer structure of management-resource-task agents is generally adopted, and the three-layer structure is respectively used for performing complex coordination work, managing processing equipment resources and receiving and distributing tasks. The mode of applying the multi-agent system to workshop scheduling actually only divides the workshop scheduling into a plurality of modules for processing, does not take basic workpieces, equipment and logistics tools as basic intelligent units, and cannot realize the autonomous workshop scheduling, namely, the problem of workshop scheduling cannot be solved through interaction of agents.
Based on this, there is a need in the art for new systems and methods for autonomic plant scheduling that address the above-mentioned problems.
Disclosure of Invention
In order to solve the problems in the prior art, namely the problem of realizing the autonomous dispatching of the workshop, the invention provides a workshop autonomous dispatching system based on multiple intelligent agents.
This workshop is dispatch system independently includes: the system comprises a production information base, an equipment information base, a workpiece intelligent agent group, an equipment intelligent agent group and a logistics intelligent agent;
the production information base is configured to store production information;
the equipment information base is configured to store production equipment information;
the workpiece intelligent agent group is configured to be capable of receiving a production plan and reading production information matched with the received production plan from the production information base, and sending the read production information corresponding to the received production plan to the equipment intelligent agent group;
the equipment intelligent agent group is configured to be capable of receiving the production information sent by the workpiece intelligent agent group, reading the production equipment information from the equipment information base, and performing feasibility judgment on the production plan according to the read production equipment information;
the logistics intelligent agent is configured to be capable of executing the received instruction sent by the workpiece intelligent agent group and monitoring the working state of the corresponding logistics tool in real time.
In the above-mentioned workshop autonomous scheduling system, the workpiece intelligent agent group includes: the intelligent body of the workpiece main pipe, the intelligent body of the workpiece branch pipe and the intelligent body of the workpiece.
Each workpiece intelligent body corresponds to a workpiece to be machined, the workpiece intelligent bodies can monitor the machining state of the workpiece to be machined in real time and upload the machining state data of the workpiece to be machined to the workpiece branch pipe intelligent bodies;
each workpiece branch intelligent agent is configured to receive data uploaded by the workpiece intelligent agent and upload the data to the workpiece main pipe intelligent agent;
the workpiece main pipe intelligent body is configured to receive data uploaded by the workpiece branch pipe intelligent body, so that the processing state of the workpieces in the workshop is monitored in real time.
In the above autonomous scheduling system for a plant, the intelligent group of devices includes: the intelligent agent for the main equipment pipe, the intelligent agent for the branch equipment pipe and the intelligent agent for the equipment.
Each equipment agent corresponds to one processing equipment, and the equipment agents can monitor the working state of the processing equipment in real time and upload the working state data of the processing equipment to the equipment branch management agents;
each equipment branch management intelligent agent is configured to receive data uploaded by the equipment intelligent agents and upload the data to an equipment main pipe intelligent agent;
and the equipment main pipe intelligent body is configured to receive the data uploaded by the equipment branch pipe intelligent body, so that the equipment state of the workshop is monitored in real time.
In the workshop autonomous scheduling system, the workpiece main pipe intelligent body can receive a production plan, read production information matched with the received production plan from the production information base and send the read production information to the equipment main pipe intelligent body;
the equipment main pipe intelligent body receives the production information sent by the workpiece main pipe intelligent body, reads the production equipment information from the equipment information base, and carries out feasibility judgment on the production plan according to the read production equipment information;
the production information stored in the production information base comprises production content information, production constraint information and optimization target information; the production equipment information stored in the equipment information base comprises basic information and production information of production equipment.
In the above-mentioned autonomous scheduling system for a plant, the system further includes:
the behavior record library is configured to receive data generated in the production process and sent by the workpiece management agent and the equipment management agent;
the decision support library is configured to store decision support information, and the decision support information comprises a scheduling strategy, evaluation information and an abnormal problem solution; and the decision support library can be updated according to the data stored in the behavior record library.
In the autonomous workshop scheduling system, when the equipment main pipe intelligent body judges that a production plan is feasible according to read production equipment information, the equipment main pipe intelligent body sends the production equipment information corresponding to each equipment branch pipe body to the workpiece main pipe intelligent body, the workpiece main pipe intelligent body decomposes the production plan into various production tasks according to the production equipment information of each equipment branch pipe intelligent body, and transfers the production tasks to the workpiece branch pipe intelligent bodies corresponding to the equipment branch pipe intelligent bodies;
when the equipment main pipe intelligent body judges that the production plan is not feasible according to the read production equipment information, the equipment main pipe intelligent body feeds back the production plan infeasibility information to the workpiece main pipe intelligent body, and the workpiece main pipe intelligent body sends out a production plan infeasibility prompt.
In the autonomous workshop scheduling system, after the workpiece branch management intelligent agent receives production task information, corresponding production equipment information is obtained from the equipment branch management intelligent agent, and a task model is established according to the production equipment information and the production task information; and the workpiece sub-management intelligent agent reads a scheduling strategy from the decision support library according to the established task model and sends the task model and the scheduling strategy to the workpiece intelligent agent.
In the autonomous dispatching system of the workshop, the workpiece intelligent agent calculates an optimal dispatching scheme according to the received task model and the dispatching strategy and sends the optimal dispatching scheme to the workpiece branch management intelligent agent; and the workpiece branch intelligent body sends the optimal scheduling scheme to the workpiece main pipe intelligent body, and the workpiece main pipe intelligent body redistributes the production tasks according to the received optimal scheduling scheme and judges the feasibility of the redistributed production tasks.
In the autonomous workshop scheduling system, when the workpiece main pipe intelligent agent judges that the redistributed production task is feasible, the workpiece main pipe intelligent agent sends a feasibility instruction to the workpiece branch pipe intelligent agent, the workpiece branch pipe intelligent agent sends the feasibility instruction to the workpiece intelligent agent, the workpiece intelligent agent receives the feasibility instruction and sends a task instruction to the logistics intelligent agent, and the logistics intelligent agent receives and executes the task instruction; and when the workpiece main pipe intelligent body judges that the redistributed production task is not feasible, the workpiece main pipe intelligent body sends out a production plan infeasible prompt.
On the other hand, the invention also provides a workshop autonomous scheduling method based on the multi-agent, which comprises the following steps:
step 10, receiving a production plan through a workpiece main pipe intelligent body and sending the production plan to an equipment main pipe intelligent body;
step 20, the equipment main pipe intelligent agent carries out feasibility judgment on the received production plan;
step 30, under the condition that the production plan is feasible, decomposing the production plan by the workpiece main pipe intelligent body, and transferring a production task to the workpiece branch pipe intelligent body;
step 40, the workpiece sub-management intelligent agent establishes a task model according to the received production task, reads a scheduling strategy from a decision support library according to the task model, and then sends the task model and the scheduling strategy to the workpiece intelligent agent;
step 50, the workpiece intelligent agent sends a task instruction to the logistics intelligent agent according to the received task model and the received scheduling strategy;
and step 60, executing the received instruction by the logistics intelligent agent.
In the above method, step 30 further comprises:
step 301, under the condition that the production plan is not feasible, feeding back the production plan infeasible information to the workpiece main pipe intelligent agent by the equipment main pipe intelligent agent, and sending out a production plan infeasible prompt by the workpiece main pipe intelligent agent.
In the above method, step 40 further comprises:
step 401, after receiving production task information, the workpiece branch management agent obtains production equipment information from the equipment branch management agent, and establishes a task model according to the production equipment information and the production task information.
In the above method, step 50 further comprises:
step 501, the workpiece intelligent agent performs parallel calculation on the received task model and the scheduling strategy to obtain an optimal scheduling strategy, and sends the optimal scheduling strategy to the workpiece branch management intelligent agent;
step 502, the workpiece branch intelligent agent sends the optimal scheduling scheme to the workpiece main pipe intelligent agent, and the workpiece main pipe intelligent agent redistributes the production tasks according to the received optimal scheduling scheme and judges the feasibility of the redistributed production tasks;
step 503, in a case that the optimal scheduling policy is feasible, the workpiece main pipe agent sends a feasibility instruction to the workpiece branch pipe agent, the workpiece branch pipe agent sends the feasibility instruction to the workpiece agent, the workpiece agent receives the feasibility instruction and sends a task instruction to the logistics agent, and the logistics agent receives and executes the task instruction;
and step 504, under the condition that the optimal scheduling strategy is not feasible, the workpiece main pipe intelligent agent sends out a production plan infeasible prompt.
In summary, the workshop site resources of the invention are divided into a workpiece intelligent agent group, an equipment intelligent agent group and a logistics intelligent agent group, a single workpiece to be processed, processing equipment and a logistics tool are all regarded as intelligent agents, and the receiving, the transferring, the autonomous scheduling and the implementation of the production plan are realized through the mutual cooperation among the intelligent agents. In addition, the application of the multi-agent system is equivalent to the introduction of a plurality of expert systems which complement and cooperate with each other, so that the complex problem of the multi-agent system can be simplified, the multi-agent high-efficiency parallel processing can process the large-scale scheduling problem, the production efficiency and the product quality are improved, and the cost is reduced. In addition, the intelligent agent covers all workpieces to be processed, equipment and logistics tools, so that data in the production process can be conveniently collected, the production state and the equipment running condition are monitored, a fault is given out in time, self-adaptive adjustment is carried out according to the change of the workshop environment, and the robustness and the reliability of the system are improved.
Drawings
FIG. 1 is a schematic structural diagram of a multi-agent based autonomous scheduling system for a plant of the present invention;
FIG. 2 is a flow chart of the multi-agent based autonomous scheduling method for a plant of the present invention.
Detailed Description
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and are not intended to limit the scope of the present invention.
The invention discloses a workshop autonomous scheduling system based on multiple intelligent agents, which divides resources related to a workshop site into a workpiece intelligent agent group, an equipment intelligent agent group and a logistics intelligent agent. The whole process from the input of the production plan to the output of the product is completed through the mutual coordination and cooperation among the workpiece intelligent agent group, the equipment intelligent agent group and the logistics intelligent agent.
The technical solution of the present invention will be described in detail below with reference to the accompanying drawings. As shown in fig. 1, the multi-agent-based autonomous workshop scheduling system of the present invention mainly includes a production information base, an equipment information base, a workpiece agent group, an equipment agent group, and a logistics agent.
The production information repository is configured to store production information. Specifically, the production information stored in the production information library mainly includes information such as production contents (e.g., a type of a product to be produced, a production quantity, a processing manner, processing time, a construction period, and the like), optimization objectives (e.g., a minimum time that can be achieved by the entire production process, a minimum energy consumption, and the like), production constraints (e.g., a preparation time, a delivery time, and a priority constraint, and the like), and the like.
The device information base is configured to store production device information, which specifically includes basic information of the production device (such as name, type, time, etc. of the device) and production information of the device (such as production speed, accuracy, etc. of the device).
The workpiece intelligent agent group is configured to be capable of receiving the production plan and reading production information matched with the received production plan from the production information base, and sending the read production information corresponding to the received production plan to the equipment intelligent agent group. Wherein, the work piece intelligent object group includes that the work piece house steward intelligence body, work piece divide a tub intelligent object and the work piece intelligent object.
The equipment intelligent agent group is configured to receive the production information sent by the workpiece intelligent agent group, read the production equipment information from the equipment information base and conduct feasibility judgment on the production plan according to the read production equipment information. The equipment intelligent agent group comprises an equipment main pipe intelligent agent, an equipment branch pipe intelligent agent and an equipment intelligent agent.
The logistics intelligent agent is configured to be capable of receiving and executing the instruction sent by the workpiece intelligent agent group and monitoring the working state of the corresponding logistics tool in real time. Wherein, every commodity circulation intelligent agent corresponds a commodity circulation instrument that is used for transporting the instrument of treating processing, and the operating condition of the commodity circulation instrument that the real-time supervision of commodity circulation intelligent agent corresponds to when the commodity circulation instrument breaks down, in time send out the police dispatch newspaper and remind.
In one embodiment of the invention, the workpiece manifold agent and the equipment manifold agent are located in a field control center. The intelligent workpiece branch management body and the intelligent equipment branch management body are located in corresponding fixed areas, namely production areas which are respectively responsible for the intelligent workpiece branch management body and the intelligent equipment branch management body, and have the functions of displaying, alarming, bar code or RFID scanning reading and writing, data storage, wired and wireless communication, high-performance computing capacity, database access and production condition monitoring permission. The workpiece intelligent body, the equipment intelligent body and the logistics intelligent body are respectively fixed on the workpiece, the equipment and the logistics tool in an adsorption or clamping mode, have alarm, wireless communication, data storage and low-performance computing capabilities, and have the authority of monitoring the state of the workpiece or the equipment.
The plant autonomous scheduling system further comprises a behavior record library and a decision support library.
The behavior record library is configured to receive data generated in the production process and sent by the workpiece management agent and the equipment management agent. The system specifically comprises a workpiece intelligent agent group, an equipment intelligent agent group and data generated by a logistics intelligent agent in the production process.
The decision support library is configured to store decision support information, and the decision support information mainly includes scheduling strategies, evaluation information, abnormal problem coping strategies and the like. Specifically, the scheduling strategy comprises a scheduling model, a solving method, solving parameter setting, intelligent agent task allocation, execution result feedback and evaluation scores. The solving method comprises a basic operation research algorithm, a neighborhood searching algorithm and an agent-based algorithm which correspond to the model; the evaluation scores are used for different models to describe the adaptation degree of the algorithm to the models. The evaluation information comprises error rates, production states, aging degrees and the like of the intelligent controller, the logistics tool and the processing equipment and a comprehensive evaluation score obtained through weighting. The abnormal problem handling strategy mainly comprises a processing scheme when task change, equipment failure, intelligent agent failure or raw material deficiency occurs. In addition, the decision support library can be updated according to the data stored in the behavior record library, namely, the decision support information can be continuously updated and expanded along with the production.
In this embodiment, the workshop is divided into a plurality of fixed areas, and each fixed area is provided with a corresponding workpiece management agent and a corresponding equipment management agent to respectively manage the workpiece agents and the equipment agents in the fixed area.
Each workpiece intelligent body corresponds to a workpiece to be machined, the workpiece intelligent bodies can monitor the machining state of the workpiece to be machined in real time and upload the machining state data of the workpiece to be machined to the corresponding workpiece branch pipe intelligent bodies; each equipment intelligent agent corresponds to one processing equipment, and the equipment intelligent agent can monitor the working state of the processing equipment in real time and upload the working state data of the processing equipment to the corresponding equipment branch management intelligent agent.
Each workpiece sub-pipe intelligent agent is configured to receive data uploaded by the workpiece intelligent agent and upload the data to the workpiece main pipe intelligent agent. Each device sub-management agent is configured to receive data uploaded by the device agents and upload the data to the device main management agent. Each equipment branch management agent can also acquire the state information (such as vibration, temperature, sound and the like, which cannot be automatically acquired, and is manually checked and recorded) of the equipment in the fixed area, and sends the state information of the equipment to the equipment information base for updating the equipment information base.
All the intelligent bodies related to the workpieces of the intelligent body main pipe of the workpiece main pipe can receive data uploaded by the intelligent bodies of the workpiece branch pipes, so that the processing state of the workpieces in a workshop can be monitored in real time. When the processing state of the workshop workpiece is monitored, the production progress and production fault lamp information of the workshop can be displayed through the monitoring platform, and the conditions appearing in the production process are timely fed back to workshop management personnel. The workpiece main pipe intelligent agent is responsible for receiving the production plan, reading production information matched with the received production plan from the production information base, wherein the production information comprises production content information, production constraint information, optimization target information and the like, and sending the production information to the equipment main pipe intelligent agent.
All the related agents of the main agent intelligent agent of the main agent of the equipment can receive the data uploaded by the intelligent agents of the branch agents of the equipment, thereby monitoring the equipment state of the workshop in real time and reporting the equipment state information to the workshop management personnel in time. The equipment main pipe intelligent body receives the production information sent by the workpiece main pipe intelligent body and reads the production equipment information from the equipment information base, and the feasibility of the production plan is judged according to the workshop production equipment information, namely whether the conditions of the production equipment meet the requirements of the production plan is judged.
When the equipment main pipe intelligent body judges that the production plan is not feasible (namely the conditions of the production equipment do not meet the production plan) according to the read production equipment information, the equipment main pipe intelligent body feeds back the production plan infeasibility information to the workpiece main pipe intelligent body, the workpiece main pipe intelligent body sends out a production plan infeasibility prompt, and a plan making department reforms the production plan.
When the equipment main pipe intelligent body judges that the production plan is feasible according to the read production equipment information (namely the condition of the production equipment meets the production plan), the equipment main pipe intelligent body sends the production equipment information corresponding to each equipment branch pipe body to the workpiece main pipe intelligent body, the workpiece main pipe intelligent body decomposes the production plan according to the production equipment information of each equipment branch pipe intelligent body, and transfers the production task to the workpiece branch pipe intelligent body corresponding to the equipment branch pipe intelligent body.
After receiving the lowered production task (i.e. the decomposed production plan), the workpiece branch management agent obtains production equipment information from the equipment branch management agent responsible for the production equipment in the fixed area, wherein the production equipment information comprises the number of the production equipment, the production time of each process, the application limit of the equipment, the buffer area between the equipment and the like, and a task model is established by combining the production task information (basic information such as processing time, construction period and the like and optimization targets). Specifically, the task model established by the intelligent agent for managing workpieces according to the production equipment information and the production task information is generally represented by a < E, R, O > triple, wherein E represents an environment, R represents a constraint, and O represents a target. The environment represents a workshop production equipment environment which mainly comprises a flow shop, a processing shop and an open shop, and if parallel equipment exists, the workshop environment has certain flexibility; workpieces in the flow shop have the same determined processing paths, workpieces in the processing shop have the determined processing paths, the processing paths may be the same or different, and an open shop has no specific processing path, which is not common generally; due to the addition of parallel equipment, processing nodes in the same processing path have multiple choices, and the flexibility of a processing workshop is improved. The constraints mainly comprise task constraints, equipment constraints and other constraints; the task constraint comprises a submission date and constraint contents specified by a processing priority constraint task; the equipment constraint comprises workpiece constraint and time constraint applied by equipment, the workpiece is processed on one kind of equipment, but not all the same kind of equipment can process the workpiece, and meanwhile, the time point applied by the equipment and the maximum time of continuous operation are limited; other constraints refer to constraints other than those described above. The objective is mainly to schedule the index to be optimized, usually to minimize or maximize some objective function, and generally to have the objectives of minimizing the manufacturing period, minimizing the maximum delay time, and so on.
The task model triplets are combined according to actual conditions, and for a specific production workshop, the task triplets are determined in most cases, namely the task model is known. The corresponding task model has a mature scheduling algorithm (for example, for a deterministic processing workshop, a conversion bottleneck heuristic algorithm proposed by Adams, Balas and Zawack is used for solving the unconstrained processing workshop problem of minimized manufacturing period which is common in a production field, Nakano and Yamada apply the traditional genetic algorithm to the method for scheduling the processing workshop, a feasible solution which is as close to an optimal solution as possible is obtained through proper coding, and on the basis, the method is combined with heuristic algorithms such as simulated annealing, tabu search algorithm and the like to obtain a more accurate or solution which can solve the scheduling problem under the condition of various constraints, the recent achievements include the application of improved heuristic algorithms, such as the improved genetic algorithm and the improved artificial fish swarm algorithm, obtain good achievements, the methods have strong applicability, can process the problems of constraint and multi-objective optimization, and for a multi-agent structure, the method based on the market and the agent is simple and easy to implement, has strong adaptability and can find a better feasible solution although the precision is poorer than that of other targeted optimization algorithms, and can be used for processing the scheduling problem of a complex environment by adding a learning mechanism; genetic algorithms and agent-based methods have been embodied in some ERP and MES systems, such as the well-known SAP system; the description of other task models is omitted, but corresponding feasible solutions can be found through existing algorithms generally), and the algorithms are stored in a decision support library.
And the workpiece branch management intelligent agent reads the scheduling strategy from the decision support library according to the established task model and sends the established task model and the read scheduling strategy to the workpiece intelligent agent. Specifically, after a task model is established, a workpiece sub-management intelligent agent firstly queries whether the same instance exists in a decision support library, and if the same instance exists, the scheduling strategy in the instance is directly sent to the workpiece intelligent agent; if the same instance does not exist, selecting a corresponding scheduling strategy according to the task model, changing parameters of the scheduling strategy according to the task model information, and sending the obtained scheduling strategy to the workpiece intelligent agent; if there is no same instance or no scheduling policy corresponding to the task model, the agent-based or knowledge-based approach may be used by the agent-managed agent to find a feasible scheduling policy and send the obtained scheduling policy to the agent.
In a possible implementation manner, when the workpiece management agent queries the corresponding scheduling policy in the decision support library, the task model evaluation score can be selected from top to bottom according to a scheduling policy algorithm.
The workpiece intelligent agent calculates an optimal solution of task allocation in a mode of parallel computing of a plurality of workpiece intelligent agents according to the received task model and the scheduling strategy, and sends the obtained optimal scheduling scheme to the workpiece main pipe intelligent agent; and the workpiece main pipe intelligent body redistributes the production tasks according to the received optimal scheduling scheme and judges the feasibility of the redistributed production tasks. Specifically, because the production capacity of each fixed area is different, the production task index assigned to the workpiece master pipe agent by the workpiece master pipe agent may not meet the optimal scheduling scheme, may just meet the optimal scheduling scheme, and may exceed the optimal scheduling scheme. Therefore, the workpiece main pipe intelligent agent redistributes the production tasks, so that the fixed area which is responsible for each workpiece branch pipe intelligent agent can complete the production tasks. The workpiece main pipe intelligent body sends the production capacity information of the area which is responsible for each workpiece branch pipe intelligent body to the equipment main pipe intelligent body and writes the information into a production information base, whether the production task requirements such as manufacturing period and delay are met is checked, when the redistributed production task is not feasible (the production task requirements such as manufacturing period and delay are not met), the workpiece main pipe intelligent body sends out a production plan non-feasibility prompt, and a manager reformulates a production plan.
When the workpiece main pipe intelligent body judges that the redistributed production task is feasible (the production task requirements such as manufacturing period, delay and the like are met), the workpiece main pipe intelligent body sends a feasibility instruction to the workpiece branch pipe intelligent body, the workpiece branch pipe intelligent body sends the feasibility instruction to the workpiece intelligent body, the workpiece intelligent body receives the feasibility instruction and sends a task instruction to the logistics intelligent body, and the logistics intelligent body receives and executes the task instruction. Specifically, the logistics intelligent agent sends the received instruction to the logistics tool controller, and the logistics tool controller controls the logistics workpiece to carry the tool to be processed to the designated processing equipment to be processed, so that the production tasks are completed in sequence. And the workpiece intelligent agent and the equipment intelligent agent record data obtained in the production process and respectively upload the data to the workpiece branch management intelligent agent and the equipment branch management intelligent agent for temporary storage. When an abnormal problem occurs in the production process, inquiring an abnormal problem coping strategy in the decision support library, selecting a corresponding solution, and when the solution of the abnormal problem does not exist in the decision support library, sending an alarm and reminding workshop management personnel.
After the production plan is finished, the workpiece branch management intelligent agent and the equipment branch management intelligent agent store the received data, operation information, abnormal problem solution, evaluation information and the like in a behavior record library; the decision support library reads the content in the behavior record library, adjusts the evaluation score of the scheduling strategy according to the execution condition, records the optimized scheduling strategy parameters, reads the abnormal condition occurring in the execution process and records the solution, and mines the potential problem in the data through data analysis to perform fault early warning.
On the other hand, the invention also provides a workshop autonomous scheduling method based on the multi-agent. The method comprises the following steps:
and step 10, receiving the production plan through the workpiece main pipe intelligent body and sending the production plan to the equipment main pipe intelligent body. In this step, the workpiece main pipe intelligent agent performs preliminary analysis on the received production plan, acquires production content information, production constraint information, and optimization target information, and sends the production content information, the production constraint information, and the optimization target information to the equipment main pipe intelligent agent.
And 20, the equipment main pipe intelligent agent judges the feasibility of the received production plan. In this step, the equipment main intelligent agent receives the production content information, the production constraint information and the optimization target information, reads the equipment information base, and judges the feasibility of the production plan according to the read production equipment information.
And step 30, under the condition that the production plan is feasible, decomposing the production plan by the workpiece main pipe intelligent body, and transferring the production task to the workpiece branch pipe intelligent body. Specifically, the equipment main pipe intelligent body sends the production capacity information of the area which is responsible for each equipment branch intelligent body to the workpiece main pipe intelligent body, and the workpiece main pipe intelligent body decomposes the production plan and transfers the production plan to the workpiece branch intelligent body. And under the condition that the production plan is not feasible, the equipment main pipe intelligent body feeds back the production plan infeasible information to the workpiece main pipe intelligent body, and the workpiece main pipe intelligent body sends out a production plan infeasible prompt.
And step 40, the workpiece branch management intelligent agent establishes a task model according to the received production task, reads the scheduling strategy from the decision support library according to the task model, and then sends the task model and the scheduling strategy to the workpiece intelligent agent. In the step, after the workpiece branch management intelligent agent receives the production task information, the production equipment information is obtained from the equipment branch management intelligent agent, and a task model is established according to the production equipment information and the production task information. Reference is made in particular to the description hereinbefore.
And step 50, the workpiece intelligent agent sends a task instruction to the logistics intelligent agent according to the received task model and the scheduling strategy. In this step, the method further includes:
step 501, the workpiece intelligent agent performs parallel calculation on the received task model and the scheduling strategy to obtain an optimal scheduling strategy, and sends the optimal scheduling strategy to the workpiece sub-management intelligent agent.
And 502, the workpiece branch intelligent agent sends the optimal scheduling scheme to the workpiece main pipe intelligent agent, and the workpiece main pipe intelligent agent redistributes the production tasks according to the received optimal scheduling scheme and judges the feasibility of the redistributed production tasks.
Step 503, under the condition that the optimal scheduling strategy is feasible, the workpiece main pipe intelligent body sends a feasibility instruction to the workpiece branch pipe intelligent body, the workpiece branch pipe intelligent body sends the feasibility instruction to the workpiece intelligent body, the workpiece intelligent body receives the feasibility instruction and sends a task instruction to the logistics intelligent body, and the logistics intelligent body receives and executes the task instruction.
And step 504, under the condition that the optimal scheduling strategy is not feasible, the workpiece main pipe intelligent body sends out a production plan infeasible prompt.
And step 60, the logistics intelligent agent executes the received instruction. Specifically, the logistics intelligent agent sends the received instruction to the logistics tool controller, and the logistics tool controller controls the logistics workpiece to carry the tool to be processed to the designated processing equipment to be processed, so that the production tasks are completed in sequence.
In this embodiment, after the production plan is completed, the workpiece management agent and the equipment management agent store the received data, operation information, abnormal problem solution, evaluation information, and the like in the behavior record library; and the decision support library adjusts the evaluation score of the scheduling strategy according to the content in the behavior record library, records the optimized scheduling strategy parameters, reads abnormal conditions occurring in the execution process, records a solution, and mines potential problems in the data through data analysis to perform fault early warning.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (13)
1. A multi-agent based autonomous workshop scheduling system, the system comprising: the system comprises a production information base, an equipment information base, a workpiece intelligent agent group, an equipment intelligent agent group and a logistics intelligent agent;
the production information base is configured to store production information;
the equipment information base is configured to store production equipment information;
the workpiece intelligent agent group is configured to be capable of receiving a production plan and reading production information matched with the received production plan from the production information base, and sending the read production information corresponding to the received production plan to the equipment intelligent agent group;
the equipment intelligent agent group is configured to be capable of receiving the production information sent by the workpiece intelligent agent group, reading the production equipment information from the equipment information base, and performing feasibility judgment on the production plan according to the read production equipment information;
the logistics intelligent agent is configured to be capable of executing the received instruction sent by the workpiece intelligent agent group and monitoring the working state of the corresponding logistics tool in real time.
2. The system of claim 1, wherein the group of artifact agents comprises: the intelligent workpiece body, the intelligent workpiece pipe distribution body and the intelligent workpiece main pipe body;
each workpiece intelligent body corresponds to a workpiece to be machined, the workpiece intelligent bodies can monitor the machining state of the workpiece to be machined in real time and upload the machining state data of the workpiece to be machined to the workpiece branch pipe intelligent bodies;
each workpiece branch intelligent agent is configured to receive data uploaded by the workpiece intelligent agent and upload the data to the workpiece main pipe intelligent agent;
the workpiece main pipe intelligent body is configured to receive data uploaded by the workpiece branch pipe intelligent body, so that the processing state of the workpieces in the workshop is monitored in real time.
3. The system of claim 2, wherein the set of device agents comprises: the intelligent device, the main intelligent device and the branch intelligent device;
each equipment agent corresponds to one processing equipment, and the equipment agents can monitor the working state of the processing equipment in real time and upload the working state data of the processing equipment to the equipment branch management agents;
each equipment branch management intelligent agent is configured to receive data uploaded by the equipment intelligent agents and upload the data to an equipment main pipe intelligent agent;
and the equipment main pipe intelligent body is configured to receive the data uploaded by the equipment branch pipe intelligent body, so that the equipment state of the workshop is monitored in real time.
4. The plant autonomous scheduling system of claim 3,
the workpiece main pipe intelligent body can receive a production plan, read production information matched with the received production plan from the production information base and send the read production information to the equipment main pipe intelligent body;
the equipment main pipe intelligent body receives the production information sent by the workpiece main pipe intelligent body, reads the production equipment information from the equipment information base, and carries out feasibility judgment on the production plan according to the read production equipment information; wherein,
the production information stored in the production information base comprises production content information, production constraint information and optimization target information; the production equipment information stored in the equipment information base comprises basic information and production information of production equipment.
5. The system for autonomic scheduling of plants according to claim 4, further comprising:
the behavior record library is configured to receive data generated in the production process and sent by the workpiece management agent and the equipment management agent;
the decision support library is configured to store decision support information, and the decision support information comprises a scheduling strategy, evaluation information and an abnormal problem solution; and is
The decision support library can be updated according to the data stored in the behavior record library.
6. The plant autonomous scheduling system of claim 5,
when the equipment main pipe intelligent body judges that the production plan is feasible according to the read production equipment information, the equipment main pipe intelligent body sends the production equipment information corresponding to each equipment branch pipe body to the workpiece main pipe intelligent body, the workpiece main pipe intelligent body decomposes the production plan into various production tasks according to the production equipment information of each equipment branch pipe intelligent body, and transfers the production tasks to the workpiece branch pipe intelligent bodies corresponding to the equipment branch pipe intelligent bodies;
when the equipment main pipe intelligent body judges that the production plan is not feasible according to the read production equipment information, the equipment main pipe intelligent body feeds back the production plan infeasibility information to the workpiece main pipe intelligent body, and the workpiece main pipe intelligent body sends out a production plan infeasibility prompt.
7. The plant autonomous scheduling system of claim 6,
after receiving production task information, the workpiece branch management intelligent agent acquires corresponding production equipment information from the equipment branch management intelligent agent, and establishes a task model according to the production equipment information and the production task information;
and the workpiece sub-management intelligent agent reads a scheduling strategy from the decision support library according to the established task model and sends the task model and the scheduling strategy to the workpiece intelligent agent.
8. The plant autonomous scheduling system of claim 7,
the workpiece intelligent agent calculates an optimal scheduling scheme according to the received task model and the scheduling strategy and sends the optimal scheduling scheme to the workpiece branch management intelligent agent;
and the workpiece branch intelligent body sends the optimal scheduling scheme to the workpiece main pipe intelligent body, and the workpiece main pipe intelligent body redistributes the production tasks according to the received optimal scheduling scheme and judges the feasibility of the redistributed production tasks.
9. The plant autonomous scheduling system of claim 8,
when the workpiece main pipe intelligent body judges that the redistributed production task is feasible, the workpiece main pipe intelligent body sends a feasibility instruction to the workpiece branch pipe intelligent body, the workpiece branch pipe intelligent body sends the feasibility instruction to the workpiece intelligent body, the workpiece intelligent body receives the feasibility instruction and sends a task instruction to the logistics intelligent body, and the logistics intelligent body receives and executes the task instruction;
and when the workpiece main pipe intelligent body judges that the redistributed production task is not feasible, the workpiece main pipe intelligent body sends out a production plan infeasible prompt.
10. A scheduling method of the multi-agent based autonomous workshop scheduling system as claimed in claim 9, comprising the steps of:
step 10, receiving a production plan through a workpiece main pipe intelligent body and sending the production plan to an equipment main pipe intelligent body;
step 20, the equipment main pipe intelligent agent carries out feasibility judgment on the received production plan;
step 30, under the condition that the production plan is feasible, decomposing the production plan by the workpiece main pipe intelligent body, and transferring a production task to the workpiece branch pipe intelligent body;
step 40, the workpiece sub-management intelligent agent establishes a task model according to the received production task, reads a scheduling strategy from a decision support library according to the task model, and then sends the task model and the scheduling strategy to the workpiece intelligent agent;
step 50, the workpiece intelligent agent sends a task instruction to the logistics intelligent agent according to the received task model and the received scheduling strategy;
and step 60, executing the received instruction by the logistics intelligent agent.
11. The method of claim 10, wherein step 30 further comprises: step 301, under the condition that the production plan is not feasible, feeding back the production plan infeasible information to the workpiece main pipe intelligent agent by the equipment main pipe intelligent agent, and sending out a production plan infeasible prompt by the workpiece main pipe intelligent agent.
12. The method of claim 10, wherein step 40 further comprises:
step 401, after receiving production task information, the workpiece branch management agent obtains production equipment information from the equipment branch management agent, and establishes a task model according to the production equipment information and the production task information.
13. The method of claim 10, wherein step 50 further comprises:
step 501, the workpiece intelligent agent performs parallel calculation on the received task model and the scheduling strategy to obtain an optimal scheduling strategy, and sends the optimal scheduling strategy to the workpiece branch management intelligent agent;
step 502, the workpiece branch intelligent agent sends the optimal scheduling scheme to the workpiece main pipe intelligent agent, and the workpiece main pipe intelligent agent redistributes the production tasks according to the received optimal scheduling scheme and judges the feasibility of the redistributed production tasks;
step 503, in a case that the optimal scheduling policy is feasible, the workpiece main pipe agent sends a feasibility instruction to the workpiece branch pipe agent, the workpiece branch pipe agent sends the feasibility instruction to the workpiece agent, the workpiece agent receives the feasibility instruction and sends a task instruction to the logistics agent, and the logistics agent receives and executes the task instruction;
and step 504, under the condition that the optimal scheduling strategy is not feasible, the workpiece main pipe intelligent agent sends out a production plan infeasible prompt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611100675.9A CN106527373B (en) | 2016-12-05 | 2016-12-05 | Workshop Autonomous Scheduling system and method based on multiple agent |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611100675.9A CN106527373B (en) | 2016-12-05 | 2016-12-05 | Workshop Autonomous Scheduling system and method based on multiple agent |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106527373A true CN106527373A (en) | 2017-03-22 |
| CN106527373B CN106527373B (en) | 2019-02-01 |
Family
ID=58354799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611100675.9A Active CN106527373B (en) | 2016-12-05 | 2016-12-05 | Workshop Autonomous Scheduling system and method based on multiple agent |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106527373B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106873564A (en) * | 2017-04-26 | 2017-06-20 | 南京航空航天大学 | Flow-type multiple agent Real-time dispatch system and method based on intelligent workshop |
| CN107479428A (en) * | 2017-10-09 | 2017-12-15 | 上海德衡数据科技有限公司 | A kind of integrated data center operational system information processing method based on multiple agent |
| CN108181810A (en) * | 2017-12-15 | 2018-06-19 | 清华大学 | A kind of robust Single Machine Scheduling method based on bounded-but-unknown uncertainty |
| CN108469798A (en) * | 2018-05-15 | 2018-08-31 | 哈尔滨理工大学 | A kind of Job-Shop system based on line side library feeding |
| CN108549977A (en) * | 2018-03-29 | 2018-09-18 | 华南理工大学 | The flexible production dynamic scheduling system towards order based on multi-Agent |
| CN108764580A (en) * | 2018-05-28 | 2018-11-06 | 延安大学 | A kind of assembly shop scheduling system |
| CN109190995A (en) * | 2018-09-18 | 2019-01-11 | 北京航空航天大学 | A kind of two-way combined dispatching policy decision method of Maintenance Resource based on multiple agent |
| CN109213079A (en) * | 2017-06-29 | 2019-01-15 | 深圳模德宝科技有限公司 | A kind of control method and its device of automated production |
| CN109213080A (en) * | 2017-06-29 | 2019-01-15 | 深圳模德宝科技有限公司 | A kind of control method and its device of lathe |
| CN109255501A (en) * | 2018-10-29 | 2019-01-22 | 中国南方电网有限责任公司 | A kind of step library group's Long-term Optimal Dispatch algorithm based on multi-Agent artificial fish-swarm algorithm |
| WO2019037122A1 (en) * | 2017-08-25 | 2019-02-28 | 深圳市得道健康管理有限公司 | Artificial intelligence terminal and behavior control method therefor |
| CN109765862A (en) * | 2018-12-26 | 2019-05-17 | 同济大学 | The sustainable dispatch control method of hybrid flowshop based on self-adapted genetic algorithm |
| CN110764472A (en) * | 2019-09-25 | 2020-02-07 | 南京航空航天大学 | Workshop real-time scheduling method and device based on composite agent |
| CN111260181A (en) * | 2019-12-31 | 2020-06-09 | 同济大学 | Workshop self-adaptive production scheduling device based on distributed intelligent manufacturing unit |
| CN111650895A (en) * | 2020-04-08 | 2020-09-11 | 上海航天精密机械研究所 | Automatic line production task dynamic scheduling method |
| CN112434440A (en) * | 2020-12-02 | 2021-03-02 | 武汉工程大学 | Intelligent parking method and system based on multi-Agent self-adaptive online verification |
| CN113093673A (en) * | 2021-03-31 | 2021-07-09 | 南京大学 | Method for optimizing workshop operation schedule by using mean field action value learning |
| CN113568374A (en) * | 2020-09-14 | 2021-10-29 | 宁波舜宇智能科技有限公司 | Method, device, electronic device and storage medium for controlling production process of product |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001331462A (en) * | 2000-05-23 | 2001-11-30 | Yokogawa Electric Corp | Agent base production system |
| JP2003044548A (en) * | 2001-07-31 | 2003-02-14 | Amada Co Ltd | Outsourcing method and system for sheet-metal working |
| US7127310B1 (en) * | 2002-08-30 | 2006-10-24 | Advanced Micro Devices, Inc. | Method and apparatus for determining cost functions using parameterized components |
| JP2007334733A (en) * | 2006-06-16 | 2007-12-27 | Yokogawa Electric Corp | Working information management system |
| CN101706886A (en) * | 2009-08-28 | 2010-05-12 | 华南理工大学 | Order-driven Single-piece small-batch combined flow production method for processing workshop |
| CN102542411A (en) * | 2011-12-22 | 2012-07-04 | 浙江工业大学 | Method for carrying out dispatching control on multi-variety multi-process manufacturing enterprise workshop on basis of ACA (Automatic Circuit Analyzer) model |
| CN106155781A (en) * | 2015-04-08 | 2016-11-23 | 中国科学院软件研究所 | A kind of real-time task scheduling method in multiple agent platform |
-
2016
- 2016-12-05 CN CN201611100675.9A patent/CN106527373B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001331462A (en) * | 2000-05-23 | 2001-11-30 | Yokogawa Electric Corp | Agent base production system |
| JP2003044548A (en) * | 2001-07-31 | 2003-02-14 | Amada Co Ltd | Outsourcing method and system for sheet-metal working |
| US7127310B1 (en) * | 2002-08-30 | 2006-10-24 | Advanced Micro Devices, Inc. | Method and apparatus for determining cost functions using parameterized components |
| JP2007334733A (en) * | 2006-06-16 | 2007-12-27 | Yokogawa Electric Corp | Working information management system |
| CN101706886A (en) * | 2009-08-28 | 2010-05-12 | 华南理工大学 | Order-driven Single-piece small-batch combined flow production method for processing workshop |
| CN102542411A (en) * | 2011-12-22 | 2012-07-04 | 浙江工业大学 | Method for carrying out dispatching control on multi-variety multi-process manufacturing enterprise workshop on basis of ACA (Automatic Circuit Analyzer) model |
| CN106155781A (en) * | 2015-04-08 | 2016-11-23 | 中国科学院软件研究所 | A kind of real-time task scheduling method in multiple agent platform |
Non-Patent Citations (3)
| Title |
|---|
| 初红艳 等: "基于多Agent和CORBA的加工单元型制造车间调度系统", 《制造技术与机床》 * |
| 林慧苹 等: "基于分层调度模型的生产计划和调度集成研究", 《计算机集成制造系统-CIMS》 * |
| 高世一: "基于多智能体的制造系统生产控制建模研究", 《计算机集成制造系统》 * |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106873564B (en) * | 2017-04-26 | 2019-09-20 | 南京航空航天大学 | Flow-type multiple agent real-time scheduling method based on intelligent workshop |
| CN106873564A (en) * | 2017-04-26 | 2017-06-20 | 南京航空航天大学 | Flow-type multiple agent Real-time dispatch system and method based on intelligent workshop |
| CN109213079B (en) * | 2017-06-29 | 2020-10-23 | 深圳模德宝科技有限公司 | Control method and device for automatic production |
| CN109213079A (en) * | 2017-06-29 | 2019-01-15 | 深圳模德宝科技有限公司 | A kind of control method and its device of automated production |
| CN109213080A (en) * | 2017-06-29 | 2019-01-15 | 深圳模德宝科技有限公司 | A kind of control method and its device of lathe |
| CN109213080B (en) * | 2017-06-29 | 2020-10-23 | 深圳模德宝科技有限公司 | Machine tool control method and device |
| WO2019037122A1 (en) * | 2017-08-25 | 2019-02-28 | 深圳市得道健康管理有限公司 | Artificial intelligence terminal and behavior control method therefor |
| CN107479428A (en) * | 2017-10-09 | 2017-12-15 | 上海德衡数据科技有限公司 | A kind of integrated data center operational system information processing method based on multiple agent |
| CN108181810B (en) * | 2017-12-15 | 2020-05-12 | 清华大学 | Robust single machine scheduling method based on interval uncertainty |
| CN108181810A (en) * | 2017-12-15 | 2018-06-19 | 清华大学 | A kind of robust Single Machine Scheduling method based on bounded-but-unknown uncertainty |
| CN108549977A (en) * | 2018-03-29 | 2018-09-18 | 华南理工大学 | The flexible production dynamic scheduling system towards order based on multi-Agent |
| CN108549977B (en) * | 2018-03-29 | 2022-07-26 | 华南理工大学 | Multi-Agent-based order-oriented flexible production dynamic scheduling system |
| CN108469798A (en) * | 2018-05-15 | 2018-08-31 | 哈尔滨理工大学 | A kind of Job-Shop system based on line side library feeding |
| CN108764580A (en) * | 2018-05-28 | 2018-11-06 | 延安大学 | A kind of assembly shop scheduling system |
| CN109190995B (en) * | 2018-09-18 | 2021-06-08 | 北京航空航天大学 | Multi-agent-based maintenance resource bidirectional joint scheduling strategy decision method |
| CN109190995A (en) * | 2018-09-18 | 2019-01-11 | 北京航空航天大学 | A kind of two-way combined dispatching policy decision method of Maintenance Resource based on multiple agent |
| CN109255501A (en) * | 2018-10-29 | 2019-01-22 | 中国南方电网有限责任公司 | A kind of step library group's Long-term Optimal Dispatch algorithm based on multi-Agent artificial fish-swarm algorithm |
| CN109255501B (en) * | 2018-10-29 | 2021-09-24 | 中国南方电网有限责任公司 | Multi-Agent artificial fish swarm algorithm-based cascade library long-term optimization scheduling algorithm |
| CN109765862A (en) * | 2018-12-26 | 2019-05-17 | 同济大学 | The sustainable dispatch control method of hybrid flowshop based on self-adapted genetic algorithm |
| CN110764472A (en) * | 2019-09-25 | 2020-02-07 | 南京航空航天大学 | Workshop real-time scheduling method and device based on composite agent |
| WO2021056605A1 (en) * | 2019-09-25 | 2021-04-01 | 南京航空航天大学 | Workshop real-time scheduling method and apparatus based on composite intelligent agent |
| CN110764472B (en) * | 2019-09-25 | 2022-04-05 | 南京航空航天大学 | Workshop real-time scheduling method and device based on composite agent |
| CN111260181A (en) * | 2019-12-31 | 2020-06-09 | 同济大学 | Workshop self-adaptive production scheduling device based on distributed intelligent manufacturing unit |
| CN111650895A (en) * | 2020-04-08 | 2020-09-11 | 上海航天精密机械研究所 | Automatic line production task dynamic scheduling method |
| CN113568374A (en) * | 2020-09-14 | 2021-10-29 | 宁波舜宇智能科技有限公司 | Method, device, electronic device and storage medium for controlling production process of product |
| CN112434440A (en) * | 2020-12-02 | 2021-03-02 | 武汉工程大学 | Intelligent parking method and system based on multi-Agent self-adaptive online verification |
| CN113093673A (en) * | 2021-03-31 | 2021-07-09 | 南京大学 | Method for optimizing workshop operation schedule by using mean field action value learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106527373B (en) | 2019-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106527373B (en) | Workshop Autonomous Scheduling system and method based on multiple agent | |
| CN109917770B (en) | Intelligent management and control system for automatic production line of large structural part | |
| CN110058573B (en) | Huff and puff flexible intelligent assembly logistics path planning platform | |
| CN107036618A (en) | A kind of AGV paths planning methods based on shortest path depth optimization algorithm | |
| CN110084405B (en) | Throughput flexible intelligent assembly logistics path planning method | |
| CN105824300A (en) | Heavy type intelligent factory system based on IoT (Internet of Things) technology and digital management technology | |
| CN111680893A (en) | Digital twin system of multi-self-addressing robot picking system and scheduling method | |
| CN111915410A (en) | Intelligent management and control system for high-dynamic production logistics process | |
| Jha | Handbook of flexible manufacturing systems | |
| CN103197614B (en) | The automatic material conveyer controlled based on PLC and control method thereof | |
| CN116777187B (en) | Multi-path inspection intelligent central control scheduling method and platform | |
| CN114418177B (en) | New product material distribution prediction method based on digital twin workshops for generating countermeasure network | |
| Lin et al. | Integrated cyber physical simulation modelling environment for manufacturing 4.0 | |
| CN112462702A (en) | Intelligent monitoring and intelligent scheduling system based on industrial internet | |
| CN110516939A (en) | Warehouse homework dispatches system | |
| CN111913483A (en) | Dispatching system and method for four-way shuttle | |
| CN110232504A (en) | A kind of quality manufacturing execution system platform and terminal | |
| Tian et al. | Real-time shop floor scheduling method based on virtual queue adaptive control: Algorithm and experimental results | |
| CN116224926A (en) | Dynamic scheduling optimization method and device for single-piece small-batch flexible manufacturing workshops | |
| CN115587295A (en) | Intelligent generation method and system of supply chain strategy based on machine self-learning | |
| Park et al. | A cognitive agent based manufacturing system adapting to disturbances | |
| Majdzik | A feasible schedule for parallel assembly tasks in flexible manufacturing systems | |
| CN114037341B (en) | DDQN-based intelligent workshop dynamic self-adaptive scheduling method and system | |
| CN115796326A (en) | Intelligent workshop production scheduling system and method | |
| CN115409392A (en) | Method and device for determining material production plan, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |