CN115409397A - Intelligent scheduling method based on improved BAS algorithm - Google Patents
Intelligent scheduling method based on improved BAS algorithm Download PDFInfo
- Publication number
- CN115409397A CN115409397A CN202211084703.8A CN202211084703A CN115409397A CN 115409397 A CN115409397 A CN 115409397A CN 202211084703 A CN202211084703 A CN 202211084703A CN 115409397 A CN115409397 A CN 115409397A
- Authority
- CN
- China
- Prior art keywords
- production
- order
- production line
- information
- data
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004519 manufacturing process Methods 0.000 claims abstract description 96
- 238000009826 distribution Methods 0.000 claims abstract description 22
- 241001481710 Cerambycidae Species 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 15
- 241000254173 Coleoptera Species 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 claims description 3
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000003278 mimic effect Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- YZCKVEUIGOORGS-IGMARMGPSA-N Protium Chemical compound [1H] YZCKVEUIGOORGS-IGMARMGPSA-N 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012549 training 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- 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
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Manufacturing & Machinery (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Algebra (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Optimization (AREA)
- Quality & Reliability (AREA)
- Robotics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
Abstract
The invention discloses an intelligent scheduling method based on an improved BAS algorithm, which comprises the following steps: (1) acquiring order information and equipment information; and (2) marking the order information and the equipment information: marking the order according to the degree of urgency; classifying the equipment according to orders of different emergency degrees; (3) And respectively distributing the orders to production equipment according to a BAS algorithm, evaluating each distribution scheme and iterating to obtain an optimal scheduling distribution mode. The invention can accurately and quickly finish the optimal scheduling distribution for the production of the intelligent factory.
Description
Technical Field
The invention relates to the field of control and scheduling of intelligent factories, in particular to an intelligent scheduling method based on an improved BAS algorithm.
Background
Smart manufacturing has become an increasingly hot spot of social concern. The industrial manufacturing field is developing towards digitalization, intellectualization and diversification, and the intelligent manufacturing technology has become one of the fields with high attention in the industry. In this context, smart factories are effectively supporting the implementation of smart manufacturing.
Different from the traditional mechanized factory, the intelligent factory further enlarges the production scale due to the deepening of the digitization degree, and the data volume in the production process is also larger, so the scheduling difficulty is further improved, and how to efficiently and accurately schedule the production line of the intelligent factory is a very critical problem. The scheduling problem and the related knowledge thereof comprise the related problems of how to reasonably plan the processing sequence of the product, how to more efficiently process the production data, how to more effectively combine the links of inventory, production, transportation and the like, and the problems are very important problems in the management and production of modern factories. At present, scholars at home and abroad schedule intelligent factories mainly focus on realizing task allocation of the factories by utilizing data sets and past experiences, and intelligent algorithms such as a convolutional neural network, a multi-Agent and an Agent are used. Although the method has good effect on the scheduling problem of the intelligent factory, a large amount of historical data is required for training to ensure the accuracy of the model, and once the range of the data set is exceeded, the scheduling is inaccurate to a certain extent.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an intelligent scheduling method based on an improved BAS algorithm, which can accurately and quickly finish the optimal scheduling allocation for the production of an intelligent factory.
In order to achieve the purpose, the invention adopts the technical scheme that: an intelligent scheduling method based on an improved BAS algorithm comprises the following steps:
(1) Acquiring order information and equipment information;
(2) Marking order information and equipment information: marking the order according to the degree of urgency; classifying the equipment according to the orders of different emergency degrees;
(3) And respectively distributing the orders to production equipment according to a BAS algorithm, evaluating each distribution scheme and iterating to obtain an optimal scheduling distribution mode.
The step (1) comprises the following steps: acquiring order information of a customer by using an MES system; and receiving the equipment state information and the environment information by using the PLC data acquisition station.
The step (1) also comprises the steps of preprocessing the order information and the equipment information and eliminating abnormal data.
The step (2) comprises the following steps:
classifying and recording the order information as B1, B2 and B3, 8230according to the order emergency degree;
classifying the production line equipment information into A1, A2 and A3 \8230;
each type of production line equipment corresponds to the producible order urgency degree; and the higher the production urgency, the higher the production line cost expense and the shorter the time corresponding to the order.
The BAS algorithm is used for carrying out scheduling distribution processing on the orders for improving the BAS algorithm for updating the antenna distance and the step length.
The improved BAS algorithm comprises the steps of:
step a: when the longicorn is at any position, the orientation of the head is random, and the vector normalization formula of the longicorn orientation is as follows:
in the formula, rand (D, 1) represents a randomly generated scheduling instruction function, and D is the dimension of a space;
step b: after obtaining the direction vector, the positions of the left and right antennae of the beetle are defined as follows:
in the formula, the quantity of orders with different urgency degrees is taken as the position x of the left and right antennae of the initial beetle l And x r (ii) a Taking the quantity of orders of each grade at m time as a centroid position x m The difference of the orders quantity of each grade of the left antenna and the right antenna at the time m is taken as the distance d between the two antennas m 。
Step c: the method is characterized in that a fitness function is constructed by taking the utilization efficiency and the yield of a production line as targets, and the concrete form is as follows:
wherein M represents the number of production lines, T represents the total time for producing the processed devices, C represents the total income from production, and C represents the total income from production cost For the total cost, λ 1 ,λ 2 Respectively weighting the utilization efficiency and the yield of the production line in an objective function; n is a radical of 1 ,N 2 ,N 3 Respectively represent the degree of production emergency as B 1 ,B 2 ,B 3 The number of hourly production tasks; o is 1 ,O 2 ,O 3 Respectively represent the production emergency degree of B 1 ,B 2 ,B 3 The number of production task processes, s, n, o, represents the serial number corresponding to the production line, production task and process, x i (i =1,2,3) represents the execution time of the o-th process of the task n on the production line s with the order urgency of i; t is i (i =1,2,3) indicates the order urgency of i, the latest end time of all processes, i.e., maximum completionTime; c 1 ,C 2 ,C 3 Respectively representing the costs of the production machines of different production lines, the lower the number the higher the cost, C 4 For other comprehensive costs. The larger J (x) at this time means the higher the utilization efficiency and profitability of the production line of the intelligent factory.
Step d: calculating the odor concentration J (x) of tentacles on two sides of the longicorn according to the fitness function J (x) l ) And J (x) r ) Namely the grade degree of a production line, the adaptability of the left antenna and the right antenna of the longicorn is compared, and the position of the next step of movement is determined. To mimic the longicorn detection mechanism, the following location update iterative model is generated:
in the formula, sign is a sign function, and the newly increased order quantity of each grade at m time is taken as a search step delta m 。
Step e: in practical applications, the distance difference d between two whiskers m And step size delta of longicorn m The update rule is as follows:
d m =d e ·d m-1
δ m =δ e ·δ m-1
in the formula (d) e The attenuation coefficient of the distance between the two antennae is defined as the difference of the order number of each grade of the antennae at the time m-1 as the distance d between the two antennae at the previous time m-1 ,δ e The new order quantity of each grade at the m-1 moment is taken as the search step delta at the previous moment as the attenuation coefficient of the step m-1 。
Step f: in order to solve the problem that the BAS algorithm can only update one antenna distance and step length every iteration and easily cause the system to be locally optimal, improvement is carried out on the basis of the step e, according to the existing attenuation coefficient, the order quantity difference of each grade of about 10 groups of antennas and the order quantity newly added in each grade, namely 10 groups of antenna distance and step length data are generated every time, the optimal antenna distance and step length are obtained through weighting calculation of a data set, and the data are used as the optimal antenna distance and step length value of the current position.
Step g: and (c) updating the antenna distance and the step length, judging whether the optimal or the maximum iteration times is reached, if so, returning the optimal distribution quantity, namely the data for producing each emergency degree order corresponding to each type of production line equipment after the iteration is finished, and otherwise, returning to the step b.
And transmitting the order information to a client order workstation, receiving the equipment state information and the environmental information by utilizing the PLC data acquisition stations, and uploading the data to a data layer by each PLC data acquisition station and the client order workstation.
And (3) the data processing center acquires the order classification and the production line equipment information from the data layer and executes the step (3) to output the quantity of each emergency order distributed and produced by each type of production line equipment.
The production scheduling distribution result output by the data processing center is sent to the production line control system, the production line control system receives the transmitted distribution command, starts scheduling production according to the requirement and transmits the related production condition to the display layer; the console of the display layer displays the relevant information of the perception layer, the data layer and the scheduling layer in the form of a monitoring platform, and provides corresponding interfaces for manual intervention.
The invention has the advantages that: 1. repeated or wrong order information is removed based on the pre-analysis of the data of the sensing layer, so that the processing efficiency of the data layer on the data of the sensing layer is improved;
2. the number of the optimal production line distribution tasks is searched through the BAS algorithm, the target optimization is simply and quickly realized, and the problem that the distribution result seriously depends on historical data due to the fact that other intelligent algorithms use a large amount of data to train the model is avoided;
3. aiming at the problem that whether the current data is the optimal antenna distance and the step length cannot be determined because the attenuation coefficient of a celestial cow is fixed when the antenna distance and the step length are updated and only one group of data can be generated at one time, the invention provides an optimization algorithm for improving the antenna distance and the step length of the celestial cow.
Drawings
The contents of the expressions in the various figures of the present specification and the labels in the figures are briefly described as follows:
FIG. 1 is an overall framework diagram of an intelligent plant scheduling system
FIG. 2 is a flow chart of an improved longicorn whisker algorithm
Detailed Description
The following description of preferred embodiments of the present invention will be made in further detail with reference to the accompanying drawings.
Aiming at the technical problems in the production scheduling process of an intelligent factory, the invention provides a scheduling method based on an improved BAS algorithm, and the invention is further explained by combining the attached drawings and the embodiment
As shown in fig. 1, an intelligent factory scheduling method mainly includes the following steps:
step 1: the running state and the environmental state of the equipment are obtained through an intelligent sensor arranged on the bottom layer mechanical equipment, and the order information of a customer is obtained through an MES system;
step 2: receiving the equipment state information and the environment information by using a PLC data acquisition station, and sending order information to a customer order workstation;
and step 3: each PLC data acquisition station and each customer order workstation remove abnormal data through data preprocessing, and the rest data are sent to a data layer;
and 4, step 4: marking the customer order information as B through a clustering algorithm 1 ,B 2 ,B 3 Wherein a smaller number indicates a more urgent customer order; record production line equipment information as A 1 ,A 2 ,A 3 Wherein a smaller number indicates a higher production line grade, a higher cost for producing a piece of equipment, and a shorter time define A 1 Can complete B 1 ,B 2 ,B 3 In any task, A 2 Can accomplish B 2 ,B 3 In any task, A 3 Can only accomplish B 3 The task in (1) counts the number of each state and uploads the number to a data processing center of a scheduling layer;
and 5: the scheduling layer firstly calls an improved BAS algorithm, the distribution process of the intelligent factory order is simulated by continuously searching the food position in the three-dimensional space through the longicorn, and the iteration result is sent to the corresponding production line;
step 6: the production lines of the three levels receive the distribution command transmitted by the upper intelligent controller, start to schedule production according to requirements and transmit related production conditions to the display layer;
and 7: the control console of the display layer displays relevant information of the sensing layer, the data layer and the scheduling layer in a monitoring platform mode, so that relevant personnel can timely and accurately obtain factory information conveniently, corresponding interfaces are provided for manual intervention, and man-machine friendly interactive application and experience are achieved.
As shown in fig. 2, the improved BAS algorithm used in step 5 specifically includes the following steps:
step a: when the longicorn is at any position, the orientation of the head is random, and the vector normalization formula of the longicorn orientation is as follows:
in the formula, rand (D, 1) represents a randomly generated scheduling instruction function, and D is a dimension of space.
Step b: after the direction vector is obtained, defining the left and right antennae of the beetle to obtain the following orders of different grades:
in the formula, the quantity of orders with different urgency degrees is taken as the position x of the left and right antennae of the initial beetle l And x r (ii) a Taking the number of orders of each grade at m time as the centroid position x m The difference of the orders quantity of each grade of the left antenna and the right antenna at the time m is taken as the distance d between the two antennas m 。
Step c: the method is characterized in that a fitness function is constructed by taking the utilization efficiency and the yield of a production line as targets, and the concrete form is as follows:
wherein M represents the number of production lines, T represents the total time for producing the processed devices, C represents the total income from production, and C represents the total income from production cost λ being the total cost 1 ,λ 2 Respectively weighting the utilization efficiency and the yield of the production line in an objective function; n is a radical of hydrogen 1 ,N 2 ,N 3 Respectively represent the production emergency degree of B 1 ,B 2 ,B 3 The number of hourly production tasks; o is 1 ,O 2 ,O 3 Respectively represent the production emergency degree of B 1 ,B 2 ,B 3 The number of production task processes, s, n, o, represents the serial numbers corresponding to the production line, production task and process, x i (i =1,2,3) represents the execution time of the o-th process of the task n on the production line s with the order urgency of i; t is i (i =1,2,3) indicates an order urgency of i, the latest end time of all processes, i.e., the maximum completion time; c 1 ,C 2 ,C 3 Respectively representing the costs of the production machines of different production lines, the lower the number the higher the cost, C 4 For other comprehensive costs. The larger J (x) at this time is, the higher the utilization efficiency and profitability of the production line of the intelligent factory become.
Step d: calculating the odor concentration J (x) of tentacles on two sides of the longicorn according to the fitness function J (x) l ) And J (x) r ) Namely the grade degree of a production line, the adaptability of the left antenna and the right antenna of the longicorn is compared, and the position of the next step of movement is determined. To mimic the longicorn detection mechanism, the following location update iterative model is generated:
in the formula, sign is a sign function, and the number of newly-increased orders in each grade at m time is used as a search step delta m 。
Step e: in practical applications, the distance difference d between two whiskers m And step size delta of longicorn m The update rule is as follows:
d m =d e ·d m-1
δ m =δ e ·δ m-1
in the formula, d e The attenuation coefficient of the distance between the two antennae is defined as the difference of the order number of each grade of the antennae at the time m-1 as the distance d between the two antennae at the previous time m-1 ,δ e The new order quantity of each grade at the m-1 moment is taken as the search step delta at the previous moment as the attenuation coefficient of the step m-1 。
Step f: in order to solve the problem that the BAS algorithm can only update one antenna distance and step length every iteration and easily cause the system to be locally optimal, improvement is carried out on the basis of the step e, according to the existing attenuation coefficient, the order quantity difference of each grade of about 10 groups of antennas and the order quantity newly added in each grade, namely 10 groups of antenna distance and step length data are generated every time, the optimal antenna distance and step length are obtained through weighting calculation of a data set, and the data are used as the optimal antenna distance and step length value of the current position.
Step g: and (c) updating the antenna distance and the step length, judging whether the optimal number or the maximum iteration number is reached, if so, ending the iteration and returning to the optimal distribution number, otherwise, returning to the step b.
The intelligent factory dispatching system can effectively improve the efficiency and the accuracy of factory logistics dispatching, and is simple and easy to realize. The method has the following advantages:
1. repeated or wrong order information is removed based on the pre-analysis of the data of the sensing layer, so that the processing efficiency of the data layer on the data of the sensing layer is improved;
2. the number of the optimal production line distribution tasks is searched through the BAS algorithm, the target optimization is simply and quickly realized, and the problem that the distribution result seriously depends on historical data due to the fact that other intelligent algorithms use a large amount of data to train the model is solved;
3. aiming at the problem that whether the current data is the optimal antenna distance and the step length cannot be determined because the attenuation coefficient of a celestial cow is fixed when the antenna distance and the step length are updated and only one group of data can be generated at one time, the invention provides an optimization algorithm for improving the antenna distance and the step length of the celestial cow.
It is clear that the specific implementation of the invention is not restricted to the above-described modes, and that various insubstantial modifications of the inventive concept and solution are within the scope of protection of the invention.
Claims (9)
1. An intelligent scheduling method based on an improved BAS algorithm is characterized in that: the method comprises the following steps:
(1) Acquiring order information and equipment information;
(2) Marking order information and equipment information: marking the order according to the emergency degree; classifying the equipment according to the orders of different emergency degrees;
(3) And respectively distributing the orders to production equipment according to a BAS algorithm, evaluating each distribution scheme and iterating to obtain an optimal scheduling distribution mode.
2. The intelligent scheduling method based on the improved BAS algorithm as claimed in claim 1, wherein: the step (1) comprises the following steps: acquiring order information of a customer by using an MES system; and receiving the equipment state information and the environmental information by using a PLC data acquisition station.
3. The intelligent scheduling method based on the improved BAS algorithm as claimed in claim 2, wherein: the step (1) further comprises preprocessing the order information and the equipment information and eliminating abnormal data.
4. The intelligent scheduling method based on the improved BAS algorithm as claimed in claim 1, wherein: the step (2) comprises the following steps:
classifying the order information into B1, B2 and B3, 8230according to the order emergency degree;
classifying the production line equipment information into A1, A2 and A3 \8230;
each type of production line equipment corresponds to the producible order urgency degree; and the higher the production urgency, the higher the production cost expense and the shorter the time corresponding to the order.
5. The intelligent scheduling method based on the improved BAS algorithm as claimed in claim 4, wherein: the BAS algorithm is used for carrying out scheduling distribution processing on the orders for improving the BAS algorithm for updating the antenna distance and the step length.
6. The intelligent scheduling method based on the improved BAS algorithm as claimed in claim 5, wherein: the improved BAS algorithm comprises the steps of:
step a: when the longicorn is at any position, the orientation of the head is random, and the vector normalization formula of the longicorn orientation is as follows:
in the formula, rand (D, 1) represents a randomly generated scheduling instruction function, and D is the dimension of a space;
step b: after obtaining the direction vector, the positions of the left and right antennae of the beetle are defined as follows:
in the formula, the quantity of orders with different urgency degrees is taken as the position x of the left and right antennae of the initial beetle l And x r (ii) a Taking the number of orders of each grade at m time as the centroid position x m The difference of the orders quantity of each grade of the left antenna and the right antenna at the time m is taken as the distance d between the two antennas m ;
Step c: the method is characterized in that a fitness function is constructed by taking the utilization efficiency and the yield of a production line as targets, and the concrete form is as follows:
wherein M represents the number of production lines, T represents the total time for producing the processed devices, C represents the total income of production, and C represents the total income of production cost For the total cost, λ 1 ,λ 2 Respectively weighting the utilization efficiency and the yield of the production line in an objective function; n is a radical of 1 ,N 2 ,N 3 Respectively represent the production emergency degree of B 1 ,B 2 ,B 3 The number of hourly production tasks; o is 1 ,O 2 ,O 3 Respectively represent the production emergency degree of B 1 ,B 2 ,B 3 The number of production task processes, s, n, o, represents the serial numbers corresponding to the production line, production task and process, x i (i =1,2, 3) represents the execution time of the o-th process of the task n on the production line s, with the order urgency level i; t is a unit of i (i =1,2,3) indicates an order urgency of i, the latest end time of all processes, i.e., the maximum completion time; c 1 ,C 2 ,C 3 Respectively representing the costs of the production machines of different production lines, the lower the number the higher the cost, C 4 For other comprehensive costs. The larger J (x) at this time means the higher the utilization efficiency and profitability of the production line of the intelligent factory.
Step d: calculating the odor concentration J (x) of tentacles on two sides of the longicorn according to the fitness function J (x) l ) And J (x) r ) Namely the grade degree of a production line, the adaptability of the left antenna and the right antenna of the longicorn is compared, and the position of the next step of movement is determined. To mimic the longicorn detection mechanism, the following location update iterative model is generated:
in the formula, sign is a sign function, and the number of newly-increased orders in each grade at m time is used as a search step delta m 。
Step e: in practical applications, the distance difference d between two whiskers m And step size delta of longicorn m The update rule is as follows:
d m =d e ·d m-1
δ m =δ e ·δ m-1
in the formula (d) e The attenuation coefficient of the distance between the two antennae is defined as the difference of the order number of each grade of the antennae at the time m-1 as the distance d between the two antennae at the previous time m-1 ,δ e The new order quantity of each grade at the m-1 moment is taken as the search step delta at the previous moment as the attenuation coefficient of the step m-1 ;
Step f: in order to solve the problem that the BAS algorithm can only update one antenna distance and step length in each iteration and easily cause the system to be in local optimum, the improvement is carried out on the basis of the step e, according to the existing attenuation coefficient, the order number difference of each grade of 10 groups of left and right antennas and the order number newly added in each grade are generated each time, namely 10 groups of antenna distance and step length data are obtained, the optimal antenna distance and step length are obtained through the weighted calculation of a data set, and the data are used as the optimal antenna distance and step length value of the current position;
step g: and (c) updating the antenna distance and the step length, judging whether the optimal or the maximum iteration times is reached, if so, returning the optimal distribution quantity, namely the data for producing each emergency degree order corresponding to each type of production line equipment after the iteration is finished, and otherwise, returning to the step b.
7. The intelligent scheduling method based on the improved BAS algorithm as claimed in claim 6, wherein: and sending the order information to a client order workstation, receiving the equipment state information and the environment information by utilizing the PLC data acquisition stations, and uploading the data to a data layer by each PLC data acquisition station and the client order workstation.
8. The intelligent scheduling method based on the improved BAS algorithm as claimed in claim 7, wherein: and (4) the data processing center acquires the order classification and the production line equipment information from the data layer and executes the step (3) to output the quantity of each emergency order distributed and produced by each type of production line equipment.
9. The intelligent scheduling method based on the improved BAS algorithm as claimed in claim 8, wherein: the production scheduling distribution result output by the data processing center is sent to the production line control system, the production line control system receives the transmitted distribution command, starts scheduling production according to the requirement and transmits the related production condition to the display layer; the console of the display layer displays the relevant information of the perception layer, the data layer and the scheduling layer in the form of a monitoring platform, and provides corresponding interfaces for manual intervention.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211084703.8A CN115409397A (en) | 2022-09-06 | 2022-09-06 | Intelligent scheduling method based on improved BAS algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211084703.8A CN115409397A (en) | 2022-09-06 | 2022-09-06 | Intelligent scheduling method based on improved BAS algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115409397A true CN115409397A (en) | 2022-11-29 |
Family
ID=84163262
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211084703.8A Pending CN115409397A (en) | 2022-09-06 | 2022-09-06 | Intelligent scheduling method based on improved BAS algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115409397A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116105743A (en) * | 2023-04-17 | 2023-05-12 | 山东大学 | Information factor distribution method of federal filtering system and underwater navigation system |
-
2022
- 2022-09-06 CN CN202211084703.8A patent/CN115409397A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116105743A (en) * | 2023-04-17 | 2023-05-12 | 山东大学 | Information factor distribution method of federal filtering system and underwater navigation system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106527373B (en) | Workshop Autonomous Scheduling system and method based on multiple agent | |
CN111915410B (en) | Intelligent management and control system for high-dynamic production logistics process | |
CN107944765B (en) | Evaluation system and evaluation method for intelligent manufacturing production scheduling cooperative management and control capability | |
CN113985879B (en) | Intelligent mobile inspection method based on historical data dynamic optimization | |
Deng et al. | Metaverse-driven remote management solution for scene-based energy storage power stations | |
CN115933684A (en) | AGV-based intelligent dynamic dispatching logistics system for digital twin workshop | |
CN111311133B (en) | Monitoring system applied to power grid production equipment | |
CN117709617A (en) | MES-based intelligent scheduling system for production workshop | |
CN114418177B (en) | New product material distribution prediction method based on digital twin workshops for generating countermeasure network | |
CN116822380B (en) | Collaborative optimization method for tail gas recycling in copper smelting process based on digital twin | |
CN110501978A (en) | A kind of robot product workshop scheduled production dispatching method | |
CN115409397A (en) | Intelligent scheduling method based on improved BAS algorithm | |
CN111882363A (en) | Sales prediction method, system and terminal | |
CN113189942A (en) | Intelligent industrial data analysis system and method | |
CN113591295A (en) | Power cable management method based on digital twinning | |
CN117234214A (en) | Automatic shuttle for stacking industrial goods | |
Leon et al. | A Hybrid Simulation and Reinforcement Learning Algorithm for Enhancing Efficiency in Warehouse Operations | |
Rodriguez-Fernandez et al. | Modelling behaviour in UAV operations using higher order double chain Markov models | |
CN115617089A (en) | Temperature control method, device, equipment and medium based on sensor state change | |
CN108665094A (en) | A kind of copper plate/strip founding-tandem rolling Optimization Scheduling of data-driven | |
CN116341931B (en) | Multi-preference steel enterprise operation data analysis system and method | |
De Kuyffer et al. | Offshore windmill and substation maintenance planning with distance, fuel consumption and tardiness optimisation | |
CN117494472A (en) | Discrete process optimization method and device based on simulation verification | |
CN114723220B (en) | Digital twin flexible workshop real-time scheduling method based on variable time window | |
CN115409392A (en) | Method and device for determining material production plan, storage medium and electronic equipment |
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 |