CN115049324A - Wharf AGV (automatic guided vehicle) scheduling method and device, computer equipment and storage medium - Google Patents
Wharf AGV (automatic guided vehicle) scheduling method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115049324A CN115049324A CN202210983715.8A CN202210983715A CN115049324A CN 115049324 A CN115049324 A CN 115049324A CN 202210983715 A CN202210983715 A CN 202210983715A CN 115049324 A CN115049324 A CN 115049324A
- Authority
- CN
- China
- Prior art keywords
- agv
- dispatching
- time
- data
- historical
- 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
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
- G06Q10/06313—Resource planning in a project environment
-
- 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
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a dispatching method and a dispatching device for wharf AGV vehicles, computer equipment and a storage medium, belonging to the field of data processing, wherein the method comprises the steps of acquiring historical operation data of historical AGV vehicles of container wharfs of all operation paths; analyzing and training the historical operation data to obtain a model; acquiring current operation data at a preset frequency; inputting the current operation data into an AGV evaluation time model corresponding to each operation path to obtain the predicted residual time proportion of each operation path; based on the remaining time proportion, resetting the dispatching numerical values of all AGV vehicles in the current operation data according to the AGV vehicle state information judgment model and the operation path AGV vehicle dispatching model to obtain an AGV vehicle dispatching adjustment value; and adjusting and limiting the AGV dispatching adjustment value according to the dispatching limitation rule to obtain the AGV dispatching update values of all the operation paths. Through the processing scheme disclosed by the invention, the code AGV is dynamically and reasonably distributed.
Description
Technical Field
The invention relates to the field of data processing, in particular to a wharf AGV dispatching method and device, computer equipment and a storage medium.
Background
In the field of automatic container terminals, an agv (automatic Guided vehicle) automatically guides a trolley to take charge of container transportation between a ship loading area and a storage yard area, and plays a key role in realizing terminal automation. In the wharf operation, the efficiency of the bridge crane operation is directly related to the AGV matching quantity, the wharf operation efficiency can be effectively improved by reasonably distributing the AGV quantity of each bridge crane, the empty driving rate and the waiting time of the AGV are reduced, and the abutment time rate of the bridge crane is improved. How to reasonably distribute and schedule the AGV vehicles is one of the difficulties in the operation of the automatic container terminal.
Disclosure of Invention
Therefore, in order to overcome the defects of the prior art, the invention provides a wharf AGV dispatching method, a wharf AGV dispatching device, a computer device and a storage medium for dynamically and reasonably allocating the wharf AGV.
In order to achieve the purpose, the invention provides a wharf AGV dispatching method, which comprises the following steps: acquiring historical operation data of historical AGV vehicles of container terminals of all operation paths, wherein the historical operation data comprises historical dispatching data of the AGV vehicles and historical working data of the AGV vehicles on the operation paths in a historical time period; analyzing the historical operation data, and respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path; acquiring historical operation data in a preset time period before the current time point of the operation path, an operation plan of the operation path of the ship at the port and the planned berthing time of the ship, wherein the operation plan is operated at the current time point, and the current operation data are acquired; inputting the current operation data into an AGV evaluation time model corresponding to each operation path to obtain the predicted residual time proportion of each operation path; based on the remaining time proportion, resetting the dispatching values of all the AGV vehicles in the current operation data according to the AGV vehicle state information judgment model and the operation path AGV vehicle dispatching model to obtain an AGV vehicle dispatching adjustment value; and adjusting and limiting the AGV dispatching adjustment value according to a dispatching limitation rule to obtain the AGV dispatching update values of all the operation ways.
In one embodiment, the analyzing the historical operation data and respectively training an AGV state information determination model, an AGV scheduling model and an AGV evaluation time model corresponding to each operation path includes: sampling the historical operation data, and extracting the scheduling number of the AGV vehicles, the working state labels of the AGV vehicles and the operation time of the AGV vehicles on the operation road in a historical time period; determining the operation characteristics of each operation path according to the scheduling number of the AGV cars, the working state labels of the AGV cars and the operation time of the AGV cars; and respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path according to the operation characteristics.
In one embodiment, the inputting the current operation data into an AGV estimation time model corresponding to each operation path to obtain a predicted remaining time ratio of each operation path includes: obtaining the number N of total operation paths from the current operation data STS Total number N of AGV vehicles on all current operation roads AGV Planned debarking time t of ship left Current time t now (ii) a According to planned departure time t of ship left Current time t now Calculating to obtain the residual operation time t of each operation path work =t left -t now (ii) a The number N of the total operation paths in the current operation data STS Total number N of AGV cars AGV Inputting an AGV evaluation time model to obtain the predicted operation time y of the operation path t Calculating a predicted remaining time ratio of each operation route,α i Is shown asiThe remaining time proportion of the working path.
In one embodiment, the resetting the scheduling values of all the AGVs in the current job data according to the AGV state information determination model and the job path AGV scheduling model based on the remaining time ratio to obtain an AGV scheduling adjustment value includes: proportional to the remaining timeα i And a predetermined threshold valueαCarrying out comparison and judgment; when in useα i Is greater thanαThen, the current operation data is input into the operation path AGV dispatching model to obtain a first dispatching estimated value y of the AGV w (ii) a And inputting the current operation data into the AGV state information judgment model to determine whether the AGV is in a gear failure or the AGV is in an excessive redundant scheduling value y c (ii) a According to the first scheduling estimated value y of the AGV w And a redundancy scheduling value y c Obtaining the dispatching adjustment value y of the AGV p =y w -y c (ii) a When in useα i Is less thanαWhen the AGV is in the process of the Automatic Guided Vehicle (AGV), the dispatching adjustment value is,N STS Is the number of total operation paths, N AGV Total number of AGV cars for the current operation roadiThe order of the operation paths is r i And sigma is the standard deviation of the AGV dispatching quantity of the operation path in the historical data.
In one embodiment, the scheduling restriction rule includes: each of the working pathsiSetting the minimum dispatching quantity N of AGV vehicles min And a maximum scheduling number N max ,N i At N min And N max To (c) to (d); counting total N of AGV operation quantity of all operation paths used =∑ Shipping operation road i N i ×β 1 +∑ Ship unloading operation road i N i ×β 2 ,β 1 To calculate the ratio of the loading operation time to the scheduling time of the AGV,β 2 the ratio of the average dispatching time for AGV ship unloading; n is a radical of used ≤N AGV , N AGV Indicating the total number of AGV vehicles on all the current working paths.
In one embodiment, when N used >N AGV In time, calculate that each job path should reduce the actual AGV job count to(ii) a For the working path of shipmentiAdjusting the AGV dispatching quantity to(ii) a For the working path of ship unloadingiAdjust the AGV dispatching quantity to。
A dock AGV car scheduling apparatus, the apparatus comprising: the historical data acquisition module is used for acquiring historical operation data of historical AGV vehicles of the container terminal of all operation paths, and the historical operation data comprises historical dispatching data of the AGV vehicles and historical working data of the AGV vehicles on the operation paths in a historical time period; the model training module is used for analyzing the historical operation data and respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path; the current data acquisition module is used for acquiring historical operation data in a preset time period before the current time point of the operation path, an operation plan of the operation path of the ship at the port and the planned debarking time of the ship, which are operated at the current time point, by using a preset frequency to obtain the current operation data; the residual time proportion acquisition module is used for inputting the current operation data into an AGV evaluation time model corresponding to each operation path to obtain the predicted residual time proportion of each operation path; the scheduling adjustment value generation module is used for resetting the scheduling values of all the AGV vehicles in the current operation data according to the AGV vehicle state information judgment model and the operation path AGV vehicle scheduling model based on the residual time proportion to obtain an AGV vehicle scheduling adjustment value; and the scheduling update value generation module is used for adjusting and limiting the AGV scheduling adjustment value according to the scheduling limitation rule to obtain the AGV scheduling update values of all the operation ways.
A computer arrangement comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the above method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method as described above.
Compared with the prior art, the invention has the advantages that: the method comprises the steps of generating a scheduling model according to historical operation data, adjusting a theoretical value obtained by the scheduling model according to current operation data, and simultaneously using the historical operation data and the current operation data which are loaded and unloaded at present as independent variables to participate in a training process of the model, so that the obtained AGV scheduling updating value is more accurate and can be more attached to the current operation, the condition of executing the operation can be better reflected, and reasonable distribution of the AGV of each bridge crane can be realized. In addition, the current operation data is dynamically acquired in real time, so that the finally obtained AGV dispatching update value is more accurate.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for dispatching a dock AGV according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram illustrating the model training steps in one embodiment;
FIG. 3 is a block diagram of an embodiment of a quay AGV dispatching device;
FIG. 4 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure in the specification. It is to be understood that the described embodiments are merely illustrative of some, and not restrictive, of the embodiments of the disclosure. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It should be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without inventive step, are intended to be within the scope of the present disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the appended claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the disclosure, one skilled in the art should appreciate that one aspect described herein may be implemented independently of any other aspects and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. Additionally, such an apparatus may be implemented and/or such a method may be practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present disclosure, and the drawings only show the components related to the present disclosure rather than the number, shape and size of the components in actual implementation, and the type, amount and ratio of the components in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated.
In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects may be practiced without these specific details.
As shown in fig. 1, an embodiment of the present disclosure provides a method for dispatching a terminal AGV, which may be applied to a terminal or a server, where the terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable smart devices, and the server may be implemented by an independent server or a server cluster formed by multiple servers, where the method includes the following steps:
The historical operation data comprises historical dispatching data of the AGV vehicles on the operation path in a historical time period and historical work data of the AGV vehicles. The historical job data may include ship loading and unloading data that is historically docked at the dock and the loading and unloading jobs are completed by the dock. The historical time period may be a time period that is backward pushed forward starting from the current time point, and the length of the time period may be day, month, quarter, year, and the like. The historical scheduling data of the AGV vehicles may include the scheduling number of the AGV vehicles corresponding to the loading/unloading job on the job path. The AGV car historical operating data may include whether each AGV car is operating, the length of operation, etc. over a historical period of time.
The server can acquire historical operation data of historical AGV vehicles of container terminals of all operation paths. The server can sample historical job data, and can acquire a sample set X of historical job data construction model training in a preset time period before all job path sample time points at a preset frequency. The preset frequency may be a frequency of 20 minutes/time. The sample time points of each sample are different, so the server will extract historical operation data of the past three hours of the sample time point, the operation of the time point and the operation plans of all operation paths of the ships in the port according to the sample time point of each sample.
And 102, analyzing historical operation data, and respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path.
And analyzing the historical operation data by the server, and respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path. The server can use the feature extractor to extract the operation features of each operation path, and then respectively train the AGV state information judgment model f corresponding to each operation path according to the operation features c AGV dispatching model f of operation path r AGV evaluation time model f t 。f r Predicting the dispatching quantity f of AGV in historical state of operation path c Predicting the condition of AGV gear breakage or AGV excess in the future 5-20 minutes of the operation way f t And predicting the predicted time for completing the operation on the operation path.
And 103, acquiring historical operation data in a preset time period before the current time point of the operation path, the operation plan of the operation path of the ship at the port, which is operated at the current time point, and the ship plan debarking time at a preset frequency to obtain the current operation data.
The server obtains historical operation data in a preset time period before the current time point of the operation path, an operation plan of the operation path of the ship at the port and the ship plan leaving time, wherein the operation plan is operated at the current time point, and the current operation data are obtained. The sampling frequency of the current job data may or may not be the same as the sampling frequency of the historical job data. In one embodiment, the preset frequency may be a frequency of 15 minutes/time.
And 104, inputting the current operation data into the AGV evaluation time model corresponding to each operation path to obtain the predicted residual time proportion of each operation path.
The server inputs the current operation data into the AGV evaluation time model corresponding to each operation path to obtain the predicted residual time of each operation pathAnd (4) remaining time proportion. The server can use the feature extractor to extract the feature x of each job path in the current job data and respectively calculate y r =f r (x),y c =f c (x),y t =f t (x),y r Indicating that the scheduled number of AGVs is set based on historical job data prediction for current job data. y is c Y represents the situation of predicting whether the AGV shortage or the AGV excess will occur within 5 to 15 minutes in the future according to the historical operation data t Indicating that the predicted job time for the job path is predicted based on the historical job data. The server will utilize y t And obtaining the predicted residual time proportion of each operation path.
And 105, resetting the dispatching values of all the AGV vehicles in the current operation data according to the residual time proportion and the AGV vehicle state information judgment model and the operation path AGV vehicle dispatching model to obtain the dispatching adjustment values of the AGV vehicles.
And the server resets the dispatching numerical values of all the AGV vehicles in the current operation data according to the residual time proportion and the AGV vehicle state information judgment model and the operation path AGV vehicle dispatching model to obtain the dispatching adjustment values of the AGV vehicles.
And step 106, adjusting and limiting the AGV dispatching adjustment value according to the dispatching limitation rule to obtain the AGV dispatching update value of all the operation paths.
And the server adjusts and limits the AGV dispatching adjustment value according to the dispatching limitation rule to obtain the AGV dispatching update value of all the operation paths. The updated AGV dispatching value is the final dispatching value of the AGV on each operation path. In one embodiment, the scheduling restriction rule includes: each working roadiSetting the minimum dispatching quantity N of AGV vehicles min And a maximum scheduling number N max ,N i At N min And N max N is i =max (min(N i ,N max ),N min ). Where N is max And N min All are adjustable hyper-parameters;
counting total N of AGV operation quantity of all operation paths used =∑ Shipping operation road i N i ×β 1 +∑ Ship unloading operation road i N i ×β 2 ,β 1 To calculate the ratio of the loading operation time to the scheduling time of the AGV,β 2 the ratio of the average dispatching time for AGV ship unloading; n is a radical of used ≤N AGV , N AGV Indicating the total number of AGV vehicles on all the current working paths.
In one embodiment, when N used >N AGV In time, calculate that each job path should reduce the actual AGV job count to;
For the working path of shipmentiAdjusting the AGV dispatching quantity to(ii) a For the working path of the ship unloadingiAdjusting the AGV dispatching quantity to(ii) a After the adjustment is finished, N used And N AGV And (4) approaching.
According to the method, the scheduling model is generated according to the historical operation data, the theoretical value obtained by the scheduling model is adjusted according to the current operation data, the historical operation data and the current operation data which are loaded and unloaded at present are simultaneously used as independent variables to participate in the training process of the model, so that the obtained AGV scheduling updating value is more accurate and can be attached to the current operation, the condition of executing the operation can be better reflected, and the reasonable distribution of the AGV of each bridge crane can be realized. In addition, the current operation data is dynamically acquired in real time, so that the finally obtained AGV dispatching update value is more accurate.
As shown in fig. 2, in an embodiment, analyzing historical job data, and respectively training an AGV state information determination model, an AGV scheduling model, and an AGV evaluation time model corresponding to each job path includes:
In one embodiment, the method for acquiring the AGV scheduling number in the history state of the job path by the server is as follows: calculating the number of the AGV in scheduling once per minute from the past 15 minutes to the next 15 minutes of the sample time point, namely counting the number of the AGV vehicles which start to schedule for the AGV, are greater than the time point, end to schedule for the time point and schedule for the operation path; then, the AGV number which is being dispatched every minute is taken as the maximum value, and the value is set as the dispatching number Y of the AGV which is set at the time r 。
In one embodiment, the server may extract the operating state tag Y of each AGV corresponding to the sample operation time from the historical operation data c . The server records the gear-breaking times c of the AGV in every minute for 5-20 minutes in the future of the sampling time point 1 And recording whether the situation that the last door closing frame trolley is already put in a box and the next door closing frame trolley does not reach the bridge crane. Likewise, the number of AGV overruns c is recorded per minute 2 I.e., whether there are more than two AGVs, the arrival time before this point in time and the last closing time of the closing gantry trolley after this closing. For c 1 >0 and c 2 If the number of the AGV dispatching tags is not less than 0, setting the tags to be +1, wherein the situation indicates that the number of the AGV dispatches currently is small, more AGV are needed, and the AGV needs to be increased; for c 1 =0 and c 2 >Under the condition of 0, setting the label as-1 to indicate that the current AGV schedules more, so that the scheduling number of the AGV can be reduced; otherwise, setting the flag to 0, which indicates that the AGV number does not need to be adjusted.
In one embodiment, the server may extract the job time Y for each AGV corresponding to the sample job plan from the historical job data t . And the server acquires the total operation time of the operation path of the current sampling time node. I.e. calculating the working time from the sampling time point to the last container of the working road to finish loading and unloading. When the time point of the last closing main trolley for completing loading and unloading and the time point of the next closing main trolley for starting operation are more than 20 minutes, the bridge crane is judged not to be in the operation path for operationThe time should be subtracted by the job time for that time period.
The server extracts a job feature X for each job path using a feature extractor. And the server determines the operation characteristics of each operation path according to the scheduling number of the AGV vehicles, the working state labels of the AGV vehicles and the operation time of the AGV vehicles.
And 203, respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path according to the operation characteristics.
And the server respectively trains an AGV state information judgment model, an operation path AGV dispatching model and an AGV evaluation time model corresponding to each operation path according to the operation characteristics. The server according to the data set X and the corresponding scheduling number Y r Predicting the scheduling quantity by using a gradient lifting decision tree, and training the gradient lifting decision tree to obtain a model f r . The server is based on the data set X and the corresponding classification label Y c Predicting the result of AGV gear-breaking or process by using gradient lifting decision tree, and training the gradient lifting decision tree to obtain model f c . The server operates time Y according to the data set X and the corresponding operation path t Predicting the operation time of the operation road by using linear regression, and training a linear regression model to obtain a model f t 。
In one embodiment, inputting the current operation data into the AGV estimation time model corresponding to each operation path to obtain the predicted remaining time ratio of each operation path includes: obtaining the number N of total operation paths from the current operation data STS Total number N of AGV vehicles on all current operation roads AGV Planned departure time t of ship left Current time t now (ii) a According to planned departure time t of ship left Current time t now Calculating to obtain the residual operation time t of each operation path work =t left -t now (ii) a The number N of total operation paths in the current operation data STS Total number N of AGV cars AGV Inputting an AGV evaluation time model to obtain the predicted operation time y of the operation path t Calculating a predicted remaining time ratio of each operation route,α i Is shown asiThe remaining time proportion of the working path.
The server obtains the number N of the total operation paths from the current operation data STS Total number N of AGV vehicles on all current operation roads AGV Planned departure time t of ship left Current time t now (ii) a According to planned departure time t of ship left Current time t now Calculating to obtain the residual operation time t of each operation path work =t left -t now (ii) a The number N of total operation paths in the current operation data STS Total number N of AGV cars AGV Inputting an AGV evaluation time model to obtain the predicted operation time y of the operation path t Calculating a predicted remaining time ratio of each operation route,α i Is shown asiThe remaining time proportion of the work lane.
In one embodiment, based on the remaining time ratio, resetting the scheduling values of all AGV vehicles in the current job data according to the AGV vehicle state information judgment model and the job path AGV vehicle scheduling model to obtain an AGV vehicle scheduling adjustment value, including:
proportional to the remaining timeα i And a predetermined threshold valueαCarrying out comparison and judgment;
when in useα i Is greater thanαThen, the current operation data is input into an AGV dispatching model of an operation path to obtain a first dispatching estimated value y of the AGV w (ii) a And inputting the current operation data into an AGV state information judgment model to determine whether the AGV is in a gear failure or the AGV is in an excessive redundancy adjustment value y c (ii) a According to the first scheduling estimated value y of the AGV w And a redundancy scheduling value y c Obtaining the dispatching adjustment value y of the AGV p =y w +y c Wherein, y c =1 indicating a lack of AGV, the possibility of AGV coming out of gear next, y c =1 indicates that too many AGVs do not require as many AGVs; setting the dispatching quantity of AGV as y = theta x y r +(1-θ)×y p Theta is a hyperparameter and theta stands for y and is the sum of two numbers, i.e., two kinds of values y can be used r And y p To get the value of y, θ =0.7 may be set. Taking the number of AGV scheduling at the sampling time point of +/-15 minutes as sampling source data, counting the number of AGV scheduling at one time per minute, taking the number of AGV scheduling at one time per minute to obtain the maximum value, and setting the maximum value as the AGV scheduling number y in actual working r 。
When in useα i Is less thanαWhen the AGV is in the process of the Automatic Guided Vehicle (AGV), the dispatching adjustment value is,N STS Is the number of total operation paths, N AGV Total number of AGV vehicles on the current operation roadiThe order of the operation paths is r i Sigma is the standard deviation of the dispatching quantity of AGV in the operation path in the historical data, r i Indicates the remaining time ratio a of the ith operation road i The order of (a). When there are two work lanes i and j, if a i < a j That is, job lane i is more urgent than job lane j, so job laneiThe dispatching quantity of AGV should be larger than that of the job path j, so r j >r i Thus r is j >r i The total number of AGV vehicles indicating the ith working path is larger than the working path r j The emergency degree factor is smaller than the operation road r i The AGV dispatch number.And if the operation path is urgent, distributing the AGV dispatching quantity of the operation path according to the normal distribution of the ranked AGV dispatching quantity and not adopting the predicted AGV dispatching quantity.iAndjare the sort numbers of the job paths, and may be integers starting from 1.
The data used in the above models include, but are not limited to, the following:
characteristic data of first and second bridge cranes
(1) X1, bridge crane ID, enumeration data. Due to the different specific performance of each bridge crane, there may be different estimates of the operating time for different bridge crane IDs.
Second, case number characteristic data
(2) X2, total bin count, numerical data. Containers with different container orders are different, and the specific ship unloading strategies adopted by the bridge crane are different.
(3) X3, number of unboxed boxes, numerical data. And (5) ship operation basic data.
(4) X4, number of unboxed boxes, numerical data. And (5) ship operation basic data.
(5) X5, number of boxes sent, numerical data. And (5) ship operation basic data.
(6) X6, number of bins sent, numerical data. And (5) ship operation basic data.
The data X3 to X6 may include the number of boxes since the start of the present loading and unloading operation.
(7) X7, ratio of planned shipment total boxes to loading and unloading total boxes, numerical data. And (5) ship operation basic data.
(8) X8, ratio of planned ship unloading total boxes to loading and unloading total boxes, and numerical data. And (5) ship operation basic data.
(9) X9, ratio of the number of loaded boxes to the total number of loaded and unloaded boxes, and numerical data. And (5) ship operation basic data.
(10) X10, ratio of planned shipment small box number to total loading and unloading box number, and numerical data. And (5) ship operation basic data.
(11) X11, ratio of planned shipment big boxes to total loading and unloading boxes, numerical data. And (5) ship operation basic data.
(12) X12, ratio of the number of loaded small boxes to the total number of loading and unloading boxes, and numerical data. And (5) ship operation basic data.
Third, bridge crane operation characteristic data
(13) X13, current bridge handling type, enumeration data. Loading or unloading.
(14) X14, current bridge operation process, enumerate data. Double boxes, single box, double lifting appliance.
(15) X15, job bit where the current bridge crane is located, enumerates the data. Corresponding to the position on the vessel.
(16) X16, determine if the shell bit is big shell bit, enumerate the data. In the case of 40-foot container operations, the large bunk, i.e. the position on board the 40-foot container being operated, needs to be determined.
(17) X17, the current working layer on which the bridge crane is located, numerical data. The ship is high and the ship operation basic data is indicated.
Fourthly, the loading and unloading operation bridge crane completes operation information data
(18) X18, number of completed bins, numerical data. The bridge crane has been operated.
(19) X19, existing operating time in this decimal place, numerical data. Basic data of bridge crane operation.
(20) X20, average working time per box in the current loading and unloading work, numerical data. And carrying out data statistics on the bridge crane operation in the loading and unloading operation.
(21) X21, predicted remaining operating time according to current efficiency, numerical data. And dividing the total box number by the efficiency of the bridge crane and basic data of the bridge crane operation.
Fifthly, the ship characteristic data of loading and unloading at this time
(22) X22, ship type, enumeration data. There are different types of vessels.
(23) X23, remaining parking time, numerical data. And estimating the working time.
(24) X24, planned berth time, numerical data. And (5) ship operation basic data.
Sixthly, loading and unloading global characteristic data this time
(25) X25, number of work paths being worked, numerical data. And (5) wharf operation basic data.
(26) X26, total number of current full field stowage, numerical data. And (5) wharf operation basic data.
(27) X27, number of boxes that have been sent at the current full field, numerical data. And (5) wharf operation basic data.
(28) X28, total number of cases in past three hours, numerical data. And (5) wharf operation basic data.
In some other embodiments, X28 may adopt the total number of boxes in the entire time from the start of the current loading and unloading operation to the current sampling time instead of the total number of boxes in the past three hours.
(29) X29, current number of vessels berthed, numerical data. And (5) wharf operation basic data.
(30) X30, current dock AGV total, numerical data. And (5) wharf operation basic data.
Characteristic data of seven-key operation road and bridge crane
(31) And X31, finishing time of a key operation road bridge crane plan and numerical data. According to the completion time of the operation plan.
It should be noted that, after the start of the loading and unloading operation, the bridge crane in which the key operation line is located may be determined by comparing the predicted completion operation time of each bridge crane.
(32) And X32, ranking and enumerating data of the current number of the bridge crane plan boxes in the total number of the ship plan boxes. In a plurality of bridge cranes of the current ship, the operation paths of the bridge cranes can be estimated according to the total box volume, then importance ranking is given, and a normalization method can be used for calculation.
(33) And X33, and ranking enumeration data of the total number of planning boxes of the wharf occupied by the current number of planning boxes of the bridge crane. In a plurality of bridge cranes of the whole wharf, the operation paths of the bridge cranes can be estimated according to the total box volume, then importance ranking is given, and a normalization method can be used for calculation.
When a dock uses AGV vehicles for container transfers, such as an automated container terminal, the job data may also include operating characteristics of the AGV vehicles within three hours, as follows:
eight, AGV vehicle operation characteristic data within three hours
(34) X34, mean time to dispatch for loading of AGV vehicle for last three hours, numerical data. And (5) wharf job statistical data.
(35) X35, average scheduled time to unload of last three hours AGV vehicle, numerical data. And (5) wharf job statistical data.
(36) X36, mean time to load AGV vehicle for the last three hours, numerical data. And (5) wharf job statistical data.
(37) X37, average scheduled time to unload of last three hours AGV vehicle, numerical data. And (5) wharf job statistical data.
In some other embodiments, at least one of the data X34 to X37 may be the operation characteristic data of the AGV vehicle in the entire time from the start of the current loading/unloading operation to the current sampling time, instead of the operation characteristic data of the AGV vehicle in the past three hours.
At least one of the data X34 to X37 may be the operation characteristic data of the AGV in other time periods, for example, the operation characteristic data of the AGV in the last two hours or the last six hours, instead of the operation characteristic data of the AGV in the last two hours. Taking X34 as an example, the average loading scheduling time of the AGV vehicle in the last three hours is substituted by the average loading scheduling time of the AGV vehicle in the last two hours or the average loading scheduling time of the AGV vehicle in the last six hours, and the substituted time is input into the model as independent variable data for training.
Nine, current characteristic data of bridge crane
(38) X38, the number of AGV vehicles dispatched by the bridge crane in real time, and numerical data. The number of AGV vehicle dispatches, i.e., how many AGVs are available for use by the current job path.
The operation path refers to an operation path for lifting a container from a ship to a bridge crane and then transporting the container back to the container area by the bridge crane, or an operation path for transporting a container from the container area to a position below the bridge crane and then lifting the container by the bridge crane to a designated bin position on the ship.
(39) X39, the number of AGV vehicles in real time operation of the bridge crane, and numerical data.
(40) X40, the number of broken gear ratio of the bridge crane in the loading and unloading operation, and numerical data. And (5) wharf job statistical data.
(41) X41, the number of times the bridge crane of the loading and unloading operation waits for the AGV vehicle, and numerical data. And (5) wharf job statistical data.
(42) X42, average waiting time of the bridge crane in the current loading and unloading work, and numerical data. And (5) wharf job statistical data.
(43) X43, average waiting time of the AGV vehicle in the current loading/unloading work, and numerical data. And (5) wharf job statistical data.
The data may be of a data type of some or all of X1 to X43, and the data corresponding to the loading/unloading work that has been completed in the past may be used as the first work data, that is, may be trained as the historical work data to be introduced into the model.
In one embodiment, as shown in FIG. 3, a terminal AGV car dispatching apparatus is provided, which comprises a historical data obtaining module 301, a model training module 302, a current data obtaining module 303, a remaining time proportion obtaining module 304, a dispatching adjustment value generating module 305 and a dispatching update value generating module 306.
The historical data acquisition module 301 is configured to acquire historical operation data of historical AGV vehicles of the container terminal on all operation paths, where the historical operation data includes historical scheduling data of the AGV vehicles on the operation paths and historical working data of the AGV vehicles within a historical time period.
And the model training module 302 is used for analyzing historical operation data and respectively training an AGV state information judgment model, an operation path AGV dispatching model and an AGV evaluation time model corresponding to each operation path.
The current data obtaining module 303 is configured to obtain, at a preset frequency, historical operation data in a preset time period before a current time point of an operation path, an operation plan of an operation path of a ship at a port, and a ship plan deberthing time, where the operation is being performed at the current time point, so as to obtain current operation data.
And a remaining time proportion obtaining module 304, configured to input the current operation data into the AGV vehicle evaluation time model corresponding to each operation lane, so as to obtain a predicted remaining time proportion of each operation lane.
And the scheduling adjustment value generating module 305 is configured to reset the scheduling values of all the AGVs in the current job data according to the AGV state information determination model and the job path AGV scheduling model based on the remaining time proportion, so as to obtain an AGV scheduling adjustment value.
And the scheduling update value generation module 306 is configured to adjust and limit the AGV scheduling adjustment value according to the scheduling limit rule, so as to obtain AGV scheduling update values of all the job paths.
In one embodiment, the model training module comprises:
and the sampling unit is used for sampling historical operation data and extracting the scheduling number of the AGV vehicles, the working state labels of the AGV vehicles and the operation time of the AGV vehicles on the operation path in a historical time period.
And the characteristic extraction unit is used for determining the operation characteristics of each operation path according to the scheduling number of the AGV cars, the working state labels of the AGV cars and the operation time of the AGV cars.
And the model training unit is used for respectively training the AGV state information judgment model, the AGV dispatching model and the AGV evaluation time model corresponding to each operation path according to the operation characteristics.
In one embodiment, the remaining time proportion obtaining module includes:
a data acquisition unit for acquiring the total number N of job paths from the current job data STS Total number N of AGV vehicles on all current operation roads AGV Planned departure time t of ship left Current time t now 。
A remaining operation time calculation unit for calculating a planned departure time t of the ship left Current time t now Calculating to obtain the residual operation time t of each operation path work =t left -t now 。
A proportion calculation unit for calculating the total number N of operation paths in the current operation data STS Total number N of AGV cars AGV Inputting an AGV evaluation time model to obtain the predicted operation time y of the operation path t Calculating a predicted remaining time ratio of each operation route,α i Is shown asiThe remaining time proportion of the working path.
In one embodiment, the scheduling adjustment value generation module includes:
a determination unit for dividing the remaining timeα i And a predetermined threshold valueαAnd (6) carrying out comparison and judgment.
A first adjustment value calculating unit for calculating a first adjustment value whenα i Is greater thanαThen, the current operation data is input into an AGV dispatching model of an operation path to obtain a first dispatching estimated value y of the AGV w (ii) a And inputting the current operation data into an AGV state information judgment model to determine whether the AGV is in a gear failure state or the AGV is in an excessive redundant adjustment value y c (ii) a According to the first scheduling estimated value y of the AGV w And a redundancy scheduling value y c Obtaining the dispatching adjustment value y of the AGV p =y w +y c 。
A second adjustment value calculating unit for calculating a second adjustment value when the first adjustment value is greater than the second adjustment valueα i Is less thanαWhen the AGV is in the process of the Automatic Guided Vehicle (AGV), the dispatching adjustment value is,N STS Is the number of total operation paths, N AGV Total number of AGV cars for the current operation roadiThe sequence of each operation path is r i And sigma is the standard deviation of the AGV dispatching quantity of the operation path in the historical data.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store historical job data, current job data, and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a dock AGV car scheduling method.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: acquiring historical operation data of historical AGV vehicles of container terminals of all operation paths, wherein the historical operation data comprises historical dispatching data of the AGV vehicles on the operation paths and historical working data of the AGV vehicles in a historical time period; analyzing historical operation data, and respectively training an AGV state information judgment model, an AGV scheduling model and an AGV evaluation time model corresponding to each operation path; acquiring historical operation data in a preset time period before the current time point of an operation path, an operation plan of an operation path of a ship at a port, which is operated at the current time point, and ship plan debarking time at a preset frequency to obtain current operation data; inputting current operation data into an AGV evaluation time model corresponding to each operation path to obtain the predicted residual time proportion of each operation path; based on the remaining time proportion, resetting the dispatching numerical values of all AGV vehicles in the current operation data according to the AGV vehicle state information judgment model and the operation path AGV vehicle dispatching model to obtain an AGV vehicle dispatching adjustment value; and adjusting and limiting the AGV dispatching adjustment value according to the dispatching limitation rule to obtain the AGV dispatching update values of all the operation paths.
In one embodiment, the analyzing historical job data and training the AGV state information determination model, the AGV scheduling model and the AGV evaluation time model corresponding to each job path respectively, which are implemented when the processor executes the computer program, includes: sampling historical operation data, and extracting the scheduling number of the AGV vehicles, the working state labels of the AGV vehicles and the operation time of the AGV vehicles on an operation path in a historical time period; determining the operation characteristics of each operation path according to the scheduling number of the AGV cars, the working state labels of the AGV cars and the operation time of the AGV cars; and respectively training an AGV state information judgment model, an operation path AGV dispatching model and an AGV evaluation time model corresponding to each operation path according to the operation characteristics.
In one embodiment, the entering of the current operation data into the AGV estimation time model corresponding to each operation path to obtain the predicted remaining time ratio of each operation path, implemented when the processor executes the computer program, includes: obtaining the number N of total operation paths from the current operation data STS Total number N of AGV vehicles on all current operation roads AGV Planned departure time t of ship left Current time t now (ii) a According to planned departure time t of ship left Current time t now Calculating to obtain the residual operation time t of each operation path work =t left -t now (ii) a The number N of total operation paths in the current operation data STS AGV total number N AGV Inputting an AGV evaluation time model to obtain the predicted operation time y of the operation path t Calculating a predicted remaining time ratio of each operation route,α i Is shown asiThe remaining time proportion of the working path.
In one embodiment, the resetting of the scheduling values of all AGV vehicles in the current job data according to the AGV vehicle state information determination model and the job path AGV vehicle scheduling model based on the remaining time ratio when the processor executes the computer program to obtain the AGV vehicle scheduling adjustment value includes: proportional to the remaining timeα i And a predetermined threshold valueαCarrying out comparison and judgment; when in useα i Is greater thanαThen, the current operation data is input into an AGV dispatching model of an operation path to obtain a first dispatching estimated value y of the AGV w (ii) a And inputting the current operation data into an AGV state information judgment model to determine whether the AGV is in a gear failure or the AGV is in an excessive redundancy adjustment value y c (ii) a According to the first scheduling estimated value y of the AGV w And a redundancy scheduling value y c Obtaining the dispatching adjustment value y of the AGV p =y w +y c (ii) a When in useα i Is less thanαWhen the AGV is in the process of the Automatic Guided Vehicle (AGV), the dispatching adjustment value is,N STS Is the number of total operation paths, N AGV Total number of AGV cars for the current operation roadiThe order of the operation paths is r i And sigma is the standard deviation of the AGV dispatching quantity of the operation path in the historical data.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring historical operation data of historical AGV vehicles of container terminals of all operation paths, wherein the historical operation data comprises historical dispatching data of the AGV vehicles on the operation paths and historical working data of the AGV vehicles in a historical time period; analyzing historical operation data, and respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path; acquiring historical operation data in a preset time period before the current time point of an operation path, an operation plan of the operation path of the ship at the port, which is operated at the current time point, and the planned departure time of the ship at the port by preset frequency to obtain the current operation data; inputting the current operation data into an AGV evaluation time model corresponding to each operation path to obtain the predicted residual time proportion of each operation path; based on the remaining time proportion, resetting the dispatching numerical values of all AGV vehicles in the current operation data according to the AGV vehicle state information judgment model and the operation path AGV vehicle dispatching model to obtain an AGV vehicle dispatching adjustment value; and adjusting and limiting the AGV dispatching adjustment value according to the dispatching limitation rule to obtain the AGV dispatching update values of all the operation paths.
In one embodiment, the analyzing historical job data and the training of the AGV state information determination model, the AGV scheduling model and the AGV evaluation time model corresponding to each job path respectively, which are implemented when the computer program is executed by the processor, includes: sampling historical operation data, and extracting the scheduling number of the AGV vehicles, the working state labels of the AGV vehicles and the operation time of the AGV vehicles on an operation path in a historical time period; determining the operation characteristics of each operation path according to the scheduling number of the AGV cars, the working state labels of the AGV cars and the operation time of the AGV cars; and respectively training an AGV state information judgment model, an operation path AGV dispatching model and an AGV evaluation time model corresponding to each operation path according to the operation characteristics.
In one embodiment, the computer program when executed by a processor implements the method of inputting current operation data into an AGV vehicle evaluation time model corresponding to each operation path to obtain a predicted remaining time ratio for each operation path, comprising: obtaining the number N of total operation paths from the current operation data STS Total number N of AGV vehicles on all current operation roads AGV Planned departure time t of ship left Current time t now (ii) a According to planned departure time t of ship left Current time t now Calculating to obtain the residual operation time t of each operation path work =t left -t now (ii) a The number N of total operation paths in the current operation data STS Total number N of AGV cars AGV Inputting an AGV evaluation time model to obtain the predicted operation time y of the operation path t Calculating a predicted remaining time ratio of each operation route,α i Is shown asiThe remaining time proportion of the working path.
In one embodiment, the resetting of the scheduling values of all AGV vehicles in the current job data according to the AGV vehicle state information determination model and the job path AGV vehicle scheduling model based on the remaining time ratio when the computer program is executed by the processor to obtain the AGV vehicle scheduling adjustment value includes: proportional to the remaining timeα i And a predetermined threshold valueαCarrying out comparison and judgment; when in useα i Is greater thanαThen, the current operation data is input into an AGV dispatching model of an operation path to obtain a first dispatching estimated value y of the AGV w (ii) a And inputting the current operation data into an AGV state information judgment model to determine whether the AGV is in a gear-off state or the AGV passes throughRemaining redundant scheduling value y c (ii) a According to the first scheduling estimated value y of the AGV w And a redundancy scheduling value y c Obtaining the dispatching adjustment value y of the AGV p =y w +y c (ii) a When in useα i Is less thanαWhen the AGV is in the process of the Automatic Guided Vehicle (AGV), the dispatching adjustment value is,N STS Is the number of total operation paths, N AGV Total number of AGV cars for the current operation roadiThe order of the operation paths is r i And sigma is the standard deviation of the AGV dispatching quantity of the operation path in the historical data.
The above description is only for the specific embodiments of the present disclosure, but the scope of the present disclosure is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present disclosure should be covered within the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (9)
1. A wharf AGV car scheduling method is characterized by comprising the following steps:
acquiring historical operation data of historical AGV vehicles of container terminals of all operation paths, wherein the historical operation data comprises historical dispatching data of the AGV vehicles and historical working data of the AGV vehicles on the operation paths in a historical time period;
analyzing the historical operation data, and respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path;
acquiring historical operation data in a preset time period before the current time point of the operation path, an operation plan of the operation path of the ship at the port and the planned berthing time of the ship, wherein the operation plan is operated at the current time point, and the current operation data are acquired;
inputting the current operation data into an AGV evaluation time model corresponding to each operation path to obtain the predicted residual time proportion of each operation path;
based on the remaining time proportion, resetting the dispatching values of all the AGV vehicles in the current operation data according to the AGV vehicle state information judgment model and the operation path AGV vehicle dispatching model to obtain an AGV vehicle dispatching adjustment value;
and adjusting and limiting the AGV dispatching adjustment value according to a dispatching limitation rule to obtain the AGV dispatching update values of all the operation ways.
2. The wharf AGV dispatching method according to claim 1, wherein the analyzing the historical operation data and respectively training an AGV state information judgment model, an operation path AGV dispatching model and an AGV evaluation time model corresponding to each operation path comprises:
sampling the historical operation data, and extracting the scheduling number of the AGV vehicles, the working state labels of the AGV vehicles and the operation time of the AGV vehicles on the operation road in a historical time period;
determining the operation characteristics of each operation path according to the scheduling number of the AGV cars, the working state labels of the AGV cars and the operation time of the AGV cars;
and respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path according to the operation characteristics.
3. The dock AGV vehicle dispatching method of claim 1, wherein said inputting said current job data into an AGV vehicle evaluation time model corresponding to each said job path to obtain a predicted remaining time proportion for each said job path comprises:
obtaining the number N of total operation paths from the current operation data STS Total number N of AGV vehicles on all current operation roads AGV Planned debarking time t of ship left Current time t now ;
According to planned departure time t of ship left Current time t now Calculating to obtain the value of each operation pathRemaining operation time t work =t left -t now ;
The number N of the total operation paths in the current operation data STS Total number N of AGV cars AGV Inputting an AGV evaluation time model to obtain the predicted operation time y of the operation path t Calculating a predicted remaining time ratio of each operation route,α i Is shown asiThe remaining time proportion of the working path.
4. The wharf AGV dispatching method according to claim 1, wherein the resetting of the dispatching numerical values of all the AGV cars in the current operation data according to the AGV car state information determination model and the operation path AGV car dispatching model based on the remaining time ratio to obtain an AGV car dispatching adjustment value comprises:
proportional to the remaining timeα i And a predetermined threshold valueαCarrying out comparison and judgment;
when the temperature is higher than the set temperatureα i Is greater thanαThen, the current operation data is input into the operation path AGV dispatching model to obtain a first dispatching estimated value y of the AGV w (ii) a And inputting the current operation data into the AGV state information judgment model to determine whether the AGV is in a gear failure or the AGV is in an excessive redundant scheduling value y c (ii) a According to the first scheduling estimated value y of the AGV w And a redundancy scheduling value y c Obtaining the dispatching adjustment value y of the AGV p =y w +y c ;
When in useα i Is less thanαWhen the AGV vehicle scheduling adjustment value is,N STS Is the number of total operation paths, N AGV Total number of AGV cars for the current operation roadiThe order of the operation paths is r i And sigma is the AGV regulation of the operation path in the historical dataAnd (4) measuring standard deviation.
5. The dockside AGV vehicle scheduling method of claim 1 wherein said scheduling restriction rules comprise:
each of the working pathsiSetting the minimum dispatching quantity N of AGV vehicles min And a maximum scheduling number N max ,N i At N min And N max To (c) to (d);
counting total N of AGV operation quantity of all operation paths used =∑ Shipping operation road i N i ×β 1 +∑ Ship unloading operation road i N i ×β 2 ,β 1 To calculate the ratio of the loading operation time to the scheduling time of the AGV,β 2 the ratio of the average dispatching time for AGV ship unloading; n is a radical of hydrogen used ≤N AGV , N AGV Indicating the total number of AGV vehicles on all the current working paths.
6. The dock AGV car dispatching method of claim 5, wherein when N is used >N AGV In time, calculate that each job path should reduce the actual AGV job count to;
7. A dock AGV car scheduling device, characterized in that, the device includes:
the historical data acquisition module is used for acquiring historical operation data of historical AGV vehicles of the container terminal of all operation paths, and the historical operation data comprises historical dispatching data of the AGV vehicles and historical working data of the AGV vehicles on the operation paths in a historical time period;
the model training module is used for analyzing the historical operation data and respectively training an AGV state information judgment model, an AGV dispatching model and an AGV evaluation time model corresponding to each operation path;
the current data acquisition module is used for acquiring historical operation data in a preset time period before the current time point of the operation path, an operation plan of the operation path of the ship at the port and the planned berthing time of the ship, which are operated at the current time point, at a preset frequency to obtain current operation data;
the residual time proportion acquisition module is used for inputting the current operation data into an AGV evaluation time model corresponding to each operation path to obtain the predicted residual time proportion of each operation path;
the scheduling adjustment value generation module is used for resetting the scheduling values of all the AGV vehicles in the current operation data according to the AGV vehicle state information judgment model and the operation path AGV vehicle scheduling model based on the residual time proportion to obtain an AGV vehicle scheduling adjustment value;
and the scheduling update value generation module is used for adjusting and limiting the AGV scheduling adjustment value according to the scheduling limitation rule to obtain the AGV scheduling update values of all the operation ways.
8. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210983715.8A CN115049324B (en) | 2022-08-17 | 2022-08-17 | Wharf AGV (automatic guided vehicle) scheduling method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210983715.8A CN115049324B (en) | 2022-08-17 | 2022-08-17 | Wharf AGV (automatic guided vehicle) scheduling method and device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115049324A true CN115049324A (en) | 2022-09-13 |
CN115049324B CN115049324B (en) | 2022-11-04 |
Family
ID=83168063
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210983715.8A Active CN115049324B (en) | 2022-08-17 | 2022-08-17 | Wharf AGV (automatic guided vehicle) scheduling method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115049324B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108845496A (en) * | 2018-05-23 | 2018-11-20 | 大连海事大学 | A kind of automatic dock AGV dispatching method and system |
CN110516976A (en) * | 2019-08-30 | 2019-11-29 | 大连海事大学 | A kind of automated container terminal AGV dispatching method of optional handling completion date |
CN110942203A (en) * | 2019-12-03 | 2020-03-31 | 青岛港国际股份有限公司 | Automatic container terminal AGV path optimization method |
CN111091238A (en) * | 2019-12-03 | 2020-05-01 | 青岛港国际股份有限公司 | Automatic container terminal AGV intelligent scheduling method |
CN112525196A (en) * | 2020-11-23 | 2021-03-19 | 山东亚历山大智能科技有限公司 | AGV route planning and scheduling method and system based on multidimensional data |
CN112764405A (en) * | 2021-01-25 | 2021-05-07 | 青岛港国际股份有限公司 | AGV scheduling method based on time estimation model |
CN113867295A (en) * | 2021-10-11 | 2021-12-31 | 西安交通大学 | Manufacturing workshop AGV dynamic scheduling method, system, equipment and storage medium based on digital twinning |
WO2022007179A1 (en) * | 2020-07-10 | 2022-01-13 | 歌尔股份有限公司 | Multi-agv motion planning method, apparatus, and system |
-
2022
- 2022-08-17 CN CN202210983715.8A patent/CN115049324B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108845496A (en) * | 2018-05-23 | 2018-11-20 | 大连海事大学 | A kind of automatic dock AGV dispatching method and system |
CN110516976A (en) * | 2019-08-30 | 2019-11-29 | 大连海事大学 | A kind of automated container terminal AGV dispatching method of optional handling completion date |
CN110942203A (en) * | 2019-12-03 | 2020-03-31 | 青岛港国际股份有限公司 | Automatic container terminal AGV path optimization method |
CN111091238A (en) * | 2019-12-03 | 2020-05-01 | 青岛港国际股份有限公司 | Automatic container terminal AGV intelligent scheduling method |
WO2022007179A1 (en) * | 2020-07-10 | 2022-01-13 | 歌尔股份有限公司 | Multi-agv motion planning method, apparatus, and system |
CN112525196A (en) * | 2020-11-23 | 2021-03-19 | 山东亚历山大智能科技有限公司 | AGV route planning and scheduling method and system based on multidimensional data |
CN112764405A (en) * | 2021-01-25 | 2021-05-07 | 青岛港国际股份有限公司 | AGV scheduling method based on time estimation model |
WO2022156440A1 (en) * | 2021-01-25 | 2022-07-28 | 青岛港国际股份有限公司 | Agv scheduling method based on time estimation model |
CN113867295A (en) * | 2021-10-11 | 2021-12-31 | 西安交通大学 | Manufacturing workshop AGV dynamic scheduling method, system, equipment and storage medium based on digital twinning |
Also Published As
Publication number | Publication date |
---|---|
CN115049324B (en) | 2022-11-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5037927B2 (en) | Information processing apparatus, information processing method, program, and recording medium | |
CN114911238B (en) | Unmanned mine car cooperative control method and system | |
CN112396362A (en) | Method and device for determining driving destination and storage medium | |
KR102503198B1 (en) | Device and method for providing optimal cargo delivery route based on artificial intelligence | |
KR20210083661A (en) | System for repositioning optimization of empty container in ship network based artificial intelligence planning technology and method therefor | |
KR20220006726A (en) | Device and method for providing automatic distribution of milk run cargo based on route big data | |
CN115983603A (en) | Intelligent scheduling algorithm, system, equipment and storage medium for container port transshipment | |
CN115293443B (en) | Bridge crane and container ship loading and unloading operation time prediction method, system and medium | |
CN115049324B (en) | Wharf AGV (automatic guided vehicle) scheduling method and device, computer equipment and storage medium | |
CN117252509A (en) | Water transportation ship arranging method and device based on commodity inventory pressure | |
CN111652551B (en) | Method and device for transporting and boxing goods | |
CN116957440A (en) | Large-scale power generation group-oriented coal transportation planning method and system | |
JP7402986B2 (en) | Container storage planning device, container storage planning system, and container storage planning method | |
Olson et al. | Medium-range scheduling for a freighter fleet | |
CN115545416A (en) | Method for generating bridge crane operation plan, method for controlling bridge crane operation plan, device, equipment and medium | |
CN113689076B (en) | Method for improving ship loading and unloading operation efficiency based on core operation line | |
Tang et al. | Regulating the imbalance for the container relocation problem: A deep reinforcement learning approach | |
CN114707820A (en) | Cargo transportation method and device, terminal equipment and readable storage medium | |
CN115545369A (en) | Automated quayside container bridge resource planning decision-making method, terminal and medium | |
Khafid et al. | A concept to reduce idle time on stevedoring activities in a container terminal | |
CN112668778A (en) | Intelligent ship scheduling system and method and computer storage medium | |
WO2003094065A1 (en) | Transport managing device | |
Park et al. | Dynamic equipment deployment at a container terminal: transfer system based on real-time positioning | |
CN110796417B (en) | Goods source value determination method, device, equipment and storage medium | |
TWI842197B (en) | Method for evaluating system reliability of transportation network and apparatus using the same |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |