CN117522234B - Digital twinning-based vehicle team logistics commanding decision modeling method, device and equipment - Google Patents
Digital twinning-based vehicle team logistics commanding decision modeling method, device and equipment Download PDFInfo
- Publication number
- CN117522234B CN117522234B CN202311517261.6A CN202311517261A CN117522234B CN 117522234 B CN117522234 B CN 117522234B CN 202311517261 A CN202311517261 A CN 202311517261A CN 117522234 B CN117522234 B CN 117522234B
- Authority
- CN
- China
- Prior art keywords
- logistics
- data
- decision
- model
- digital twin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000009826 distribution Methods 0.000 claims abstract description 99
- 238000012384 transportation and delivery Methods 0.000 claims abstract description 66
- 239000013598 vector Substances 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 41
- 230000004927 fusion Effects 0.000 claims abstract description 14
- 241000254173 Coleoptera Species 0.000 claims description 40
- 210000003608 fece Anatomy 0.000 claims description 40
- 238000004422 calculation algorithm Methods 0.000 claims description 35
- 230000003068 static effect Effects 0.000 claims description 28
- 238000010276 construction Methods 0.000 claims description 23
- 230000006399 behavior Effects 0.000 claims description 19
- 238000013439 planning Methods 0.000 claims description 19
- 230000033001 locomotion Effects 0.000 claims description 17
- 230000001133 acceleration Effects 0.000 claims description 15
- 238000007637 random forest analysis Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 12
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 230000007935 neutral effect Effects 0.000 claims description 7
- 230000000739 chaotic effect Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000035772 mutation Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 20
- 230000008569 process Effects 0.000 description 19
- 239000010410 layer Substances 0.000 description 7
- 238000004088 simulation Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 238000005096 rolling process Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 238000005094 computer simulation Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000002431 foraging effect Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000002550 fecal effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 101100457838 Caenorhabditis elegans mod-1 gene Proteins 0.000 description 1
- 208000034423 Delivery Diseases 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 101150110972 ME1 gene Proteins 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000012447 hatching Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 239000002346 layers by function Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a digital twin-based vehicle team logistics command decision modeling method, a device and equipment, wherein the method comprises the steps of obtaining logistics data required by vehicle team logistics, wherein the logistics data comprise real-time acquisition logistics data, client data and historical logistics data; carrying out data processing and fusion on the logistics data to obtain one-dimensional vector data; constructing a digital twin motorcade logistics command decision model according to real-time acquisition logistics data and historical logistics data; inputting the one-dimensional vector data into a logistics command decision model of the digital twin motorcade, and outputting a delivery destination; and (3) inputting the current positions of the vehicles with the delivery destinations and the real-time logistics data acquisition into a digital twin vehicle team logistics command decision model together, and outputting a delivery path plan of the vehicle team logistics command decision. The method generates a distribution path plan of the logistics command decision of the motorcade, can relieve the information island effect, improves the decision efficiency and realizes reliable decision deduction demonstration.
Description
Technical Field
The application relates to the technical field of logistics modeling, in particular to a digital twinning-based vehicle team logistics commanding decision modeling method, device and equipment.
Background
Fleet logistics refers to a business model of a fleet of vehicles for logistics transportation and distribution services. Fleet logistics is typically performed by a fleet manager or logistics company in charge of orchestrating and coordinating vehicle scheduling, cargo transportation, and operations during transportation. Fleet logistics plays an important role in the field of commercial logistics and provides efficient, fast and reliable cargo distribution services. In fleet logistics, command decisions play a critical role, which involves the overall planning and management of fleet operations and task scheduling. The command decision system is a technical device which comprehensively uses a computer as a core, realizes the automation of the acquisition, transmission and processing of information, ensures that command institutions at all levels carry out scientific and efficient command control and management on a vehicle team, has the functions of command control, intelligence reconnaissance, early warning detection, communication and related information guarantee, is a generic name of various information systems, widely uses the command decision system in the logistics transportation process, integrates all information in the logistics transportation process of the vehicle team, generates decision instructions, and commands a logistics distribution unit in front.
The current command decision system has large volume in the process of generating decision instructions, the influence of decision results is far away, and the incorrect logistics distribution decision results can generate irreversible influence, so that irrecoverable losses are caused. Along with the development of science and technology, the situation of the transport vehicle can be analyzed by utilizing an intelligent algorithm to obtain a command decision result, and decision support is provided for a command organization. However, the existing command decision process is complicated, and in the whole process of command decision, due to different purposes and requirements of each stage of information acquisition, decision generation and decision evaluation, an information island is generated, so that the data circulation process of each stage is slow, the decision efficiency is low, and effective decision generation and deduction cannot be performed.
Therefore, it is needed to improve the existing command decision system, combine the computer simulation means with the related decision algorithm, realize the decision generation and evaluation in the digital space, alleviate the problems of slow decision generation, poor decision effect and the like, and realize the real-time intelligent decision and efficient decision deduction demonstration.
Disclosure of Invention
The embodiment of the application provides a digital twin-based vehicle team logistics command decision modeling method, device and equipment, which are used for solving the technical problems that the existing command decision system has information islands, so that the data circulation process of each stage is slow, the decision efficiency is low, and effective decision generation and deduction cannot be performed.
In order to achieve the above object, the embodiment of the present application provides the following technical solutions:
In one aspect, a digital twinning-based fleet logistics commanding decision modeling method is provided, which comprises the following steps:
Acquiring logistics data required by a fleet logistics, wherein the logistics data comprises real-time acquisition logistics data, customer data and historical logistics data;
Carrying out data processing and fusion on the logistics data to obtain one-dimensional vector data;
constructing a digital twin motorcade logistics command decision model according to the real-time collected logistics data and the historical logistics data;
Inputting the one-dimensional vector data into the digital twin motorcade logistics command decision model, and outputting a delivery destination; and inputting the current positions of the delivery destination and the vehicles for acquiring logistics data in real time into the digital twin vehicle team logistics command decision model together, and outputting a delivery path plan of the vehicle team logistics command decision.
Preferably, acquiring the logistics data required for the fleet logistics includes:
The method comprises the steps that a detection element is adopted to collect the speed, acceleration, weight bearing, current position and environment temperature of a logistics vehicle in real time as real-time logistics data;
Obtaining static data of a logistics distribution unit, static data of a logistics distribution environment and historical decision matching data from a logistics history database as historical logistics data, wherein the static data of the logistics distribution unit comprises geometric appearance and physical behaviors, and the logistics distribution environment data comprises road information and surrounding building influence information;
The delivery purpose and delivery attitude of the client are taken as client data, and the delivery attitude comprises the positive attitude, the neutral attitude and the negative attitude of the delivery personnel.
Preferably, performing data processing and fusion on the logistics data to obtain one-dimensional vector data includes:
Cleaning and interpolating the real-time collected logistics data, the client data and the historical logistics data to obtain processing data;
Extracting features from the processed data to obtain feature data;
Combining all the characteristic data and forming one-dimensional vector data, wherein the expression of the one-dimensional vector data vec is as follows:
vec＝[v,a,t,loc1,loc2,W,att1]
Where v is the speed of the logistics vehicle, a is the acceleration of the logistics vehicle, t is the ambient temperature of the logistics vehicle, loc 1 is the current position of the logistics vehicle, loc 2 is the delivery destination, W is the weight of the logistics vehicle, and att 1 is the delivery attitude.
Preferably, constructing a digital twin fleet logistics command decision model according to the real-time collected logistics data and the historical logistics data comprises:
constructing a model by adopting three-dimensional modeling software according to the historical logistics data to obtain a twin model integrated in the same scene;
Inputting the real-time acquisition logistics data into the twin model to obtain a digital twin model;
Inputting the one-dimensional vector data into the digital twin model, and constructing decision matching by adopting a random forest algorithm to obtain a digital twin command decision model of an output distribution destination;
And constructing the digital twin command decision model by adopting an improved dung beetle optimization algorithm by taking the current position of the vehicle as a starting point and the distribution destination as a path point or an end point, so as to obtain the digital twin motorcade logistics command decision model for outputting distribution path planning.
Preferably, the digital twin-based fleet logistics commanding decision modeling method comprises the following steps: and inputting the distribution path planning into the digital twin model to simulate the movement of the twin scene, and outputting a visual fleet logistics command decision result.
In still another aspect, a digital twinning-based vehicle team logistics commanding and decision modeling device is provided, which comprises a data acquisition module, a data processing module, a model construction module and a decision output module;
The data acquisition module is used for acquiring logistics data required by the logistics of the motorcade, wherein the logistics data comprises real-time acquisition logistics data, customer data and historical logistics data;
the data processing module is used for carrying out data processing and fusion on the logistics data to obtain one-dimensional vector data;
the model construction module is used for constructing a digital twin motorcade logistics command decision model according to the real-time collected logistics data and the historical logistics data;
The decision output module is used for inputting the one-dimensional vector data into the digital twin motorcade logistics command decision model and outputting a delivery destination; and inputting the current positions of the delivery destination and the vehicles for acquiring logistics data in real time into the digital twin vehicle team logistics command decision model together, and outputting a delivery path plan of the vehicle team logistics command decision.
Preferably, the data acquisition module is further used for acquiring the speed, the acceleration, the weight of the load, the current position and the environment temperature of the logistics vehicle in real time by adopting the detection element as real-time acquisition logistics data; taking a delivery destination and a delivery attitude of a client as client data, wherein the delivery attitude comprises an active attitude, a neutral attitude and a passive attitude of a delivery person; and acquiring static data of the logistics distribution unit, static data of the logistics distribution environment and historical decision matching data from the logistics history database as historical logistics data, wherein the static data of the logistics distribution unit comprises geometric appearance and physical behaviors, and the logistics distribution environment data comprises road information and surrounding building influence information.
Preferably, the data processing module comprises a processing sub-module, a feature extraction sub-module and a merging sub-module;
the processing sub-module is used for cleaning and interpolating the real-time collected logistics data, the client data and the historical logistics data to obtain processing data;
The feature extraction submodule is used for extracting features from the processing data to obtain feature data;
the merging submodule is used for merging all the characteristic data and forming one-dimensional vector data, and the expression of the one-dimensional vector data vec is as follows:
vec＝[v,a,t,loc1,loc2,W,att1]
Where v is the speed of the logistics vehicle, a is the acceleration of the logistics vehicle, t is the ambient temperature of the logistics vehicle, loc 1 is the current position of the logistics vehicle, loc 2 is the delivery destination, W is the weight of the logistics vehicle, and att 1 is the delivery attitude.
Preferably, the model building module comprises a first building sub-module, a second building sub-module, a third building sub-module and a fourth building sub-module;
The first construction submodule is used for constructing a model by adopting three-dimensional modeling software according to the historical logistics data to obtain a twin model integrated in the same scene;
The second construction submodule is used for inputting the real-time acquisition logistics data into the twin model to obtain a digital twin model;
The third construction submodule is used for inputting the one-dimensional vector data into the digital twin model, constructing decision matching by adopting a random forest algorithm, and obtaining a digital twin command decision model of an output distribution destination;
The fourth construction submodule is used for constructing the digital twin command decision model by adopting an improved dung beetle optimization algorithm with the current position of the vehicle as a starting point and the distribution destination as a path point or an end point to obtain the digital twin fleet logistics command decision model for outputting distribution path planning.
In yet another aspect, a terminal device is provided that includes a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
The processor is used for executing the digital twin-based motorcade logistics commanding and decision modeling device according to the instructions in the program codes.
The digital twinning-based vehicle team logistics commanding decision modeling method, device and equipment comprise the steps of obtaining logistics data required by vehicle team logistics, wherein the logistics data comprise real-time acquisition logistics data, client data and historical logistics data; carrying out data processing and fusion on the logistics data to obtain one-dimensional vector data; constructing a digital twin motorcade logistics command decision model according to real-time acquisition logistics data and historical logistics data; inputting the one-dimensional vector data into a logistics command decision model of the digital twin motorcade, and outputting a delivery destination; and (3) inputting the current positions of the vehicles with the delivery destinations and the real-time logistics data acquisition into a digital twin vehicle team logistics command decision model together, and outputting a delivery path plan of the vehicle team logistics command decision. From the above technical solutions, the embodiment of the present application has the following advantages: the digital twin-based motorcade logistics commanding decision modeling method is based on the collected logistics data; the method relieves the information island effect, improves the decision efficiency, realizes reliable decision deduction demonstration, and solves the technical problems that the existing command decision system has information island, slows down the data circulation process of each stage, has low decision efficiency and can not effectively make decision generation and deduction.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a flow chart of steps of a digital twin-based fleet logistics command decision modeling method according to an embodiment of the present application;
Fig. 2 is a schematic diagram of a digital twin vehicle team logistics command decision model in the digital twin vehicle team logistics command decision modeling method according to the embodiment of the present application;
Fig. 3 is a frame flow chart of a digital twin-based fleet logistics commanding and decision modeling device according to an embodiment of the present application.
Detailed Description
In order to make the objects, features and advantages of the present application more comprehensible, the technical solutions in the embodiments of the present application are described in detail below with reference to the accompanying drawings, and it is apparent that the embodiments described below are only some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the description of embodiments of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the embodiments of the present application, the meaning of "plurality" is two or more, unless explicitly defined otherwise.
In the embodiments of the present application, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured" and the like are to be construed broadly and include, for example, either permanently connected, removably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the embodiments of the present application will be understood by those of ordinary skill in the art according to specific circumstances.
In order to solve the problems that in the existing command decision, the decision result is inaccurate due to the lack of a dynamic simulation evaluation process, and the command instruction is difficult to adapt to the dynamic environment during logistics dispatch, and deviation occurs, the embodiment of the application provides a digital twin-based vehicle team logistics command decision modeling method, device and equipment, which lays a foundation for realizing the accurate logistics dispatch generation.
The digital twin vehicle team logistics command decision model of the whole process is built through the digital twin model logistics dispatching command decision system, and real-time logistics dispatching command decision command issuing is realized, so that the digital twin vehicle team logistics command decision modeling method, device and equipment need to realize the following functions: firstly, the data collection and storage function, the logistics command decision model of the digital twin motorcade needs to work normally, and the logistics dispatch decision instruction is issued normally, so that various data needs to be collected and stored for analysis. And secondly, the data processing and fusion function is used for processing the acquired data, ensuring the data integrity, converting the data into information which can be understood by a computer, and fusing the information into a one-dimensional vector for subsequent decision. And thirdly, a model construction function is needed to construct a twin model in a digital space, simulate the geometric appearance and physical behaviors of a vehicle team logistics distribution unit and a logistics distribution environment, and realize real-time data link so as to realize simulation driving. And fourthly, a decision matching and planning function learns the existing situation-decision data according to a digital twin vehicle team logistics command decision model to realize decision generation, and route planning is required to be carried out on a distribution destination after the decision is completed. Fifthly, a real-time simulation and instruction output function is adopted to construct a digital twin vehicle team logistics command decision model capable of realizing real-time simulation, and the situation is monitored in real time.
The embodiment of the application provides a digital twin-based vehicle team logistics command decision modeling method, device and equipment, which solve the technical problems that the existing command decision system has information islands, so that the data circulation process of each stage is slow, the decision efficiency is low, and effective decision generation and deduction cannot be performed.
Embodiment one:
Fig. 1 is a flow chart of steps of a digital twin-based fleet logistics commanding and decision-making modeling method according to an embodiment of the present application.
As shown in fig. 1, the embodiment of the application provides a digital twinning-based vehicle team logistics commanding decision modeling method, which comprises the following steps:
s1, acquiring logistics data required by a motorcade logistics, wherein the logistics data comprises real-time acquisition logistics data, customer data and historical logistics data.
It should be noted that, in step S1, the digital twin-based fleet logistics command decision modeling method obtains the logistics data required by the fleet logistics, the collected logistics data is generally structured data, and the logistics data stored in the current command decision system includes structured, semi-structured and unstructured data and is stored separately.
S2, carrying out data processing and fusion on the logistics data to obtain one-dimensional vector data.
In step S2, data analysis is performed on the collected logistics data, data features are extracted, customer data is analyzed to extract decision attitude, and data integration is performed to form one-dimensional vector data, so that a subsequent decision result is generated.
S3, constructing a digital twin motorcade logistics command decision model according to the real-time collected logistics data and the historical logistics data.
In step S3, the digital twin vehicle team logistics commanding and deciding model is constructed by adopting the real-time collected logistics data and the historical logistics data, and the digital twin vehicle team logistics commanding and deciding model can perform full life cycle simulation.
S4, inputting the one-dimensional vector data into a digital twin motorcade logistics command decision model, and outputting a delivery destination; and (3) inputting the current positions of the vehicles with the delivery destinations and the real-time logistics data acquisition into a digital twin vehicle team logistics command decision model together, and outputting a delivery path plan of the vehicle team logistics command decision.
In the step S4, the digital twin vehicle team logistics command decision model is obtained according to the step S3, the one-dimensional vector data is used as input, the distribution destination is output through the random forest decision algorithm of the digital twin vehicle team logistics command decision model, then the logistics data is collected in real time according to the distribution destination and is used as the input of the digital twin vehicle team logistics command decision model, and the distribution path planning of the vehicle team logistics command decision is output through the dung beetle optimization algorithm of the digital twin vehicle team logistics command decision model; and a random forest decision algorithm is performed in a decision model of the digital twin motorcade logistics command decision model according to a decision matching library. Wherein existing decision rules are presented in a "vector + result" form.
The application provides a digital twinning-based vehicle team logistics command decision modeling method, which comprises the steps of obtaining logistics data required by vehicle team logistics, wherein the logistics data comprises real-time acquisition logistics data, client data and historical logistics data; carrying out data processing and fusion on the logistics data to obtain one-dimensional vector data; constructing a digital twin motorcade logistics command decision model according to real-time acquisition logistics data and historical logistics data; inputting the one-dimensional vector data into a logistics command decision model of the digital twin motorcade, and outputting a delivery destination; and (3) inputting the current positions of the vehicles with the delivery destinations and the real-time logistics data acquisition into a digital twin vehicle team logistics command decision model together, and outputting a delivery path plan of the vehicle team logistics command decision. The digital twin-based motorcade logistics commanding decision modeling method is based on the collected logistics data; the method relieves the information island effect, improves the decision efficiency, realizes reliable decision deduction demonstration, and solves the technical problems that the existing command decision system has information island, slows down the data circulation process of each stage, has low decision efficiency and can not effectively make decision generation and deduction.
In one embodiment of the application, obtaining logistics data required for a fleet logistics includes:
The method comprises the steps that a detection element is adopted to collect the speed, acceleration, weight bearing, current position and environment temperature of a logistics vehicle in real time as real-time logistics data;
Obtaining static data of a logistics distribution unit, static data of a logistics distribution environment and historical decision matching data from a logistics history database as historical logistics data, wherein the static data of the logistics distribution unit comprises geometric appearance and physical behaviors, and the logistics distribution environment data comprises road information and surrounding building influence information;
Taking the delivery purpose and delivery attitude of the client as client data, wherein the delivery attitude comprises the positive attitude, the neutral attitude and the negative attitude of the delivery personnel.
It should be noted that, the real-time collection of the logistics data is performed by adopting different types of sensors, and the real-time collection of the logistics data mainly includes: the speed of the logistics vehicle, the acceleration of the logistics vehicle, the weight of the logistics vehicle, the geographic position information (such as the current position) of the logistics vehicle, the ambient temperature and the like. The customer data may be text entered for the customer, including the purpose of delivery and the attitude of delivery. And acquiring static data of the logistics distribution unit, static data of the logistics distribution environment and historical decision matching data from a historical database of the conventional decision command system, wherein the static data of the logistics distribution unit comprise geometric appearance and physical behaviors, and the logistics distribution environment data mainly comprise data such as road information and surrounding building influence information. In this embodiment, the model may be input through a data input interface during the process of constructing the digital twin fleet logistics command decision model. The digital twin-based motorcade logistics commanding and decision modeling method is used for extracting characteristics of customer data by adopting a text emotion extraction algorithm (such as a natural language processing algorithm such as Bi-lstm, transformer and the like), and extracting corresponding attitudes. If the text information input by the customer is the request for normal delivery/(no language information), the delivery attitude is a neutral attitude; if the client inputs text information to request delayed dispatch, the distribution attitude is a negative attitude; if the text information input by the client is important and the progress is quickened, the distribution attitude is an active attitude.
In one embodiment of the present application, performing data processing and fusion on the logistics data to obtain one-dimensional vector data includes:
Cleaning and interpolating the real-time collected logistics data, client data and historical logistics data to obtain processed data;
Extracting features from the processed data to obtain feature data;
Combining all the characteristic data and forming one-dimensional vector data, and expressing a one-dimensional vector data vec:
vec＝[v,a,t,loc1,loc2,W,att1]
Where v is the speed of the logistics vehicle, a is the acceleration of the logistics vehicle, t is the ambient temperature of the logistics vehicle, loc 1 is the current position of the logistics vehicle, loc 2 is the delivery destination, W is the weight of the logistics vehicle, and att 1 is the delivery attitude.
The digital twin-based vehicle team logistics commanding and decision modeling method is used for cleaning data of real-time collected logistics data, wherein the cleaning content comprises the steps of deleting repeated redundant information by adopting a data detection algorithm and deleting abnormal data information of a sensor by adopting a data clustering algorithm, so that data consistency is kept. The digital twin-based motorcade logistics commanding decision modeling method carries out data interpolation on real-time acquisition logistics data, enriches discrete data information and keeps data integrity. The digital twin-based vehicle team logistics commanding and decision modeling method integrates historical logistics data and displays the historical logistics data in a vector+result mode.
In one embodiment of the application, constructing a digital twin fleet logistics command decision model from real-time acquisition logistics data and historical logistics data comprises:
constructing a model by adopting three-dimensional modeling software according to the historical logistics data to obtain a twin model integrated in the same scene;
Inputting the real-time acquisition logistics data into a twin model to obtain a digital twin model;
Inputting the one-dimensional vector data into a digital twin model, and constructing decision matching by adopting a random forest algorithm to obtain a digital twin command decision model of an output distribution destination;
And constructing a digital twin command decision model by taking the current position of the vehicle as a starting point and a delivery destination as a route point or an end point and adopting an improved dung beetle optimization algorithm to obtain the digital twin motorcade logistics command decision model for outputting the delivery path planning.
In an embodiment of the present application, obtaining the content of the twin model of the same scene integration includes:
Constructing a logistics dispatching geometric model by adopting three-dimensional visualization software according to the geometric appearance of static data of the logistics dispatching unit;
adding physical behaviors on the basis of the logistics distribution geometric model, and constructing a logistics distribution model with distribution operation behaviors;
Constructing a dispatching environment model by adopting three-dimensional modeling software according to road information of logistics dispatching environment data and surrounding building influence information;
And setting the logistics distribution model and the distribution environment model in the same scene for integration to obtain the twin model.
It should be noted that, the movement behavior of the logistics distribution model includes aspects of movement direction, movement speed, movement acceleration and the like of the fleet logistics distribution unit, and the digital twinning-based fleet logistics command decision modeling method can verify whether the movement direction accords with the actual movement unit through the logistics distribution model, and whether the movement speed and the movement acceleration of the movement unit accord with the actual movement logic and the actual movement performance. In this embodiment, three-dimensional visualization software such as units and UE4 may be selected to construct a geometric logistics distribution model according to the geometric appearance of static data of the logistics distribution unit, and then a kinematic model such as carsim, ADAMS, cruise is adopted to construct a logistics distribution model with distribution operation behaviors according to the physical behaviors of static data of the logistics distribution unit. And three-dimensional modeling software such as units, UE4 and the like can be selected to construct and send an environment model according to road information and surrounding building influence information of logistics distribution environment data. The twin model constructed by the digital twin-based motorcade logistics commanding decision modeling method realizes the construction of the physical dispatching static scene, and can verify the physical dispatching movement performance.
In the embodiment of the application, the real-time acquisition logistics data is input into the twin model through the data interface to obtain the digital twin model capable of being simulated in real time, and the digital twin model can realize the dynamic scene simulation of logistics dispatch. And the command decision of the real-time logistics condition can be realized in the digital twin model.
The digital twin-based vehicle team logistics commanding and decision-making modeling method realizes the static scene construction of logistics through a twin model, and realizes dynamic and static combination by adding real-time collected logistics data based on the twin model, thus obtaining a digital twin model capable of dynamic simulation.
In the embodiment of the application, in the process of constructing the digital twin command decision model, a random forest algorithm and historical decision matching data can be adopted to carry out decision matching construction according to one-dimensional vector data.
The method is characterized in that random forest training is carried out according to one-dimensional vector data, and a digital twin command decision model of an output distribution destination is obtained. In this embodiment, the random forest algorithm is composed of decision tree algorithms, and high-dimensional feature classification can be effectively achieved by using the idea of ensemble learning. And obtaining historical decision matching data from the logistics historical database to perform random forest model training. In the actual vehicle team logistics dispatching process, real-time acquisition logistics data of logistics dispatching are received through a digital twin model, the command is updated every thirty seconds, and the real-time command decision command is generated by utilizing the trained digital twin command decision model to obtain a dispatching destination. The matching criterion form of the historical decision matching data consists of one-dimensional situation vectors and distribution destinations, and one or more destinations can be formed. For decision instruction generation, a trained random forest model is used for commanding decision output delivery destinations in real time.
In the embodiment of the application, in the construction of a digital twin motorcade logistics command decision model, for global logistics dispatching path planning, the current position of a vehicle is taken as a starting point, a dispatching destination is taken as a path point or an end point, and an improved dung beetle optimization is adopted to plan a global logistics dispatching path. The method comprises the steps of planning a path of a moving entity according to an improved dung beetle optimization algorithm and a digital twin command decision model to obtain a moving path, wherein the specific improvement is that an initial chaotic mapping process and a dung beetle mutation process are added, and the situation that a local optimal solution is trapped is avoided.
It should be noted that, the dung beetle optimizing algorithm is an intelligent optimizing algorithm, which imitates the foraging habit of the dung beetles in the nature, improves the position updating process, and can obtain an optimal path faster in logistics distribution. However, the initial solution distribution is uneven, and population variation is performed in the optimizing stage, so that the problem of sinking into a local optimal solution is avoided.
In the embodiment of the application, the digital twin motorcade logistics command decision model adopts a dung beetle optimization algorithm to output the contents of the distribution path plan, which comprises the following steps:
Obtaining logistics distribution scene parameters, and setting a fitness function according to the logistics distribution scene parameters, wherein the logistics distribution scene parameters comprise distribution distance, route corner and load degree; the fitness function is: j cost＝w1*Jpath+w2*Jsmooth+w3*Jweight, wherein J path is a delivery distance, J smooth is a route corner, J weight is a loading degree, and w i is a weight coefficient of a corresponding parameter;
Setting iteration parameters, wherein the iteration parameters comprise the maximum iteration times, the number of independent variables of an objective function and the maximum population number, and carrying out population initialization by improving chaotic sane mapping according to the iteration parameters to obtain an initialization result; the initialization expression is: d i+1＝sin(μπdi),ei+1＝sin(μπei),wi+1＝(di+1+ei+1) mod1, wherein d i and e i represent randomly allocated populations, w i+1 is the final mapping result, i is the ith dung beetle, and μ is a control parameter;
according to the initialization result, iteratively calculating the fitness of each population by updating the position of the dung beetles, and screening to obtain the optimal fitness; and obtaining a rough distribution path according to the optimal fitness, and processing the rough distribution path by adopting Spine interpolation, natural adjacent point interpolation or Lagrange interpolation to obtain a fine distribution path plan. Fitness is a series of vectors representing position coordinates.
The initialization result is a random allocation dung beetle position, which is composed of a starting position, a distribution destination to be passed and other generated random positions. The optimal fitness is the fitness with the smallest value selected from the fitness of each population.
In the embodiment of the application, the behavior of the dung beetles comprises rolling, dancing, breeding and stealing, and in the rolling process, the updating mode expression of the dung beetles is as follows: x i(t+1)＝xi(t)+α×k×xi(t-1)+b×Δx,Δx＝|xi(t)-xw is the number of iterations, wherein t is the current iteration number, x i (t) is the position information of the ith dung beetle in the t iteration, k is a constant (0,0.2), the constant represents a deflection coefficient, b is a constant belonging to (0, 1), and is a natural coefficient, and the value is-1 or 1, x w is the global worst position;
If the dung beetles roll to touch the obstacle, dancing to obtain a new route; in order to simulate dance behaviors, a tangential function is utilized to obtain a new rolling direction, the interval is [0, pi ], and an updating formula of the dung beetle position is as follows: x i(t+1)＝xi(t)+α×k×xi (t-1) +bx.DELTA.x. In the updating formula of the dung beetle position, whether the dung beetle performs rolling behavior or dancing behavior is confirmed through a random value.
In the breeding process, a boundary selection strategy is applied to simulate the spawning area of female insects, wherein the position of dung beetles is defined as ：Lb*＝max(X*×(1-R),Lb),Ub*＝max(X*×(1-R),Ub),Bi(t+1)＝X*+b1×(Bi(t)-Lb*)+b2×(Bi(t)-Ub*),, X * is the current local optimal position, lb * and Ub * are the lower bound and the upper bound of the spawning area respectively, B i (t) is the position of the ith hatched fecal ball in the t-th iteration, B 1 and B 2 are two independent random vectors with the sizes of 1 xD respectively, and D is the dimension of the optimization problem, so that the position of the hatched fecal ball is strictly limited within a certain range, namely offspring moves within a certain range;
Defining a child foraging strategy as ：Lbb＝max(Xb×(1-R),Lb),Ubb＝max(Xb×(1-R),Ub),xi(t+1)＝X*+C1×(Bi(t)-Lbb)+C2×(Bi(t)-Ubb), after the child hatching is successful, wherein Lb b and Ub b are respectively the lower bound and the upper bound of a foraging area, X i (t) is the position of the ith child in the t-th iteration, C 1 is a random number following normal distribution, and C 2 is a random vector;
Meanwhile, the method simulates the theft behavior of the dung beetles, iterates and updates the overall optimal position of logistics dispatching, and the updating mode expression of the dung beetles is as follows: x i(t+1)＝Xb+S×g×(|xi(t)-X*|+|xi(t)-X* |), where X i (t) is the i-th thief's location at the t-th iteration and X b is the current optimal location.
In the embodiment of the application, new feasible solutions are continuously generated around the current optimal solution by simulating the life habit of the dung beetles in the process of iteratively calculating the fitness of the population by updating the positions of the dung beetles. However, as the number of iterations increases, the diversity of the population gradually decreases, and the algorithm is also prone to falling into local optima. In order to solve the problem, the digital twin-based motorcade logistics commanding decision modeling method introduces a cauchy-differential variation strategy, introduces a variation factor to a position update formula of a joiner, performs position update after rolling, dancing, propagation and theft stages are completed respectively, avoids the population to be in local optimum, and performs iterative calculation on the fitness of the population by updating the position of dung beetles as follows: u best＝Xbest[1+(Xbest(t)/Xi (t)) Gauss (0, 1), where U best is the updated optimal position (highest fitness population), X best is the current optimal position (currently calculated population fitness), t is the number of iterations, i is the ith dung beetle, and Gauss (0, 1) is (0, 1) Gaussian noise.
In the embodiment of the application, the digital twin-based vehicle team logistics command decision modeling method is constructed one by one through the twin model, the digital twin command decision model and the digital twin vehicle team logistics command decision model, so that the digital twin vehicle team logistics command decision model can build real-time connection between a physical entity and a virtual entity through the acquired motion unit, the client data and the real-time acquisition logistics data, the twin entity can map the physical entity behavior in real time, the digital description of command decisions can be effectively, comprehensively and accurately realized, and the trust of the follow-up logistics simulation deduction is enhanced. The digital twin-based motorcade logistics command decision modeling method can combine the related logistics distribution decision planning algorithm for acquiring logistics data and historical decision matching data in a logistics historical library in real time, update the decision library in real time, optimize a decision model, fully utilize various data information and obtain dynamic command decision instruction generation according to distribution path planning, and realize intelligent distribution decision result generation; and a digital twin system integrating data extraction, situation awareness and decision planning can be established, so that the information island effect is relieved, the decision efficiency is improved, and reliable decision deduction demonstration is realized.
Fig. 2 is a schematic diagram of a digital twin vehicle team logistics command decision model in the digital twin vehicle team logistics command decision modeling method according to the embodiment of the application.
In the embodiment of the application, as shown in fig. 2, the digital twin vehicle team logistics command decision model constructed based on the digital twin vehicle team logistics command decision modeling method comprises a physical layer, a data layer, a functional layer and a service layer;
The physical layer is an actual operation system consisting of customer data, a logistics distribution environment and a logistics distribution unit;
the data layer comprises real-time acquisition logistics data and historical logistics data;
The function layer comprises a data function and an algorithm function, wherein the data function comprises the functions of data transmission, data fusion, data cleaning, data storage, data interpolation and the like; the algorithm function comprises voice emotion analysis, multi-parameter optimization, decision generation, path planning and other algorithms;
The twin layer is composed of a front logistics distribution movement unit and a logistics distribution environment, a digital twin model for commanding and deciding static state is constructed, and visual output is carried out by utilizing real-time data driving.
In one embodiment of the application, the digital twin-based fleet logistics command decision modeling method comprises the following steps: and inputting the distribution path planning into a digital twin model to perform motion simulation of a twin scene, and outputting a visual fleet logistics command decision result.
Embodiment two:
Fig. 3 is a frame flow chart of a digital twin-based fleet logistics commanding and decision modeling device according to an embodiment of the present application.
As shown in fig. 3, the embodiment of the application provides a digital twin-based vehicle team logistics commanding and decision modeling device, which comprises a data acquisition module 10, a data processing module 20, a model construction module 30 and a decision output module 40;
the data acquisition module 10 is used for acquiring logistics data required by the logistics of the motorcade, wherein the logistics data comprises real-time acquisition logistics data, customer data and historical logistics data;
The data processing module 20 is used for performing data processing and fusion on the logistics data to obtain one-dimensional vector data;
The model construction module 30 is used for constructing a digital twin motorcade logistics command decision model according to the real-time collected logistics data and the historical logistics data;
The decision output module 40 is used for inputting the one-dimensional vector data into the digital twin fleet logistics command decision model and outputting a delivery destination; and (3) inputting the current positions of the vehicles with the delivery destinations and the real-time logistics data acquisition into a digital twin vehicle team logistics command decision model together, and outputting a delivery path plan of the vehicle team logistics command decision.
In the embodiment of the present application, the data acquisition module 10 is further configured to acquire, in real time, the speed, the acceleration, the weight, the current location and the ambient temperature of the logistics vehicle by using the detection element as real-time data acquisition; taking a delivery destination and a delivery attitude of a client as client data, wherein the delivery attitude comprises an active attitude, a neutral attitude and a negative attitude of a delivery person; and acquiring static data of the logistics distribution unit, static data of the logistics distribution environment and historical decision matching data from the logistics history database as historical logistics data, wherein the static data of the logistics distribution unit comprises geometric appearance and physical behaviors, and the logistics distribution environment data comprises road information and surrounding building influence information.
In the embodiment of the present application, the data processing module 20 includes a processing sub-module, a feature extraction sub-module, and a merging sub-module;
the processing sub-module is used for cleaning and interpolating the real-time collected logistics data, the client data and the historical logistics data to obtain processing data;
The feature extraction sub-module is used for extracting features from the processed data to obtain feature data;
The merging sub-module is used for merging all the characteristic data and forming one-dimensional vector data, and the expression of the one-dimensional vector data vec is as follows:
vec＝[v,a,t,loc1,loc2,W,att1]
Where v is the speed of the logistics vehicle, a is the acceleration of the logistics vehicle, t is the ambient temperature of the logistics vehicle, loc 1 is the current position of the logistics vehicle, loc 2 is the delivery destination, W is the weight of the logistics vehicle, and att 1 is the delivery attitude.
In an embodiment of the present application, model building block 30 includes a first building sub-block, a second building sub-block, a third building sub-block, and a fourth building sub-block;
The first construction submodule is used for constructing a model by adopting three-dimensional modeling software according to historical logistics data to obtain a twin model integrated in the same scene;
the second construction submodule is used for inputting real-time acquisition logistics data into the twin model to obtain a digital twin model;
The third construction submodule is used for inputting the one-dimensional vector data into the digital twin model, constructing decision matching by adopting a random forest algorithm, and obtaining a digital twin command decision model of an output distribution destination;
And the fourth construction submodule is used for constructing the digital twin command decision model by adopting an improved dung beetle optimization algorithm with the current position of the vehicle as a starting point and the distribution destination as a path point or an end point to obtain the digital twin motorcade logistics command decision model for outputting the distribution path planning.
It should be noted that, the content of the module of the apparatus in the second embodiment corresponds to the content of the steps of the method in the first embodiment, and the content of the steps of the digital twin-based vehicle team logistics commanding decision modeling method has been described in the first embodiment, and the content of the module in the digital twin-based vehicle team logistics commanding decision modeling apparatus is not described in detail in this embodiment.
Embodiment III:
the embodiment of the application provides terminal equipment, which comprises a processor and a memory;
A memory for storing program code and transmitting the program code to the processor;
and the processor is used for executing the digital twin-based motorcade logistics commanding and decision modeling device according to the instructions in the program codes.
It should be noted that the processor is configured to execute the steps in the above-mentioned embodiment of the digital twin-based motorcade logistics commanding and decision modeling method according to the instructions in the program code. Or the processor, when executing the computer program, performs the functions of the modules/units in the system/device embodiments described above.
For example, a computer program may be split into one or more modules/units, which are stored in a memory and executed by a processor to perform the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in the terminal device.
The terminal device may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The terminal device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the terminal device is not limited and may include more or less components than those illustrated, or may be combined with certain components, or different components, e.g., the terminal device may also include input and output devices, network access devices, buses, etc.
The Processor may be a central processing unit (Centrdl Processing Unit, CPU), other general purpose Processor, digital signal Processor (DIGITDL SIGNDL Processor, DSP), application specific integrated Circuit (dpplicdtion SPECIFIC INTEGRDTED Circuit, dSIC), off-the-shelf programmable gate array (Field-Progrdmmdble GDTE DRRDY, FPGd) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may be an internal storage unit of the terminal device, such as a hard disk or a memory of the terminal device. The memory may also be an external storage device of the terminal device, such as a plug-in hard disk provided on the terminal device, a smart memory card (SMDRT MEDID CDRD, SMC), a secure digital (Secure Digitdl, SD) card, a flash memory card (FLDSH CDRD), etc. Further, the memory may also include both an internal storage unit of the terminal device and an external storage device. The memory is used for storing computer programs and other programs and data required by the terminal device. The memory may also be used to temporarily store data that has been output or is to be output.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a read-Only Memory (ROM), a random access Memory (RdM, rdndom dccess Memory), a magnetic disk, or an optical disk, or the like, which can store program codes.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (6)
1. The digital twinning-based motorcade logistics commanding decision modeling method is characterized by comprising the following steps of:
Acquiring logistics data required by a fleet logistics, wherein the logistics data comprises real-time acquisition logistics data, customer data and historical logistics data;
Carrying out data processing and fusion on the logistics data to obtain one-dimensional vector data;
constructing a digital twin motorcade logistics command decision model according to the real-time collected logistics data and the historical logistics data;
inputting the one-dimensional vector data into the digital twin motorcade logistics command decision model, and outputting a delivery destination; the distribution destination and the current position of the vehicle for acquiring logistics data in real time are input into the digital twin vehicle team logistics command decision model together, and a distribution path plan of a vehicle team logistics command decision is output;
The acquiring logistics data required by the motorcade logistics comprises the following steps:
The method comprises the steps that a detection element is adopted to collect the speed, acceleration, weight bearing, current position and environment temperature of a logistics vehicle in real time as real-time logistics data;
Obtaining static data of a logistics distribution unit, static data of a logistics distribution environment and historical decision matching data from a logistics history database as historical logistics data, wherein the static data of the logistics distribution unit comprises geometric appearance and physical behaviors, and the logistics distribution environment data comprises road information and surrounding building influence information;
Taking the delivery purpose and delivery attitude of a client as client data, wherein the delivery attitude comprises the positive attitude, the neutral attitude and the negative attitude of a delivery person;
The step of constructing a digital twin motorcade logistics command decision model according to the real-time collected logistics data and the historical logistics data comprises the following steps:
constructing a model by adopting three-dimensional modeling software according to the historical logistics data to obtain a twin model integrated in the same scene;
Inputting the real-time acquisition logistics data into the twin model to obtain a digital twin model;
Inputting the one-dimensional vector data into the digital twin model, and constructing decision matching by adopting a random forest algorithm to obtain a digital twin command decision model of an output distribution destination;
Taking the current position of the vehicle as a starting point and the distribution destination as a path point or an end point, and constructing the digital twin command decision model by adopting an improved dung beetle optimization algorithm to obtain a digital twin motorcade logistics command decision model for outputting distribution path planning;
The improved content of the improved dung beetle optimizing algorithm comprises population initialization through improved chaotic sane mapping according to iteration parameters, and an initialization result is obtained; according to the initialization result, iteratively calculating the fitness of each population by updating the position of the dung beetles, and screening to obtain the optimal fitness;
The initialization expression is: ，/>， in the above, the ratio of/> And/>Are randomly distributed populations of ith dung beetle,/>For the final mapping result, i is the i-th dung beetle, and/>Is a control parameter;
The expression for iteratively calculating the fitness of the population by updating the position of the dung beetle is as follows: Wherein U best is the updated optimal position, X best is the current optimal position,/> Is the position of the ith filial generation at the t-th iteration, t is the iteration number, gauss (0, 1) is (0, 1) Gaussian noise,/>Is a mutation factor.
2. The digital twinning-based fleet logistics command decision modeling method of claim 1, wherein the performing data processing and fusion on the logistics data to obtain one-dimensional vector data comprises:
Cleaning and interpolating the real-time collected logistics data, the client data and the historical logistics data to obtain processing data;
Extracting features from the processed data to obtain feature data;
Combining all the characteristic data and forming one-dimensional vector data, wherein the expression of the one-dimensional vector data vec is as follows:
；
Where v is the speed of the logistics vehicle, a is the acceleration of the logistics vehicle, t is the ambient temperature of the logistics vehicle, loc 1 is the current position of the logistics vehicle, loc 2 is the delivery destination, W is the weight of the logistics vehicle, and att 1 is the delivery attitude.
3. The digital twinning-based fleet logistics command decision modeling method of claim 1, comprising: and inputting the distribution path planning into the digital twin model to simulate the movement of the twin scene, and outputting a visual fleet logistics command decision result.
4. The digital twinning-based motorcade logistics commanding and decision modeling device is characterized by comprising a data acquisition module, a data processing module, a model construction module and a decision output module;
The data acquisition module is used for acquiring logistics data required by the logistics of the motorcade, wherein the logistics data comprises real-time acquisition logistics data, customer data and historical logistics data;
the data processing module is used for carrying out data processing and fusion on the logistics data to obtain one-dimensional vector data;
the model construction module is used for constructing a digital twin motorcade logistics command decision model according to the real-time collected logistics data and the historical logistics data;
The decision output module is used for inputting the one-dimensional vector data into the digital twin motorcade logistics command decision model and outputting a delivery destination; the distribution destination and the current position of the vehicle for acquiring logistics data in real time are input into the digital twin vehicle team logistics command decision model together, and a distribution path plan of a vehicle team logistics command decision is output;
The data acquisition module is also used for acquiring the speed, the acceleration, the weight of the load, the current position and the environment temperature of the logistics vehicle in real time by adopting the detection element as real-time logistics data; taking a delivery destination and a delivery attitude of a client as client data, wherein the delivery attitude comprises an active attitude, a neutral attitude and a passive attitude of a delivery person; obtaining static data of a logistics distribution unit, static data of a logistics distribution environment and historical decision matching data from a logistics history database as historical logistics data, wherein the static data of the logistics distribution unit comprises geometric appearance and physical behaviors, and the logistics distribution environment data comprises road information and surrounding building influence information;
the model building module comprises a first building sub-module, a second building sub-module, a third building sub-module and a fourth building sub-module:
The first construction submodule is used for constructing a model by adopting three-dimensional modeling software according to the historical logistics data to obtain a twin model integrated in the same scene;
The second construction submodule is used for inputting the real-time acquisition logistics data into the twin model to obtain a digital twin model;
The third construction submodule is used for inputting the one-dimensional vector data into the digital twin model, constructing decision matching by adopting a random forest algorithm, and obtaining a digital twin command decision model of an output distribution destination;
The fourth construction submodule is used for constructing the digital twin command decision model by adopting an improved dung beetle optimization algorithm with the current position of the vehicle as a starting point and the distribution destination as a path point or an end point to obtain a digital twin motorcade logistics command decision model for outputting distribution path planning;
The improved content of the improved dung beetle optimizing algorithm comprises population initialization through improved chaotic sane mapping according to iteration parameters, and an initialization result is obtained; according to the initialization result, iteratively calculating the fitness of each population by updating the position of the dung beetles, and screening to obtain the optimal fitness;
The initialization expression is: ，/>， in the above, the ratio of/> And/>Are randomly distributed populations of ith dung beetle,/>For the final mapping result, i is the i-th dung beetle, and/>Is a control parameter;
The expression for iteratively calculating the fitness of the population by updating the position of the dung beetle is as follows: Wherein U best is the updated optimal position, X best is the current optimal position,/> Is the position of the ith filial generation at the t-th iteration, t is the iteration number, gauss (0, 1) is (0, 1) Gaussian noise,/>Is a mutation factor.
5. The digital twinning-based fleet logistics command decision modeling apparatus of claim 4, wherein the data processing module comprises a processing sub-module, a feature extraction sub-module, and a merging sub-module;
the processing sub-module is used for cleaning and interpolating the real-time collected logistics data, the client data and the historical logistics data to obtain processing data;
The feature extraction submodule is used for extracting features from the processing data to obtain feature data;
the merging submodule is used for merging all the characteristic data and forming one-dimensional vector data, and the expression of the one-dimensional vector data vec is as follows:
；
Where v is the speed of the logistics vehicle, a is the acceleration of the logistics vehicle, t is the ambient temperature of the logistics vehicle, loc 1 is the current position of the logistics vehicle, loc 2 is the delivery destination, W is the weight of the logistics vehicle, and att 1 is the delivery attitude.
6. A terminal device comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the digital twin-based fleet flow command decision modeling method according to the instructions in the program code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311517261.6A CN117522234B (en) | 2023-11-14 | 2023-11-14 | Digital twinning-based vehicle team logistics commanding decision modeling method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311517261.6A CN117522234B (en) | 2023-11-14 | 2023-11-14 | Digital twinning-based vehicle team logistics commanding decision modeling method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117522234A CN117522234A (en) | 2024-02-06 |
| CN117522234B true CN117522234B (en) | 2024-06-18 |
Family
ID=89763912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311517261.6A Active CN117522234B (en) | 2023-11-14 | 2023-11-14 | Digital twinning-based vehicle team logistics commanding decision modeling method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117522234B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210287459A1 (en) * | 2018-09-30 | 2021-09-16 | Strong Force Intellectual Capital, Llc | Digital twin systems and methods for transportation systems |
| US11486722B2 (en) * | 2020-04-21 | 2022-11-01 | Toyota Motor Engineering & Manufacturing North America, Inc. | Vehicular edge server switching mechanism based on historical data and digital twin simulations |
| JP2023524250A (en) * | 2020-04-28 | 2023-06-09 | ストロング フォース ティーピー ポートフォリオ ２０２２，エルエルシー | Digital twin systems and methods for transportation systems |
| CN111539583B (en) * | 2020-05-13 | 2023-10-24 | 中国电子科技集团公司第十四研究所 | Production process simulation optimization method based on digital twin |
| CN113954870B (en) * | 2021-10-26 | 2023-03-03 | 海南大学 | Automatic driving vehicle behavior decision optimization system based on digital twinning technology |
| CN115310936B (en) * | 2022-08-09 | 2024-02-20 | 盟立自动化科技(上海)有限公司 | Intelligent logistics factory visualization and data service technical system based on digital twinning |
| CN115511412A (en) * | 2022-09-28 | 2022-12-23 | 河南科技大学 | Intelligent unmanned vehicle distribution system and method based on digital twins |
| CN116108717B (en) * | 2023-01-17 | 2023-09-26 | 中山大学 | Traffic transportation equipment operation prediction method and device based on digital twin |
-
2023
- 2023-11-14 CN CN202311517261.6A patent/CN117522234B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| Multi AGV simulation system of intelligent workshop based on Digital Twin;Sheng Wang等;《IEEE》;20211231;第325-329页 * |
| 基于数字孪生的决策***建模综述;熊宇涵等;《工业技术创新》;20230430;第10卷(第2期);第1-9页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117522234A (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mousavi et al. | Traffic light control using deep policy‐gradient and value‐function‐based reinforcement learning | |
| US20210150372A1 (en) | Training method and system for decision tree model, storage medium, and prediction method | |
| Wulfmeier et al. | Large-scale cost function learning for path planning using deep inverse reinforcement learning | |
| Powell | Perspectives of approximate dynamic programming | |
| Zhang et al. | Synergistic integration between machine learning and agent-based modeling: A multidisciplinary review | |
| CN108509820B (en) | Obstacle segmentation method and device, computer equipment and readable medium | |
| US20210174209A1 (en) | Neural network obtaining method and related device | |
| Kala et al. | Dynamic environment robot path planning using hierarchical evolutionary algorithms | |
| Demetriou et al. | A spatial genetic algorithm for automating land partitioning | |
| US11763191B2 (en) | Virtual intelligence and optimization through multi-source, real-time, and context-aware real-world data | |
| CN111340190A (en) | Method and device for constructing network structure, and image generation method and device | |
| US20220036232A1 (en) | Technology for optimizing artificial intelligence pipelines | |
| CN114261400A (en) | Automatic driving decision-making method, device, equipment and storage medium | |
| Puente-Castro et al. | Q-learning based system for path planning with unmanned aerial vehicles swarms in obstacle environments | |
| CN115631008A (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and commodity recommendation medium | |
| CN117522234B (en) | Digital twinning-based vehicle team logistics commanding decision modeling method, device and equipment | |
| CN117518907A (en) | Control method, device, equipment and storage medium of intelligent agent | |
| WO2023140044A1 (en) | Model generation method, model generation device, inference program, and inference device | |
| Chen et al. | Enabling deep reinforcement learning autonomous driving by 3D-LiDAR point clouds | |
| CN115981302A (en) | Vehicle following lane change behavior decision-making method and device and electronic equipment | |
| CN112820111B (en) | Abnormal vehicle identification method and device and electronic equipment | |
| CN113822293A (en) | Model processing method, device and equipment for graph data and storage medium | |
| Kumar et al. | Traffic Length Data Based Signal Timing Calculation for Road Traffic Signals Employing Proportionality Machine Learning | |
| Dubenko et al. | Multi-Agent Reinforcement Learning for Robot Collaboration | |
| Moussa et al. | Real-time path planning with virtual magnetic fields |
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 |