CN112070309A - Intelligent milk collecting platform - Google Patents

Intelligent milk collecting platform Download PDF

Info

Publication number
CN112070309A
CN112070309A CN202010947666.3A CN202010947666A CN112070309A CN 112070309 A CN112070309 A CN 112070309A CN 202010947666 A CN202010947666 A CN 202010947666A CN 112070309 A CN112070309 A CN 112070309A
Authority
CN
China
Prior art keywords
milk
milk receiving
receiving point
tank car
weight
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
Application number
CN202010947666.3A
Other languages
Chinese (zh)
Other versions
CN112070309B (en
Inventor
刘韬
朱晖
谈文蓉
谭颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southwest Minzu University
Original Assignee
Southwest Minzu University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southwest Minzu University filed Critical Southwest Minzu University
Priority to CN202010947666.3A priority Critical patent/CN112070309B/en
Publication of CN112070309A publication Critical patent/CN112070309A/en
Application granted granted Critical
Publication of CN112070309B publication Critical patent/CN112070309B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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
    • G06Q10/0835—Relationships between shipper or supplier and carriers
    • G06Q10/08355—Routing methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Biophysics (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Development Economics (AREA)
  • Evolutionary Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Physiology (AREA)
  • Evolutionary Computation (AREA)
  • Game Theory and Decision Science (AREA)
  • Molecular Biology (AREA)
  • Genetics & Genomics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Agronomy & Crop Science (AREA)
  • Animal Husbandry (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Primary Health Care (AREA)

Abstract

The invention discloses an intelligent milk collecting platform, which is characterized in that the optimal running route of a milk tank car is calculated through a genetic algorithm based on the distance between a milk collecting point and a processing factory, the milk collecting amount of the milk collecting point and the gradient of the milk collecting point, so that the running route of the milk tank car is more scientific and reasonable, data are collected through a milk collecting point data collecting module, a milk collecting relay transmission module transmits data, and a cloud service module stores data to realize intelligent milk collection and improve the milk collecting efficiency.

Description

Intelligent milk collecting platform
Technical Field
The invention relates to the technical field of milk collecting equipment, in particular to an intelligent milk collecting platform.
Background
With the development of the dairy industry, the number of farms and farmers is increasing, and hundreds of milk collection points are scattered in one area. The herdsman sends the collected milk to a milk receiving point and then sends the milk to a milk processing factory by a special milk tank truck. In the process of collecting fresh milk, transportation routes of milk tank cars to all milk collection points are generally arranged by managers according to self experiences, the problem of ramps of the transportation routes is not considered, particularly, in the plateau shape, the gradient difference of each transportation route is large, the influence of different gradients on the energy consumption of milk collection vehicles is large, the phenomena of transportation route repetition, detour, partial vehicle idling, partial vehicle overload, long running distance of the milk tank cars, insufficient utilization of the milk tank cars and the like can occur inevitably, and the phenomena of manpower, financial resources and material resources are extremely wasted.
Disclosure of Invention
The invention aims to solve the technical problem that in the process of collecting fresh milk, transportation routes of a milk tank car to all milk collecting points are generally arranged by managers according to own experiences, and the scientificity and the rationality are lacked. The invention provides an intelligent milk collecting platform, which is characterized in that the optimal running route of a milk tank car is calculated through a genetic algorithm based on the distance between a milk collecting point and a processing factory, the milk collecting amount of the milk collecting point and the gradient of the milk collecting point, so that the running route of the milk tank car is more scientific and reasonable.
The invention is realized by the following technical scheme:
an intelligent milk receiving platform comprises a milk receiving data acquisition module, a milk receiving data relay transmission module, a milk tank car route optimization management module and a cloud service module;
the milk tank car route optimization module is used for calculating an optimal running route of the milk tank car through a genetic algorithm based on the distance between the milk receiving point and the processing plant, the milk receiving amount of the milk receiving point and the gradient of the milk receiving point; the milk tank car runs to a corresponding milk collection point based on the optimal running route, and data collection of the milk collection point is carried out;
the milk receiving point data acquisition module is used for acquiring the identity information of herdsmen and the weight of the fresh milk at the milk receiving point when the milk tank car runs to the milk receiving point, and taking the time of acquiring the weight of the fresh milk as the milk receiving time; sending the number of the milk receiving point, the identity information of the herdsman, the fresh milk weight and the milk receiving time to the milk receiving relay transmission module;
the milk receiving relay transmission module is used for receiving the milk receiving point number, the herdsman identity information, the fresh milk weight and the milk receiving time sent by the milk receiving point data acquisition module and transmitting the milk receiving point number, the herdsman identity information, the fresh milk weight and the milk receiving time to the cloud service module;
the cloud service module is used for receiving the milk receiving point number, the identity information of the herdsman, the weight of the fresh milk and the milk receiving time sent by the milk receiving relay transmission module, and storing the herdsman identity information, the weight of the fresh milk and the milk receiving time corresponding to the same milk receiving point identification in a centralized manner.
Further, the milk tank car route optimization module comprises a route basic data management unit, an optimization module type management unit and an optimization route generation unit;
the path basic data management unit is used for acquiring all the numbers of the milk receiving points and the numbers of the processing plants and generating a number set P ═ P0,P1,P2…PnIn which p is0Refers to a processing plant number, P1,P2…PnThe number of each milk receiving point is coded; the method is used for acquiring the current transported milk amount of each milk receiving point and generating a milk receiving amount set M ═ M1,M2…Mn}; the method is used for acquiring the serial number of the milk tank car and generating a fleet number set V ═ {1,2, … V }; the grade calculating device is used for calculating the grade between the milk receiving points, inquiring a grade oil consumption index table based on the grade and obtaining the grade index of each grade;
and the optimization model management unit is used for optimizing the number of the milk receiving points, the number of the milk storage tank car, the current milk transportation amount and gradient grade index of each milk receiving point through a genetic algorithm to obtain a path generation model.
And the optimized path generating unit is used for generating an optimal driving route based on the path generating model.
Further, the optimizing the number of the milk receiving point, the number of the milk tank car, the current transported milk volume of each milk receiving point and the grade index of the slope by the genetic algorithm to obtain a path generation model includes:
coding the serial number of each milk receiving point through a coding rule to generate an initial group, wherein the initial group comprises a plurality of arrays;
allocating a milk tank car number to each array in the initial group, and obtaining a corresponding milk tank car identifier based on the milk tank car numbers; acquiring a fitness function value corresponding to each milk tank car identifier, and adding the fitness function values corresponding to all the milk tank car identifiers to obtain an initial fitness function value;
calling a weight processing calculation formula, and carrying out weight processing on the gradient grade index, the current transported milk amount of each milk receiving point and the initial fitness function value to obtain a weight result;
processing the weight result through a selection operator, a crossover operator and a mutation operator to obtain crossover probability and mutation probability;
and adjusting the initial fitness function value based on the cross probability and the variation probability, and outputting a path generation model corresponding to the target fitness function value when the adjusted target fitness function value meets a termination condition.
Further, the encoding each number of the milk receiving points through the encoding rule to generate an initial population, including:
coding the serial number of each milk receiving point through a coding rule to obtain a milk receiving point code;
randomly arranging the milk receiving point codes and grouping the milk receiving point codes to generate chromosomes, wherein each chromosome carries a group of milk receiving point codes, and the milk receiving point codes are converted into arrays to generate an initial group.
Further, the encoding each number of the milk receiving points according to the encoding rule to obtain the codes of the milk receiving points includes:
acquiring a corresponding serial number value based on the serial number of the milk receiving point;
and coding each milk receiving point number based on the serial number value of the milk receiving point number and the ratio of the corresponding milk receiving amount in the total milk receiving amount to obtain a milk receiving point code.
Further, the acquiring a fitness function value corresponding to each of the milk tank car identifiers, and adding the fitness function values corresponding to all the milk tank car identifiers to obtain an initial fitness function value includes:
acquiring the length of a transportation path, the number of the transportation paths and the current milk transportation amount corresponding to each milk tank car identification based on the milk tank car identifications;
determining a fitness function value based on the transport path length, the transport path number and the current transport milk amount corresponding to each milk tank truck identification; the fitness function value is specifically as follows:
Figure BDA0002675870560000041
wherein f (i) represents fitness of i-th chromosome, DnRepresents the sum of the lengths of n transport paths, w, corresponding to each point code of milk withdrawal in the chromosomeijThe milk receiving amount of the milk tank car from the ith milk receiving point to the jth milk receiving point is indicated;
and adding the fitness function values corresponding to all the milk tank truck identifications to obtain an initial fitness function value.
Further, the calling a weight processing calculation formula to perform weight processing on the gradient grade index, the current transported milk amount of each milk receiving point and the initial fitness function value to obtain a weight result includes:
acquiring a gradient grade index and the current milk conveying amount corresponding to the milk tank car identifier based on the milk tank car identifier;
calling a weight processing calculation formula based on the grade index and the current milk transportation amount, and performing weight processing on the grade index, the current milk transportation amount of each milk receiving point and the initial fitness function value to obtain a weight result corresponding to the milk tank car identifier;
the weight processing calculation formula specifically includes: f ═ ω1f+ω2sijwij+...+ω2smnwmnWherein F represents the weight result corresponding to the milk tank car identifier, omega1And ω2Representing a weight factor, sijGrade index, w, corresponding to the transportation path from the ith milk receiving point to the jth milk receiving point in the milk tank car identifierijThe milk receiving amount of the milk tank car when the milk tank car runs from the ith milk receiving point to the jth milk receiving point.
Further, the processing the weight result through the selection operator, the crossover operator, and the mutation operator to obtain the crossover probability and the mutation probability includes:
calculating the weight result to obtain the average weight F of all individuals in the Kth generation group corresponding to the weight resultavg(k) And the standard deviation σ (k) of all individuals;
calculating the variation delta F of the average weight of two adjacent generationsavg(k) And the variation delta sigma (k) of the standard deviation of two adjacent generations, and the variation delta F of the average weightavg(k) And normalizing the variation Δ σ (k) of the standard deviation;
querying a fuzzy control table based on the variable quantity of the average weight value after the normalization processing to determine the cross probability; and querying a fuzzy control table based on the variation of the normalized standard deviation to determine the variation probability.
Furthermore, the milk receiving relay transmission module comprises a network transmission unit and a non-network transmission unit;
the networked transmission unit is used for transmitting the identity information of the herdsman, the fresh milk weight and the milk collection time collected by the milk collection point data collection module to the cloud service module through a network when a milk collection point covered by a network signal exists;
the wireless transmission unit is used for taking a milk receiving terminal of a driver as a data relay terminal when a milk receiving point covered by a network signal does not exist, and storing the identity information of the herdsman, the fresh milk weight and the milk receiving time collected by the milk receiving point data collection module in a data relay application program pre-installed in the data relay terminal; when the data relay terminal runs to a position covered by a network signal, the data relay application program automatically transmits the identity information of the herdsman, the fresh milk weight and the milk collecting time to the cloud service module.
Furthermore, the intelligent milk receiving platform further comprises a system management module;
the system management module comprises a user management unit, a role management unit, a system configuration unit and a data backup and recovery unit;
the user management unit is used for managing user information;
the role management unit is used for dividing and managing the user information based on the role identification;
the system configuration unit is used for carrying out system configuration;
and the data backup and recovery unit is used for backing up and recovering data corresponding to the milk receiving data acquisition module, the milk receiving data relay transmission module and the milk tank car route optimization management module.
According to the intelligent milk collecting platform provided by the invention, the optimal running route of the milk tank car is calculated through a genetic algorithm based on the distance between the milk collecting point and a processing factory, the milk collecting amount of the milk collecting point and the gradient of the milk collecting point, so that the running route of the milk tank car is more scientific and reasonable, data are collected through the milk collecting point data collecting module, the milk collecting relay transmission module transmits the data, and the cloud service module stores the data to realize intelligent milk collection and improve the milk collecting efficiency.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
fig. 1 is a schematic structural diagram of an intelligent milk collection platform according to the present invention.
Fig. 2 is a schematic diagram of an embodiment of the milk receiving data collection module in fig. 1.
FIG. 3 is a flowchart of an embodiment of the optimization model management unit of FIG. 1.
FIG. 4 is a schematic diagram of the cross operator processing the weight result according to an embodiment of the present invention.
FIG. 5 is a schematic diagram of the weight result processing by the mutation operator according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not to be construed as limiting the present invention.
Examples
As shown in fig. 1, the invention provides an intelligent milk collecting platform, which comprises a milk collecting data acquisition module, a milk collecting data relay transmission module, a milk tank car route optimization management module and a cloud service module.
The milk tank car route optimization module is used for calculating the optimal running route of the milk tank car through a genetic algorithm based on the distance between the milk receiving point and the processing plant, the milk receiving amount of the milk receiving point and the gradient of the milk receiving point; and the milk tank car runs to the corresponding milk receiving point based on the optimal running route, and data acquisition of the milk receiving point is carried out.
The milk receiving point data acquisition module is used for acquiring the identity information of herdsmen and the weight of the fresh milk at the milk receiving point when the milk tank car runs to the milk receiving point, and taking the time of acquiring the weight of the fresh milk as the milk receiving time; and sending the number of the milk receiving point, the identity information of the herdsman, the fresh milk weight and the milk receiving time to a milk receiving relay transmission module.
Specifically, the milk collection point data acquisition module comprises a herdsman identity information acquisition unit, a fresh milk weight acquisition unit, an air temperature acquisition unit and a dairy component acquisition unit.
The system comprises a herdsman identity information acquisition unit, a central processing unit and a central processing unit, wherein the herdsman identity information acquisition unit is used for acquiring identity information of the herdsman.
And the fresh milk weight acquisition unit is used for acquiring the weight of the fresh milk, and the weight of the fresh milk comprises gross weight and tare weight. Specifically, the net weight of fresh milk is obtained by tare weight reduction. Tare weight refers to the weight of a container holding fresh milk when fresh milk is not being held.
And the air temperature acquisition unit is used for acquiring the temperature of the milk receiving point.
And the dairy component acquisition unit is used for carrying out component analysis on the fresh milk and determining whether the quality of the fresh milk meets the requirement.
It should be noted that, in this embodiment, the data collected at the milk receiving point includes, but is not limited to, the identity information of the herdsman and the weight of the fresh milk, and may further include data obtained by analyzing the components of the fresh milk, and weather information collected at the milk receiving point. The milk receiving point data acquisition module in the embodiment comprises a server, a smart phone, an identity card reader, an electronic scale, a thermal printer and a dairy component analyzer.
Specifically, as shown in fig. 2, the identity information is registered by the herdsman at the milk collection point, the two-dimensional code on the container containing fresh milk can be scanned by the smart phone to collect the identity information, and the identity information can be read by the identity card reader to collect the identity information when the milk is handed over for the first time. The herdsman puts the container containing the fresh milk on the electronic scale, and the gross weight data is automatically uploaded to the server. According to actual needs, a dairy analyzer can be selected to analyze the components of the fresh milk, determine whether the quality of the fresh milk meets requirements, automatically upload the analysis result to a server, and optionally transmit data such as air temperature to the server. After receiving fresh milk, printing a receipt by a thermal printer and delivering the receipt to the herdsman as a evidence for receiving the milk
And the milk receiving relay transmission module is used for receiving the milk receiving point number, the identity information of herdsmen, the fresh milk weight and the milk receiving time sent by the milk receiving point data acquisition module and transmitting the milk receiving point number, the identity information of the herdsmen, the fresh milk weight and the milk receiving time to the cloud service module.
Wherein, the number of the milk receiving point refers to the number for uniquely identifying the milk receiving point.
And the cloud service module is used for receiving the milk receiving point number, the identity information of the herdsman, the fresh milk weight and the milk receiving time sent by the milk receiving relay transmission module, and storing the herdsman identity information, the fresh milk weight and the milk receiving time corresponding to the same milk receiving point identification in a centralized manner.
Specifically, the cloud service module comprises a herdsman query unit, a milk powder factory query unit, a management department query unit and a data statistics and report making unit.
The herdsman inquiring unit is used for inquiring the information of the herdsman, including but not limited to which milk receiving point the herdsman belongs and the identity information of the herdsman, the milk receiving time and the milk receiving amount of the herdsman.
And the milk powder factory query unit is used for querying information of the milk powder factory, including but not limited to the name and the location of the milk powder factory.
And the management department query unit is used for querying management department information of each milk receiving point, including but not limited to management department identification and personal information of management personnel.
And the data counting and report making unit is used for counting the data collected by the milk receiving data collecting module and making a report on the counted data.
Further, the milk tank car route optimization module comprises a route basic data management unit, an optimization model management unit and an optimization route generation unit.
A path basic data management unit for acquiring all the numbers of the milk receiving points and the numbers of the processing plants and generating a number set P ═ P0,P1,P2…PnIn which p is0Refers to a processing plant number, P1,P2…PnThe number of each milk receiving point is indicated; the method is used for acquiring the current transported milk amount of each milk receiving point and generating a milk receiving amount set M ═ M1,M2…Mn}; the method is used for acquiring the serial number of the milk tank car and generating a fleet number set V ═ {1,2, … V }; the grade calculating device is used for calculating the grade between the milk receiving points, inquiring the grade oil consumption index table based on the grade, and obtaining the grade index of each grade.
The current milk transportation amount refers to the milk receiving amount which is already existed when the milk tank car arrives at the milk receiving point.
Wherein, the grade index of the gradient refers to the grade index corresponding to the gradient. The grade index refers to an index indicating a grade of grade. The grade fuel consumption index meter is a meter for obtaining the fuel consumption index based on the grade. The table comprises the gradient, the grade corresponding to the gradient, the grade index corresponding to the gradient and the oil consumption index, wherein the larger the gradient is, the higher the grade of the gradient is, the smaller the grade index of the gradient is, and the larger the oil consumption index is. For convenience of understanding, taking table 1 as an example for explanation, table 1 is a slope oil consumption index table of a road in XX county:
Figure BDA0002675870560000091
TABLE 1
And the optimization model management unit is used for optimizing the number of the milk receiving points, the number of the milk tank cars, the current milk transportation amount of each milk receiving point and the grade index of the slope through a genetic algorithm to obtain a path generation model.
The route generation model refers to a genetic algorithm obtained by a genetic algorithm on the number of the milk receiving points, the number of the milk storage tank cars, the current milk transportation amount of each milk receiving point and the grade index of the slope.
And the optimized path generating unit is used for generating an optimal driving path based on the path generating model.
Further, as shown in fig. 3, the method for optimizing the number of the milk receiving point, the number of the milk storage tank car, the current milk transportation amount and grade index of each milk receiving point by using a genetic algorithm to obtain a route generation model includes:
and coding the serial number of each milk receiving point through a coding rule to generate an initial group, wherein the initial group comprises a plurality of arrays.
Allocating a milk tank car number to each array in the initial group, and obtaining a corresponding milk tank car identifier based on the milk tank car numbers; and acquiring a fitness function value corresponding to each milk tank car identifier, and adding the fitness function values corresponding to all the milk tank car identifiers to obtain an initial fitness function value.
The milk tank car identification refers to an identification used for uniquely identifying the milk tank car, such as a, b, c and the like. The initial fitness function value is a value obtained by adding fitness function values corresponding to all the milk tank car identifications.
And calling a weight processing calculation formula, and carrying out weight processing on the gradient grade index, the current transported milk amount of each milk receiving point and the initial fitness function value to obtain a weight result.
And processing the weight result through a selection operator, a crossover operator and a mutation operator to obtain the crossover probability and the mutation probability.
Wherein the target fitness function value is a value obtained by adjusting the initial fitness function value by the crossover probability and the variation probability.
Specifically, the initial fitness function value is adjusted based on the cross probability and the variation probability, and when the adjusted target fitness function value meets a termination condition, a path generation model corresponding to the target fitness function value is output.
The termination condition refers to a condition for stopping the adjustment of the target fitness function value. The termination condition in this embodiment includes terminating execution of the genetic algorithm when the target fitness function value generated after each iteration is not improved relative to the target fitness function value of the previous iteration (that is, an absolute value of a difference between the target fitness function value generated after each iteration and the target fitness function value of the previous iteration is smaller than a preset threshold value); or the execution of the genetic algorithm is terminated after the iteration number reaches the maximum iteration number, and the termination condition which is met firstly is taken as the criterion in the two cases. The threshold value can be set according to actual conditions.
Such as: the maximum iteration number can be set to 10000, and if the maximum iteration number is not executed for 1000 times, but the absolute value of the difference value between the target fitness function value generated after each iteration of the method and the target fitness function value of the last iteration is smaller than a preset threshold value, the execution of the genetic algorithm is terminated.
Further, each number of the milk receiving points is coded through a coding rule to generate an initial group, and the method comprises the following steps:
and coding the serial number of each milk receiving point according to a coding rule to obtain the code of the milk receiving point.
Randomly arranging the milk receiving point codes and grouping to generate chromosomes, wherein each chromosome carries a group of milk receiving point codes, and the milk receiving point codes are converted into arrays to generate an initial group.
Furthermore, each number of the milk receiving points is coded through a coding rule to obtain the code of the milk receiving points, and the method comprises the following steps:
and acquiring a corresponding number value based on the number of the milk receiving point.
And coding the serial number of each milk receiving point based on the serial number value of the milk receiving point serial number and the ratio of the corresponding milk receiving amount in the total milk receiving amount to obtain the milk receiving point code.
Specifically, a value obtained by adding the serial number value of the number of the milk receiving point and the ratio of the corresponding milk receiving amount in the total milk receiving amount is used as the milk receiving point code.
Further, acquiring a fitness function value corresponding to each of the milk tank car identifiers, and adding the fitness function values corresponding to all the milk tank car identifiers to obtain an initial fitness function value, wherein the method comprises the following steps:
and acquiring the length of the transportation path, the number of the transportation paths and the current transportation milk amount corresponding to each milk tank car identifier based on the milk tank car identifiers.
As shown in table 2, the distances between some of the receiving points and between each receiving point and the processing plant are:
Figure BDA0002675870560000121
table 2 as shown in table 3, the total milk yield is 1000kg for the milk receiving amount of different milk receiving points.
Milk receiving point Number 1 Number 2 No. 3 Number 4 Number 5 Number 6 No. 7 Number 8
Milk yield 600kg 300kg 200kg 400kg 800kg 300kg 600kg 600kg
TABLE 3
Receive point No. 1 in table 3: the milk yield is 600kg, and according to the coding rule: 1+600/1000 is 1.6, the number 1 milk receiving point code is 1.6; number 2 point of receiving milk: the milk yield is 200kg, and according to the coding rule: 2+200/1000 is equal to 2.3, then the number 2 milk receiving point code is 2.3, the number 3 milk receiving point code is 3.2, the number 4 milk receiving point code is 4.4, the number 5 milk receiving point code is 5.8, the number 6 milk receiving point code is 6.3, the number 7 milk receiving point code is 7.6, and the number 8 milk receiving point code is 8.6.
After the milk receiving point codes of the milk receiving points in table 3 are obtained, the milk receiving point codes are randomly arranged and grouped to generate chromosomes, each chromosome carries a group of milk receiving point codes, and an array formed by each group of milk receiving point codes is allocated with a milk tank car identifier, as shown in table 4:
Figure BDA0002675870560000131
TABLE 4
Determining a fitness function value based on the transport path length, the transport path number and the current transport milk amount corresponding to each milk tank truck identification; the fitness function value is specifically as follows:
Figure BDA0002675870560000132
wherein f (i) represents fitness of i-th chromosome, DnRepresenting the sum of the n transport path lengths, w, corresponding to each point code in the chromosomeijThe milk receiving amount of the milk tank car when the milk tank car runs from the ith milk receiving point to the jth milk receiving point.
Specifically, after a milk tank car identifier is allocated to an array formed by encoding each milk receiving point, an adaptability function value is determined based on the transport path length, the transport path number and the current transport milk amount corresponding to each milk tank car identifier.
And adding the fitness function values corresponding to all the milk tank truck identifications to obtain an initial fitness function value.
Further, a weight processing calculation formula is called, and weight processing is performed on the gradient grade index, the current transported milk amount of each milk receiving point and the initial fitness function value to obtain a weight result, wherein the weight processing calculation formula comprises:
and acquiring the grade index of the slope corresponding to the milk tank car identifier and the current milk transportation amount based on the milk tank car identifier.
And calling a weight processing calculation formula based on the gradient grade index and the current milk volume to perform weight processing on the gradient grade index, the current milk volume transported at each milk receiving point and the initial fitness function value so as to obtain a weight result corresponding to the milk tank car identifier.
The weight processing calculation formula is specifically as follows: f ═ ω1f+ω2sijwij+...+ω2smnwmnWherein F represents the weight result corresponding to the milk tank car identifier, omega1And ω2Representing a weight factor, sijGrade index, w, corresponding to the transportation path from the ith milk collection point to the jth milk collection point in the milk tank car identifierijThe milk receiving amount of the milk tank car when the milk tank car runs from the ith milk receiving point to the jth milk receiving point.
Further, the weight result is processed through a selection operator, a crossover operator and a mutation operator to obtain a crossover probability and a mutation probability, and the method comprises the following steps:
calculating the weight result to obtain the average weight F of all individuals in the Kth generation group corresponding to the weight resultavg(k) And the standard deviation σ (k) of all individuals.
Calculating the variation delta F of the average weight of two adjacent generationsavg(k) And the variation delta sigma (k) of the standard deviation of two adjacent generations, and the variation delta F of the average weightavg(k) And the variation Δ σ (k) of the standard deviation.
Querying a fuzzy control table based on the variable quantity of the average weight value after the normalization processing to determine the cross probability; and querying a fuzzy control table based on the variation of the normalized standard deviation to determine the variation probability.
Specifically, the process of processing the weight result by the selection operator specifically includes:
in the embodiment, a classical roulette method is adopted for selection operation, and the weight of an ith genetic code is assumed to be FiThe total weight S of the groupFThe calculation formula is as follows:
Figure BDA0002675870560000141
probability P that the ith genetic code was selectediThe calculation formula is as follows:
Figure BDA0002675870560000142
according to PiN "roulette" plays were performed, each time selecting 1 genetic code, to form a new population.
Specifically, the process of processing the weight result by the crossover operator specifically includes:
step 1: randomly selecting two individuals as parents, namely a father A and a father B respectively, and using a cross probability Pc
Selecting crossed individuals in the father A and the father B;
step 2: calculating the fitness value of each segment of gene, starting operation from the gene segment with the minimum fitness value, directly transmitting the rest gene segments to filial generations, and removing repeated gene segments;
and step 3: after the step 1 and the step 2 are carried out, if no gene segments remain, obtaining final filial generations, and finishing the operation; and if gene segments are left, inserting the left genes into each position respectively, and calculating the fitness, wherein the position with the maximum fitness value is the optimal position of the gene, so as to obtain the final filial generation.
The principle of processing the weight result by the crossover operation can also be called as crossover operation, namely, the process of interchanging partial gene segments in two parents to recombine to generate a new gene combination, so that better individuals are ensured not to be damaged by the crossover operation as much as possible, and simultaneously, the requirement that the new individuals can contain more excellent genes is met.
As shown in fig. 4, if the individuals corresponding to the randomly selected two chromosomes are the first generation parent a and the parent B, where the parent a includes a first a group (fa1), a first B group (fb1) and a first c group (fc1), where the array of fa1 is 0, 1.6, 3.2, 0, the array of fb1 is 0, 2.3, 6.3, 7.6, 4.4, 0, the array of fc1 is 0, 5.8, 8.6, 0, the parent B includes a second a group (fa2), a second B group (fb2) and a second c group (fc2), where the array of fa2 is 0, 2.3, 5.8, 7.6, 0, the array of fb2 is 0, 1.6, 3.2, 0, the array of fc2 is 0, 4.4, 8.6, 6.3, 0, the function value of fc2 is 0, the function value of B is set, the fitness value of B is calculated by randomly selecting the parent a, and B, the fitness of the child B is calculated by direct calculation, and the target fitness of the selected parent B sets, forming first child fb1, the array of fb1 is 0, 2.3, 6.3, 7.6, 4.4, 0, and obtaining second generation parent a and parent B, wherein parent a comprises the array of fa1 is 0, 1.6, 3.2, 0, the array of fc1 is 0, 5.8, 8.6, 0, parent B comprises the array of fa2 is 0, 5.8, 0, the array of fb2 is 0, 1.6, 3.2, 0, the array of fc2 is 0, 8.6, 0, if the remaining parent still has an encoding already put in children, the encoding is dropped, if the last encoding still remains, the encoding is put directly in each position of children, repeating the above operations, by calculating the highest value of the target degree function of group B, continuing to put group B to children, forming second child fb1 and child fb2, fb1 is 0, 3.3.6, 3.3.493, 0, 3.6, 0, 3.493, and the third generation array is 0, 3.6, 0, 4, 0, 4, 0, 4 and obtaining second child B, wherein, the array of parent a is fb1 is 0, 5.8, 8.6, 0, parent B includes fa3 and fc3, the array of fa3 is 0, 5.8, 0, the array of fc3 is 0, 8.6, 0, if there is still a code that has been put into children in the remaining parent, the code is removed, if there is a code that is left at the end, the code is put directly into each position of children, the above operations are repeated, by calculating the highest value of the target fitness function of group B, group B is continued to be put into children, forming third children fb 5, fb2, and fc3, wherein, the array of fb1 is 0, 2.3, 6.3, 7.6, 4.4, 0, the array of fb2 is 0, 1.6, 3.2, 0, fc 4 is 0, 8.6, 0, and obtaining fourth generation a and B, wherein, the array of parent a is 0, parent a1 is 0, fa 368.6, 0, parent B is 0, the remaining is 0, fb5 is 0, fb3876, and if there is still a code that has been put into children, 0, 3, 368.24, the codes are removed, if the codes remain finally, the codes are directly put into each position of the offspring, the above operations are repeated, the target fitness function value of the group b is calculated to be the highest, the group b is continuously put into the offspring, fourth generation offspring fb1, fb2 and fc3 are formed, wherein the array of fb1 is 0, 2.3, 6.3, 7.6, 4.4 and 0, the array of fb2 is 0, 1.6, 3.2 and 0, the array of fc3 is 0, 8.6 and 0, each group of fitness values are calculated again, the corresponding position with the highest fitness value is finally selected to be put, and the final offspring fb 23, fb2 and fc3 are obtained, wherein the array of fb4 is 0, 2.3, 6.3, 7.6, 5.8, 4.4 and 0, the array of fb2 is 0, 1.6, 3.2 and 0, 3 is 0.8 and 0.6.
Specifically, the process of processing the weight result by the mutation operator specifically includes:
step 1: setting a probability of variation Pm；
Step 2: randomly generating a number of [0,1] to judge whether to mutate, if so, executing a step 3, and if not, executing a step 5;
and step 3: randomly generating the position of the gene for mutation and the number H of the gene with the mutation, wherein H cannot exceed the total gene number H of the chromosome, namely H is required to be less than or equal to H;
and 4, step 4: inserting the genes between the two selected genes into the original position according to the reverse order, and keeping the relative position between the selected gene segments unchanged;
and 5: and (4) respectively calculating the target fitness function values of the operated genes, and finally judging whether the results meet termination conditions.
The principle of processing the weight result by the mutation operator can also be called mutation operation, i.e. the phenomenon of gene mutation of species, also according to the mutation probability PmThe process of exchanging or substituting certain genes with other genes on a chromosome to generate a new individual. The mutation operation is helpful for generating new individuals, expanding the search range and further finding a better solution. The main rule in genetic algorithms is based on the probability of variation PmInversion of the binary coding of the allele. Such as: binary character 1 is converted to 0 and 0 is converted to 1.
As shown in fig. 5, if the number of the mutated genes is 2 and is less than the total number of the genes 12, the mutation group B selects two random points, and performs gene inversion operation (i.e., the genes between the two selected genes are inserted into the original positions in reverse order, and the relative positions of the selected gene segments remain unchanged), so as to obtain the operated genes.
After obtaining the operated genes, respectively carrying out target fitness function numerical calculation on the operated genes, and finally judging whether the result meets the termination condition
Furthermore, the milk receiving relay transmission module comprises a net transmission unit and a non-net transmission unit.
And the network transmission unit is used for transmitting the identity information of the herdsman, the fresh milk weight and the milk collection time collected by the milk collection point data collection module to the cloud service module through the network when the milk collection point covered by the network signal exists.
The wireless transmission unit is used for taking a milk receiving terminal of a driver as a data relay terminal when a milk receiving point covered by a network signal does not exist, and storing the identity information of herdsmen, the fresh milk weight and the milk receiving time acquired by the milk receiving point data acquisition module in a data relay application program pre-installed in the data relay terminal; when the data relay terminal runs to a position covered by a network signal, the data relay application program automatically transmits the identity information of the herdsman, the fresh milk weight and the milk receiving time to the cloud service module.
Further, the intelligent milk receiving platform further comprises a system management module.
The system management module comprises a user management unit, a role management unit, a system configuration unit and a data backup and recovery unit;
the user management unit is used for managing the user information;
the role management unit is used for carrying out division management on the user information based on the role identification;
the system configuration unit is used for carrying out system configuration;
and the data backup and recovery unit is used for backing up and recovering data corresponding to the milk receiving data acquisition module, the milk receiving data relay transmission module and the milk tank car route optimization management module.
In particular, the above embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above embodiments are only illustrative of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (10)

1. An intelligent milk receiving platform is characterized by comprising a milk receiving data acquisition module, a milk receiving data relay transmission module, a milk tank car route optimization management module and a cloud service module;
the milk tank car route optimization module is used for calculating an optimal running route of the milk tank car through a genetic algorithm based on the distance between the milk receiving point and the processing plant, the milk receiving amount of the milk receiving point and the gradient of the milk receiving point; the milk tank car runs to a corresponding milk receiving point based on the optimal running route, and data collection of the milk receiving point is carried out;
the milk receiving point data acquisition module is used for acquiring the identity information of herdsmen and the weight of the fresh milk at the milk receiving point when the milk tank car runs to the milk receiving point, and taking the time of acquiring the weight of the fresh milk as the milk receiving time; sending the number of the milk receiving point, the identity information of the herdsman, the fresh milk weight and the milk receiving time to the milk receiving relay transmission module;
the milk receiving relay transmission module is used for receiving the milk receiving point number, the herdsman identity information, the fresh milk weight and the milk receiving time sent by the milk receiving point data acquisition module and transmitting the milk receiving point number, the herdsman identity information, the fresh milk weight and the milk receiving time to the cloud service module;
the cloud service module is used for receiving the milk receiving point number, the identity information of the herdsman, the fresh milk weight and the milk receiving time sent by the milk receiving relay transmission module, and storing the herdsman identity information, the fresh milk weight and the milk receiving time corresponding to the same milk receiving point identification in a centralized manner.
2. The intelligent milk receiving platform of claim 1, wherein the milk tank car route optimization module comprises a route basic data management unit, an optimization model management unit and an optimization route generation unit;
the path basic data management unit is used for acquiring all the numbers of the milk receiving points and the numbers of the processing plants and generating a number set P ═ P0,P1,P2…PnIn which p is0Refers to a processing plant number, P1,P2…PnThe number of each milk receiving point is indicated; the method is used for acquiring the current transported milk amount of each milk receiving point and generating a milk receiving amount set M ═ M1,M2…Mn}; the method is used for acquiring the serial number of the milk tank car and generating a fleet number set V ═ {1,2, … V }; the grade calculating device is used for calculating the grade between the milk receiving points, inquiring a grade oil consumption index table based on the grade and obtaining the grade index of each grade;
the optimization model management unit is used for optimizing the number of the milk receiving points, the number of the milk storage tank car, the current transported milk volume of each milk receiving point and the grade index of the slope through a genetic algorithm to obtain a path generation model;
and the optimized path generating unit is used for generating an optimal driving route based on the path generating model.
3. The intelligent milk receiving platform of claim 2, wherein the optimizing the number of the milk receiving point, the number of the milk tank car, the current transported milk volume of each milk receiving point and the grade index by a genetic algorithm to obtain a path generation model comprises:
coding the serial number of each milk receiving point through a coding rule to generate an initial group, wherein the initial group comprises a plurality of arrays;
allocating a milk tank car number to each array in the initial group, and obtaining a corresponding milk tank car identifier based on the milk tank car numbers; acquiring a fitness function value corresponding to each milk tank car identifier, and adding the fitness function values corresponding to all the milk tank car identifiers to obtain an initial fitness function value;
calling a weight processing calculation formula, and carrying out weight processing on the gradient grade index, the current transported milk amount of each milk receiving point and the initial fitness function value to obtain a weight result;
processing the weight result through a selection operator, a crossover operator and a mutation operator to obtain crossover probability and mutation probability;
and adjusting the initial fitness function value based on the cross probability and the variation probability, and outputting a path generation model corresponding to the target fitness function value when the adjusted target fitness function value meets a termination condition.
4. The intelligent milk receiving platform of claim 3, wherein the encoding of each number of milk receiving points by the encoding rule to generate the initial population comprises:
coding the serial number of each milk receiving point through a coding rule to obtain a milk receiving point code;
randomly arranging the milk receiving point codes and grouping the milk receiving point codes to generate chromosomes, wherein each chromosome carries a group of milk receiving point codes, and the milk receiving point codes are converted into arrays to generate an initial group.
5. The intelligent milk receiving platform of claim 4, wherein the step of obtaining the milk receiving point code by coding each milk receiving point number according to the coding rule comprises:
acquiring a corresponding serial number value based on the serial number of the milk receiving point;
and coding the serial number of each milk receiving point based on the serial number value of the milk receiving point serial number and the ratio of the corresponding milk receiving amount in the total milk receiving amount to obtain the milk receiving point code.
6. The intelligent milk receiving platform of claim 3, wherein the obtaining of the fitness function value corresponding to each of the tank car identifiers and the adding of the fitness function values corresponding to all the tank car identifiers to obtain an initial fitness function value comprises:
acquiring the length of a transportation path, the number of the transportation paths and the current milk transportation amount corresponding to each milk tank car identification based on the milk tank car identifications;
determining a fitness function value based on the transport path length, the transport path number and the current transport milk amount corresponding to each milk tank truck identification; the fitness function value is specifically as follows:
Figure FDA0002675870550000031
wherein f (i) represents fitness of i-th chromosome, DnRepresenting the sum of the n transport path lengths, w, corresponding to each point code in the chromosomeijThe milk receiving amount of the milk tank car from the ith milk receiving point to the jth milk receiving point is indicated;
and adding the fitness function values corresponding to all the milk tank truck identifications to obtain an initial fitness function value.
7. The intelligent milk receiving platform of claim 3, wherein the invoking of the weight processing calculation formula weights the grade index, the current transported milk volume of each milk receiving point, and the initial fitness function value to obtain a weight result, and the method comprises:
acquiring a gradient grade index and a current milk transportation amount corresponding to the milk tank car identifier based on the milk tank car identifier;
calling a weight processing calculation formula based on the grade index and the current milk transportation amount, and performing weight processing on the grade index, the current milk transportation amount of each milk receiving point and the initial fitness function value to obtain a weight result corresponding to the milk tank car identifier;
the weight processing calculation formula specifically includes: f ═ ω1f+ω2sijwij+...+ω2smnwmnWherein F represents the weight result corresponding to the milk tank car identifier, omega1And ω2Representing a weight factor, sijGrade index, w, corresponding to the transportation path from the ith milk receiving point to the jth milk receiving point in the milk tank car identifierijThe milk receiving amount of the milk tank car when the milk tank car runs from the ith milk receiving point to the jth milk receiving point.
8. The intelligent milk receiving platform of claim 3, wherein the processing of the weight result by the selection operator, the crossover operator and the mutation operator to obtain the crossover probability and the mutation probability comprises:
calculating the weight result to obtain the average weight F of all individuals in the Kth generation group corresponding to the weight resultavg(k) And the standard deviation σ (k) of all individuals;
calculating the variation delta F of the average weight of two adjacent generationsavg(k) And the variation delta sigma (k) of the standard deviation of two adjacent generations, and the variation delta F of the average weightavg(k) Normalizing the standard deviation and the variation delta sigma (k) of the standard deviation;
querying a fuzzy control table based on the variable quantity of the average weight value after the normalization processing to determine the cross probability; and querying a fuzzy control table based on the variation of the normalized standard deviation to determine the variation probability.
9. The intelligent milk collecting platform according to claim 1, wherein the milk collecting relay transmission module comprises a network transmission unit and a wireless transmission unit;
the networked transmission unit is used for transmitting the identity information of the herdsman, the fresh milk weight and the milk collection time collected by the milk collection point data collection module to the cloud service module through a network when a milk collection point covered by a network signal exists;
the wireless transmission unit is used for taking a milk receiving terminal of a driver as a data relay terminal when a milk receiving point covered by a network signal does not exist, and storing the identity information of the herdsman, the fresh milk weight and the milk receiving time acquired by the milk receiving point data acquisition module in a data relay application program pre-installed in the data relay terminal; when the data relay terminal runs to a position covered by a network signal, the data relay application program automatically transmits the identity information of the herdsman, the fresh milk weight and the milk collecting time to the cloud service module.
10. The intelligent milk receiving platform of claim 1, further comprising a system management module;
the system management module comprises a user management unit, a role management unit, a system configuration unit and a data backup and recovery unit;
the user management unit is used for managing user information;
the role management unit is used for dividing and managing the user information based on the role identification;
the system configuration unit is used for carrying out system configuration;
and the data backup and recovery unit is used for backing up and recovering data corresponding to the milk receiving data acquisition module, the milk receiving data relay transmission module and the milk tank car route optimization management module.
CN202010947666.3A 2020-09-10 2020-09-10 Intelligent milk collection platform system Active CN112070309B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010947666.3A CN112070309B (en) 2020-09-10 2020-09-10 Intelligent milk collection platform system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010947666.3A CN112070309B (en) 2020-09-10 2020-09-10 Intelligent milk collection platform system

Publications (2)

Publication Number Publication Date
CN112070309A true CN112070309A (en) 2020-12-11
CN112070309B CN112070309B (en) 2021-03-30

Family

ID=73663594

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010947666.3A Active CN112070309B (en) 2020-09-10 2020-09-10 Intelligent milk collection platform system

Country Status (1)

Country Link
CN (1) CN112070309B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010018384A1 (en) * 2000-02-24 2001-08-30 Yoshiyuki Onimaru Vehicle deceleration controller
CN103067508A (en) * 2012-12-28 2013-04-24 银江股份有限公司 Real-time dynamic bus trip information publication system
CN103903053A (en) * 2014-01-18 2014-07-02 内蒙古农业大学 Coarse-grain parallel algorithm based on ant colony optimization and genetic algorithm
CN103957549A (en) * 2014-05-14 2014-07-30 长江水利委员会长江科学院 Node distribution optimization method for river local area wireless sensor based on genetic algorithm
KR101795935B1 (en) * 2016-05-30 2017-11-13 인하대학교 산학협력단 System and method for detecting optimal route in the unmanned aerial vehicle assisted sensor network
CN107479365A (en) * 2017-09-22 2017-12-15 西南民族大学 The fuzzy synthetic appraisement method of PID suspension controllers based on genetic algorithm
CN107664503A (en) * 2016-07-29 2018-02-06 上海汽车集团股份有限公司 Vehicle path planning method and device
CN110006428A (en) * 2019-01-21 2019-07-12 武汉大学 A kind of overlay path method and device for planning based on unmanned plane energy
CN110276499A (en) * 2019-06-28 2019-09-24 青岛立东生态有限公司 A kind of refuse collection route optimization calculation method
CN111238521A (en) * 2020-02-11 2020-06-05 北京理工大学 Path planning method and system for unmanned vehicle

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010018384A1 (en) * 2000-02-24 2001-08-30 Yoshiyuki Onimaru Vehicle deceleration controller
CN103067508A (en) * 2012-12-28 2013-04-24 银江股份有限公司 Real-time dynamic bus trip information publication system
CN103903053A (en) * 2014-01-18 2014-07-02 内蒙古农业大学 Coarse-grain parallel algorithm based on ant colony optimization and genetic algorithm
CN103957549A (en) * 2014-05-14 2014-07-30 长江水利委员会长江科学院 Node distribution optimization method for river local area wireless sensor based on genetic algorithm
KR101795935B1 (en) * 2016-05-30 2017-11-13 인하대학교 산학협력단 System and method for detecting optimal route in the unmanned aerial vehicle assisted sensor network
CN107664503A (en) * 2016-07-29 2018-02-06 上海汽车集团股份有限公司 Vehicle path planning method and device
CN107479365A (en) * 2017-09-22 2017-12-15 西南民族大学 The fuzzy synthetic appraisement method of PID suspension controllers based on genetic algorithm
CN110006428A (en) * 2019-01-21 2019-07-12 武汉大学 A kind of overlay path method and device for planning based on unmanned plane energy
CN110276499A (en) * 2019-06-28 2019-09-24 青岛立东生态有限公司 A kind of refuse collection route optimization calculation method
CN111238521A (en) * 2020-02-11 2020-06-05 北京理工大学 Path planning method and system for unmanned vehicle

Non-Patent Citations (8)

* Cited by examiner, † Cited by third party
Title
AUDRITO, GIORGIO等: "Optimal single-path information propagation in gradient-based algorithms", 《SCIENCE OF COMPUTER PROGRAMMING》 *
PATTNAIK, SB等: "Urban bus transit route network design using genetic algorithm", 《JOURNAL OF TRANSPORTATION ENGINEERING-ASCE》 *
WANG LEI等: "Dynamic path planning for mobile robot based on improved genetic algorithm", 《JOURNAL OF NANJING UNIVERSITY OF AERONAUTICS & ASTRONAUTICS》 *
冯倩倩: "基于智能优化算法的输电线路路径优化问题的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
尹亚明: "基于改进的遗传算法的仓库机器人路径优化研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
张培 等: "基于遗传算法的鲜奶冷链物流配送路径优化", 《市场周刊(理论研究)》 *
彭骞: "基于遗传算法的山区高等级公路纵断面智能优化方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 *
许永花 等: "改进遗传算法在牛奶运输车辆路径优化中的应用", 《东北农业大学学报》 *

Also Published As

Publication number Publication date
CN112070309B (en) 2021-03-30

Similar Documents

Publication Publication Date Title
CN111582552B (en) Shared bicycle parking point distribution method based on multi-target genetic algorithm
CN110909434B (en) Urban public transport trunk line network design method under low-carbon guidance
CN115099543B (en) Path planning method, device and equipment for battery replacement and storage medium
CN110516870B (en) Multi-recovery site garbage collection and transportation method based on co-evolution
CN111126799B (en) Shared network driver and crew matching method based on bipartite graph
Cosma et al. A two-level based genetic algorithm for solving the soft-clustered vehicle routing problem
CN116824861B (en) Method and system for scheduling sharing bicycle based on multidimensional data of urban brain platform
CN107679484A (en) A kind of Remote Sensing Target automatic detection and recognition methods based on cloud computing storage
CN111626492B (en) Fuzzy multi-target opportunity constraint planning method for electric vehicle charging network
CN112070309B (en) Intelligent milk collection platform system
CN114926118A (en) Method, device and equipment for processing vehicle and cargo loading information and storage medium
CN105787597B (en) Data optimization processing system
CN113793030A (en) Material scheduling method and device and storage medium
CN116342148B (en) Harmless integrated traceability management system and method for medical waste
CN111260161A (en) Method and device for issuing crowdsourcing tasks
CN115328870B (en) Data sharing method and system for cloud manufacturing
CN115660538B (en) Cargo transportation method and system
CN116050742A (en) Intelligent scheduling configuration method and system for shared vehicle operation and maintenance personnel
CN116203982A (en) Unmanned aerial vehicle power patrol track planning method and system
CN115936561A (en) Logistics vehicle track operation abnormity monitoring method
CN113191569A (en) Enterprise management method and system based on big data
CN111784243A (en) Logistics management method and device and readable storage medium
CN117273473B (en) Intelligent logistics data acquisition system based on intelligent algorithm
CN115689128B (en) Customer data analysis method and system based on CRM
CN117314124B (en) Intelligent management system and method for expressway toll service

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