CN114980131A - Raw cigarette tray wireless sensor layout optimization method based on improved particle swarm optimization - Google Patents

Raw cigarette tray wireless sensor layout optimization method based on improved particle swarm optimization Download PDF

Info

Publication number
CN114980131A
CN114980131A CN202210308361.7A CN202210308361A CN114980131A CN 114980131 A CN114980131 A CN 114980131A CN 202210308361 A CN202210308361 A CN 202210308361A CN 114980131 A CN114980131 A CN 114980131A
Authority
CN
China
Prior art keywords
population
sensor
raw
particle swarm
stack
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210308361.7A
Other languages
Chinese (zh)
Inventor
徐跃明
陈斌
周继来
方海英
郭绍坤
杨磊
许仁杰
黄纲临
徐勇
周萍
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.)
Hongyun Honghe Tobacco Group Co Ltd
Original Assignee
Hongyun Honghe Tobacco Group Co Ltd
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 Hongyun Honghe Tobacco Group Co Ltd filed Critical Hongyun Honghe Tobacco Group Co Ltd
Priority to CN202210308361.7A priority Critical patent/CN114980131A/en
Publication of CN114980131A publication Critical patent/CN114980131A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/18—Network planning tools
    • 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]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
    • 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

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a raw tobacco tray wireless sensor layout optimization method based on an improved particle swarm algorithm, which belongs to the field of tobacco maintenance. According to the sensor optimization method provided by the invention, the influence of temperature and humidity on the mildew inside the tobacco stack is considered, the established model can cover the monitoring area to the maximum extent, the cost for arranging the sensor is effectively reduced, and the sensor optimization method has a high application value in the aspect of controlling the mildew information in the tobacco leaf maintenance link of a tobacco enterprise.

Description

Raw cigarette tray wireless sensor layout optimization method based on improved particle swarm optimization
Technical Field
The invention relates to the field of sensor layout, in particular to a raw cigarette tray wireless sensor layout optimization method based on an improved particle swarm algorithm.
Background
The layout planning of the sensors is an important link of a raw tobacco goods yard for monitoring tobacco information, and because the temperature and humidity change inside a tobacco stack needs to be strictly monitored in the curing process of raw tobacco leaves, the situation that the interior of the tobacco stack is mildewed and the like so that the tobacco leaves cannot reach the best alcoholization process in the curing process is avoided.
Most of the current researches do not combine with the practical application background, which causes great difficulty to the practical application of the model and the algorithm.
Most of researches at present mainly focus on the research of WSN models and algorithms, and the research of sensor layout optimization in aspects of tobacco leaf mildew information monitoring and the like is nearly lacked. In the research of sensor layout planning, the model constraint is not perfect enough in consideration.
Disclosure of Invention
The invention provides an improved optimization method of a particle swarm algorithm for wireless sensor layout, aiming at the problems that the monitoring of temperature/humidity information is not comprehensive enough in the process of maintaining raw tobacco leaves at the present stage, the equipment investment cost is high and the like.
In order to achieve the purpose, the invention is realized by adopting the following technical complex scheme: the method comprises the following steps:
step 1, establishing a wireless sensor model;
step 2, solving the model by using an improved particle swarm algorithm;
and 3, optimizing the position of the sensor in the raw cigarette stack, predicting temperature information through an LSTM algorithm, and performing secondary optimization on the sensor layout scheme.
Preferably, in step 1, the wireless sensor model is established in the following specific manner:
Figure RE-RE-GDA0003772857940000011
Figure RE-RE-GDA0003772857940000012
where R is the sensing radius of the wireless sensor,
Figure RE-RE-GDA0003772857940000013
for monitoring the time length of the interval twice, alpha is the thermal diffusivity of the tobacco leaves, lambda is the thermal conductivity of the tobacco leaves, C V Is a volumetric specific heat and C V ＝ρ·C P 。
Random sensor position and random cigarette stack grid point
Figure RE-RE-GDA0003772857940000014
The position of (d) is expressed as follows by using Euclidean distance:
Figure RE-RE-GDA0003772857940000021
wherein
Figure RE-RE-GDA0003772857940000022
Is a collection of grid points in the inner space of the raw tobacco stack,
Figure RE-RE-GDA0003772857940000023
for any grid point
Figure RE-RE-GDA0003772857940000024
At a position in the space of the stack of raw cigarettes,
Figure RE-RE-GDA0003772857940000025
is a collection of wireless sensors in the raw tobacco stack,
Figure RE-RE-GDA0003772857940000026
is an arbitrary sensor
Figure RE-RE-GDA0003772857940000027
In the raw tobacco stack space.
Defining the coverage weight of each grid point in the raw tobacco stack, namely:
Figure RE-RE-GDA0003772857940000028
Figure RE-RE-GDA0003772857940000029
wherein C 0 、C 1 、C 2 As a coefficient, T is a storage temperature/. degree.C., ln (u) i ) Is the specific growth rate of the ith grid point affected by the temperature of that point.
Defining the weight of coverage of the sensor to the grid points in the raw tobacco stack, namely:
Figure RE-RE-GDA00037728579400000210
Figure RE-RE-GDA00037728579400000211
wherein
Figure RE-RE-GDA00037728579400000212
For the weight of coverage of the grid points by sensor j in the raw tobacco stack,
Figure RE-RE-GDA00037728579400000213
the variable is 0-1, when the distance from any grid position point in the raw tobacco stack to the sensor j is less than the sensing radius of the sensor
Figure RE-RE-GDA00037728579400000214
Otherwise
Figure RE-RE-GDA00037728579400000215
The total coverage rate of the wireless sensor to the raw tobacco stack is as follows:
Figure RE-RE-GDA00037728579400000216
preferably, the step 2 is detailed as follows; a differential crossing strategy is introduced, and a method for generating a variation population comprises the following steps:
Figure RE-RE-GDA00037728579400000217
where F denotes the difference coefficient and r3, r4 is a random integer between 1 and NP. After obtaining the variant population, performing cross operation with the original population to obtain a cross population:
Figure RE-RE-GDA00037728579400000218
preferably, the step 3: introducing a foraging selection strategy method. Before the position is updated, the structure and the information of the original population are completely copied to obtain a new population, the new population replaces the original population to carry out difference and intersection, and the original population still executes the updating strategy of the traditional particle swarm algorithm. And after the position is updated, combining the new population with the original population to form a selected population with the population scale of 2NP, sorting the fitness values, selecting better NP individuals by a greedy strategy, and entering next iteration.
Preferably, the step 2 is solved, and a differential crossing strategy and a foraging selection strategy are introduced into the [0029] improved particle swarm optimization, and the algorithm steps are as follows:
step 2.1: initializing parameters, and generating initial population by random mode
Step 2.2: calculating fitness function values of individuals in the population, updating individual extreme values and global extreme values, and storing corresponding extreme value points
Step 2.3: copying the structure and information of the population to obtain a new population, and performing differential cross operation on the new population instead of the original population;
step 2.4: updating the speed of each individual in the original population, and reassigning the speed violating the boundary condition;
step 2.5: updating the position of each individual in the original population, and reassigning the position violating the boundary condition;
step 2.6: and executing a differential crossing strategy on each individual in the new population to generate a crossing population.
Step 2.7: combining the updated cross population and the original population, sequencing the fitness values, and selecting a better individual to enter next iteration;
step 2.8: the loop is exited when the maximum number of iterations is reached, otherwise, the procedure returns to step 2.2
A differential crossing strategy is introduced, and a method for generating a variation population comprises the following steps:
Figure RE-RE-GDA0003772857940000031
where F denotes the difference coefficient, r3, r4 are random integers between 1 and NP
After obtaining the variant population, performing cross operation with the original population to obtain a cross population:
Figure RE-RE-GDA0003772857940000032
the invention has the beneficial effects that:
according to the sensor layout optimization method provided by the invention, a wireless sensor layout optimization model comprehensively considering conditions such as the coverage weight of each grid point in the raw tobacco stack, the sensing radius of the sensor and the like is designed and established, and an improved particle swarm algorithm is used, so that the better solving capability is realized when the optimal fitness function value is solved, and a certain improvement is realized in the convergence rate.
The invention aims to solve the problems of overhigh cost of the arrangement of the current sensor, lack of monitoring of tobacco leaf mildew information and the like. The layout optimization with the maximum coverage rate is realized, and the temperature and humidity change inside the cigarette stack is strictly monitored.
Drawings
FIG. 1 is a flow chart of an optimization algorithm of the present invention
FIG. 2 is a graph of a single-run objective function iteration
FIG. 3 is a graph of 15 iterations of the mean of the running objective function
FIG. 4 is a comparison graph of position optimization for two algorithms
FIG. 5 shows the result of temperature prediction
FIG. 6 is a comparison graph of two optimized sensor positions of the algorithm after the second optimization
The specific implementation mode is as follows:
in order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention.
An improved optimization method of a particle swarm algorithm for wireless sensor layout comprises the following steps: the method comprises the following steps:
the method comprises the following steps: with tobacco maintenance of a tobacco logistics center as a background, a wireless sensor model is established as follows:
Figure RE-RE-GDA0003772857940000041
Figure RE-RE-GDA0003772857940000042
where R is the sensing radius of the wireless sensor,
Figure RE-RE-GDA0003772857940000043
the time length of the interval is monitored twice, alpha is the thermal diffusivity of the tobacco leaves, lambda is the heat conductivity coefficient of the tobacco leaves, C V Is a volumetric specific heat and C V ＝ρ·C P 。
Random sensor position and random cigarette stack grid point
Figure RE-RE-GDA0003772857940000044
The position of (d) is expressed as follows by using Euclidean distance:
Figure RE-RE-GDA0003772857940000045
wherein
Figure RE-RE-GDA0003772857940000046
Is a collection of grid points in the inner space of the raw tobacco stack,
Figure RE-RE-GDA0003772857940000047
for any grid point
Figure RE-RE-GDA0003772857940000048
At a position in the space of the stack of raw cigarettes,
Figure RE-RE-GDA0003772857940000049
is a collection of wireless sensors in the raw tobacco stack,
Figure RE-RE-GDA00037728579400000410
is an arbitrary sensor
Figure RE-RE-GDA00037728579400000411
In the raw tobacco stack space.
Defining the coverage weight of each grid point in the raw tobacco stack, namely:
Figure RE-RE-GDA00037728579400000412
Figure RE-RE-GDA0003772857940000051
wherein C is 0 、C 1 、C 2 As a coefficient, T is the storage temperature/. degree.C., ln (u) i ) Is the specific growth rate of the ith grid point affected by the temperature of that point.
Defining the weight of coverage of the sensor to the grid points in the raw tobacco stack, namely:
Figure RE-RE-GDA0003772857940000052
Figure RE-RE-GDA0003772857940000053
wherein
Figure RE-RE-GDA0003772857940000054
For the weight of coverage of the grid points by sensor j in the raw tobacco stack,
Figure RE-RE-GDA0003772857940000055
the variable is 0-1, when the distance from any grid position point in the raw tobacco stack to the sensor j is less than the sensing radius of the sensor
Figure RE-RE-GDA0003772857940000056
Otherwise
Figure RE-RE-GDA0003772857940000057
The total coverage rate of the wireless sensor to the raw tobacco stack is as follows:
Figure RE-RE-GDA0003772857940000058
the method uses a small number of wireless sensors to monitor as much as possible of temperature and humidity information of the cigarette stacks, and the optimization target is as follows:
Figure RE-RE-GDA0003772857940000059
the number of wireless sensors arranged cannot exceed the maximum upper limit of the layout of each raw tobacco stack:
Figure RE-RE-GDA00037728579400000510
wherein
Figure RE-RE-GDA00037728579400000511
Upper limit for maximum number of raw tobacco stacks which can be arranged for a given enterprise
The arrangement that wireless sensor followed should be inside former cigarette buttress, can not surpass outside former cigarette buttress space:
Figure RE-RE-GDA00037728579400000512
wherein
Figure RE-RE-GDA00037728579400000513
And
Figure RE-RE-GDA00037728579400000514
respectively arranging limit limits of the wireless sensors in the cigarette stack space;
the minimum distance of any two wireless sensors inside the raw tobacco stack is limited as follows:
Figure RE-RE-GDA00037728579400000515
wherein
Figure RE-RE-GDA00037728579400000516
As the distance between any wireless sensors
Step two, solving the model by using an improved particle swarm algorithm (as shown in figure 1)
In the improved particle swarm optimization, a differential crossing strategy and a foraging selection strategy are introduced, and the optimization steps are as follows:
step 2.1: initializing parameters, and generating initial population by random mode
Step 2.2: calculating fitness function values of individuals in the population, updating individual extreme values and global extreme values, and storing corresponding extreme value points
Step 2.3: and copying the structure and information of the population to obtain a new population, and performing differential cross operation on the new population instead of the original population.
Step 2.4: and updating the speed of each individual in the original population, and reassigning the speed violating the boundary condition.
Step 2.5: and updating the position of each individual in the original population, and reassigning the position violating the boundary condition.
Step 2.6: and executing a differential crossing strategy on each individual in the new population to generate a crossing population.
Step 2.7: and combining the updated cross population and the original population, sequencing the fitness values, and selecting the better individual to enter the next iteration.
Step 2.8: the loop is exited when the maximum number of iterations is reached, otherwise, the procedure returns to step 2.2
A differential crossing strategy is introduced, and a method for generating a variation population comprises the following steps:
Figure RE-RE-GDA0003772857940000061
wherein F represents a difference coefficient, r3, r4 is a random integer between 1 and NP
After obtaining the variant population, performing cross operation with the original population to obtain a cross population:
Figure RE-RE-GDA0003772857940000062
introduction of foraging selection strategy
Before the position is updated, the structure and the information of the original population are completely copied to obtain a new population, the new population replaces the original population to carry out difference and intersection, and the original population still executes the updating strategy of the traditional particle swarm algorithm. And after the position is updated, combining the new population with the original population to form a selected population with the population scale of 2NP, sorting the fitness values, selecting better NP individuals by a greedy strategy, and entering next iteration.
To verify the superiority of the improved algorithm (IPSO), the comparison results are shown in fig. 2 and 3, in comparison with the PSO algorithm. It can be seen that the IPSO algorithm is much higher than the PSO algorithm, regardless of whether the objective function is run once or the average of the objective function is run 15 times
And thirdly, in order to further optimize the position of the sensor in the raw cigarette stack, predicting the temperature data by adopting an LSTM prediction algorithm to realize secondary optimization of the position of the sensor, wherein the prediction result is shown in figure 5.
And (5) utilizing the predicted result, and optimizing the layout scheme of the wireless sensor again, as shown in fig. 6.
The foregoing detailed description of the invention is merely exemplary in nature and is not intended to limit the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention.

Claims (5)

1. A raw cigarette tray wireless sensor layout optimization method based on an improved particle swarm algorithm is characterized by comprising the following steps: the method comprises the following steps:
step 1, establishing a wireless sensor model;
step 2, solving the model by using an improved particle swarm algorithm;
and 3, optimizing the position of the sensor in the raw tobacco stack, predicting temperature information through an LSTM algorithm, and performing secondary optimization on a sensor layout scheme.
2. The method for optimizing the layout of the wireless sensors of the raw cigarette trays based on the improved particle swarm optimization according to claim 1, wherein the method comprises the following steps: the step 1. the specific way of establishing the wireless sensor model is as follows:
Figure FDA0003562596320000011
Figure FDA0003562596320000012
where R is the sensing radius of the wireless sensor,
Figure FDA0003562596320000013
for monitoring the time length of the interval twice, alpha is the thermal diffusivity of the tobacco leaves, lambda is the thermal conductivity of the tobacco leaves, C V Is a volumetric specific heat and C V ＝ρ·C P 。
Random sensor position and random cigarette stack grid point
Figure FDA0003562596320000014
The position of (d) is expressed as follows by using Euclidean distance:
Figure FDA0003562596320000015
wherein
Figure FDA0003562596320000016
Is a collection of grid points in the inner space of the raw tobacco stack,
Figure FDA0003562596320000017
for any grid point
Figure FDA0003562596320000018
At a position in the space of the stack of raw cigarettes,
Figure FDA0003562596320000019
is a collection of wireless sensors in the raw tobacco stack,
Figure FDA00035625963200000110
is an arbitrary sensor
Figure FDA00035625963200000111
In the raw tobacco stack space.
Defining the coverage weight of each grid point in the raw tobacco stack, namely:
Figure FDA00035625963200000112
Figure FDA00035625963200000113
wherein C is 0 、C 1 、C 2 As a coefficient, T is the storage temperature/. degree.C., ln (u) i ) Is the specific growth rate of the ith grid point affected by the temperature of that point.
Defining the weight of coverage of the sensor to the grid points in the raw tobacco stack, namely:
Figure FDA0003562596320000021
Figure FDA0003562596320000022
wherein
Figure FDA0003562596320000023
For the weight of coverage of the grid points by sensor j in the raw tobacco stack,
Figure FDA0003562596320000024
the distance between any grid position point in the raw tobacco stack and the sensor j is less than the perception of the sensor, and the distance is 0-1 variableAt radius of time
Figure FDA0003562596320000025
Otherwise
Figure FDA0003562596320000026
The total coverage rate of the wireless sensor to the raw tobacco stack is as follows:
Figure FDA0003562596320000027
3. the method for optimizing the layout of the wireless sensors of the raw cigarette trays based on the improved particle swarm optimization according to claim 1, wherein the method comprises the following steps: the step 2 is detailed as follows; a differential crossing strategy is introduced, and a method for generating a variation population comprises the following steps:
Figure RE-FDA0003772857930000027
where F denotes the difference coefficient and r3, r4 is a random integer between 1 and NP. After obtaining the variant population, performing cross operation with the original population to obtain a cross population:
Figure RE-FDA0003772857930000028
4. the method for optimizing the layout of the wireless sensors of the raw cigarette trays based on the improved particle swarm optimization according to claim 1, wherein the method comprises the following steps: the step 3: introducing a foraging selection strategy method. Before the position is updated, the structure and the information of the original population are completely copied to obtain a new population, the new population replaces the original population to carry out difference and intersection, and the original population still executes the updating strategy of the traditional particle swarm algorithm. And after the position is updated, combining the new population with the original population to form a selected population with the population scale of 2NP, sorting the fitness values, selecting better NP individuals by a greedy strategy, and entering next iteration.
5. The method for optimizing the layout of the wireless sensors of the raw cigarette trays based on the improved particle swarm optimization according to claim 2, wherein the method comprises the following steps: solving the step 2, and introducing a differential crossing strategy and a foraging selection strategy into the [0029] improved particle swarm optimization, wherein the algorithm comprises the following steps:
step 2.1: initializing parameters, and generating an initial population in a random mode;
step 2.2: calculating fitness function values of individuals in the population, updating individual extreme values and global extreme values, and storing corresponding extreme values;
step 2.3: copying the structure and information of the population to obtain a new population, and performing differential cross operation on the new population instead of the original population;
step 2.4: updating the speed of each individual in the original population, and reassigning the speed violating the boundary condition;
step 2.5: updating the position of each individual in the original population, and reassigning the position violating the boundary condition;
step 2.6: and executing a differential crossing strategy on each individual in the new population to generate a crossing population.
Step 2.7: combining the updated cross population and the original population, sequencing the fitness values, and selecting a better individual to enter next iteration;
step 2.8: and (3) exiting the loop when the maximum iteration times are reached, otherwise returning to the step 2.2 and introducing a differential crossing strategy, wherein the method for generating the variation population comprises the following steps:
Figure FDA0003562596320000031
wherein F represents a difference coefficient, r3, r4 is a random integer between 1 and NP
After obtaining the variant population, performing cross operation with the original population to obtain a cross population:
Figure FDA0003562596320000032
CN202210308361.7A 2022-03-24 2022-03-24 Raw cigarette tray wireless sensor layout optimization method based on improved particle swarm optimization Pending CN114980131A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210308361.7A CN114980131A (en) 2022-03-24 2022-03-24 Raw cigarette tray wireless sensor layout optimization method based on improved particle swarm optimization

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210308361.7A CN114980131A (en) 2022-03-24 2022-03-24 Raw cigarette tray wireless sensor layout optimization method based on improved particle swarm optimization

Publications (1)

Publication Number Publication Date
CN114980131A true CN114980131A (en) 2022-08-30

Family

ID=82975477

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210308361.7A Pending CN114980131A (en) 2022-03-24 2022-03-24 Raw cigarette tray wireless sensor layout optimization method based on improved particle swarm optimization

Country Status (1)

Country Link
CN (1) CN114980131A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102222919A (en) * 2011-05-19 2011-10-19 西南交通大学 Power system reactive power optimization method based on improved differential evolution algorithm
CN107277830A (en) * 2017-08-03 2017-10-20 扬州大学 A kind of wireless sensor network node dispositions method based on particle group optimizing and mutation operator
CN110062389A (en) * 2019-04-19 2019-07-26 江西理工大学 Sensor network nodes Optimization deployment method based on improved differential evolution algorithm
CN111103854A (en) * 2019-12-10 2020-05-05 云南昆船设计研究院有限公司 System and method for improving production stability of tobacco cut-tobacco drier
CN113837428A (en) * 2021-06-29 2021-12-24 红云红河烟草(集团)有限责任公司 Sensor optimization layout and temperature and humidity prediction algorithm for raw tobacco maintenance
CN114205849A (en) * 2021-12-09 2022-03-18 华中科技大学 Wireless sensor network node credible coverage deployment optimization method based on integer programming

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102222919A (en) * 2011-05-19 2011-10-19 西南交通大学 Power system reactive power optimization method based on improved differential evolution algorithm
CN107277830A (en) * 2017-08-03 2017-10-20 扬州大学 A kind of wireless sensor network node dispositions method based on particle group optimizing and mutation operator
CN110062389A (en) * 2019-04-19 2019-07-26 江西理工大学 Sensor network nodes Optimization deployment method based on improved differential evolution algorithm
CN111103854A (en) * 2019-12-10 2020-05-05 云南昆船设计研究院有限公司 System and method for improving production stability of tobacco cut-tobacco drier
CN113837428A (en) * 2021-06-29 2021-12-24 红云红河烟草(集团)有限责任公司 Sensor optimization layout and temperature and humidity prediction algorithm for raw tobacco maintenance
CN114205849A (en) * 2021-12-09 2022-03-18 华中科技大学 Wireless sensor network node credible coverage deployment optimization method based on integer programming

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
丁旭;吴晓蓓;黄成;: "基于改进粒子群算法和特征点集的无线传感器网络覆盖问题研究", 电子学报, no. 04 *
吴意乐;何庆;徐同伟;: "改进自适应粒子群算法在WSN覆盖优化中的应用", 传感技术学报, no. 04 *
崔频;王敏;: "一种虚拟力导向遗传算法的无线传感器网络优化部署策略", 电子设计工程, no. 07 *

Similar Documents

Publication Publication Date Title
Wang et al. Balancing risk and cost in fuzzy economic dispatch including wind power penetration based on particle swarm optimization
Wang et al. Environmental/economic power dispatch using a fuzzified multi-objective particle swarm optimization algorithm
Tavakkoli-Moghaddain et al. Facilities layout design by genetic algorithms
CN109862532B (en) Rail transit state monitoring multi-sensor node layout optimization method and system
CN111553469B (en) Wireless sensor network data fusion method, device and storage medium
CN108038306A (en) A kind of method of power boiler burning modeling and optimization towards magnanimity high dimensional data
CN102238686A (en) Wireless sensor network routing method for modeling quantum genetic algorithm
CN104166630B (en) Optimization caching laying method based on prediction in a kind of content oriented central site network
Asadi et al. Sustainable building design: a review on recent metaheuristic methods
CN106789320A (en) A kind of multi-species cooperative method for optimizing wireless sensor network topology
CN114980131A (en) Raw cigarette tray wireless sensor layout optimization method based on improved particle swarm optimization
CN110516785A (en) A kind of solution double-layer satellite network hybrid algorithm based on population and whale group
CN113065631A (en) Parameter optimization method based on improved competition group algorithm
Damghanijazi et al. Meta-Heuristic Approaches for Solving Travelling Salesman Problem.
CN117236746A (en) Air conditioner load adjustable potential evaluation method
CN116702613A (en) Multi-objective optimization method and system for product performance and sintering energy consumption of ternary positive electrode material
CN113837428B (en) Sensor optimization layout and temperature and humidity prediction algorithm for raw smoke maintenance
CN115526092A (en) Power load prediction method and device
CN107330302A (en) The biological die body reconstructing method of joint Memetic algorithms and S system
CN114398748A (en) Electric heat storage device planning method and system based on hydraulic calculation and double-layer optimization
CN116540552B (en) Control parameter optimization method for EMS (electromagnetic mode) magnetic levitation train
CN114048668B (en) Comprehensive energy-oriented wireless sensor wheel value method and system
Zhang et al. Improved Wolf Pack Algorithm for Solving Traveling Salesman Problem.
CN115660337A (en) Cascade reservoir group power generation optimal scheduling method based on improved intelligent water drop algorithm
CN114844039B (en) Quantum approximation state-based demand side response collaborative optimization method

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