CN107644267A - A kind of green house control Decision fusion method based on D S evidence theories - Google Patents

A kind of green house control Decision fusion method based on D S evidence theories Download PDF

Info

Publication number
CN107644267A
CN107644267A CN201710812597.3A CN201710812597A CN107644267A CN 107644267 A CN107644267 A CN 107644267A CN 201710812597 A CN201710812597 A CN 201710812597A CN 107644267 A CN107644267 A CN 107644267A
Authority
CN
China
Prior art keywords
mrow
msub
mtr
mtd
decision
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
CN201710812597.3A
Other languages
Chinese (zh)
Other versions
CN107644267B (en
Inventor
孙力帆
张雅媛
郑国强
付主木
王旭栋
冀保峰
普杰信
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.)
Henan University of Science and Technology
Original Assignee
Henan University of Science and Technology
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 Henan University of Science and Technology filed Critical Henan University of Science and Technology
Priority to CN201710812597.3A priority Critical patent/CN107644267B/en
Publication of CN107644267A publication Critical patent/CN107644267A/en
Application granted granted Critical
Publication of CN107644267B publication Critical patent/CN107644267B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A kind of green house control Decision fusion method based on D S evidence theories, comprises the following steps：Step 1: extracting the outlier in greenhouse inner sensor measuring value using box traction substation, and outlier is modified；Step 2: carrying out Cluster-Fusion to revised measuring value, obtain clustering value set；Step 3: decision-making distribution is carried out to cluster value by D S evidence theories with decision criterion value set using value set is clustered.The present invention provides a kind of green house control Decision fusion method based on D S evidence theories, can effectively lift the fusion accuracy of achievement data and decision-making confidence level in greenhouse, while reduce risk of policy making.

Description

A kind of green house control Decision fusion method based on D-S evidence theory
Technical field
The present invention relates to wireless sensor network data processing and fusion field, specifically one kind is based on D-S evidences Theoretical green house control Decision fusion method.
Background technology
Greenhouse, also known as greenhouse, referring to has the facilities such as cold-proof, heating and printing opacity, and the room of thermophilous is cultivated for winter.Not In the season of suitable for plant growth, breeding time and increase yield can be provided, are used for low temperature season warm season vegetable, flowers, forest etc. Plant culture or nursery etc..Existing greenhouse generally includes the wound membrane for closing, the blower fan for ventilation and for improving temperature The wet curtain of indoor humidity.Traditional green house control method is mostly that the ambient parameter in greenhouse is directly measured using sensor, Then by after compared with the threshold value set, by controlling wound membrane, blower fan or the action of wet curtain, realizing and environment being joined Several adjustment, verified finally by the measuring value of sensor.But because the environment in greenhouse is extremely complex, in difference Position, the measurement of sensor may be far from each other, and this can cause control system to produce antipodal control instruction, and then Cause the environmental disorder in greenhouse.
With the fast development of science and technology and significantly improving for living standard, modern intelligent greenhouse environmental system is by more Carry out more concerns.In order to save human and material resources, financial resources, sensor network turns into people's primary selection, with sensor network from The sensor network information fusion do not opened is even more to be widely applied, such as target identification, target following and artificial intelligence etc. Field.Due to the influence of various external environmental factors and hardware, the data that sensor measures often have certain uncertainty, D-S (Dempster-Shafer) evidence theory is the probabilistic good method of the processing praised highly, and has been many expert system institutes Using, and have considerable effect in decision problem.But when height conflict between evidence be present, D-S evidences reason Often repel each other by result with convention, the result of mistake can cause the Wrong control to greenhouse, cause to temperature The destruction of room function.
The content of the invention
In order to solve deficiency of the prior art, the present invention provides a kind of green house control decision-making based on D-S evidence theory Fusion method, the fusion accuracy of achievement data and decision-making confidence level in greenhouse can be effectively lifted, while reduce decision-making wind Danger.
To achieve these goals, the concrete scheme that uses of the present invention for：
A kind of green house control Decision fusion method based on D-S evidence theory, comprises the following steps：
Step 1: extracting the outlier in greenhouse inner sensor measuring value using box traction substation, and outlier is modified；
Step 2: carrying out Cluster-Fusion to revised measuring value, obtain clustering value set；
Step 3: decision-making distribution is carried out to cluster value by D-S evidence theory with decision criterion value set using value set is clustered.
It is to the modification method of outlier in the step 1：
Step S1, outlier x and decision criterion value x is calculatedmThe distance between Δ=| xm-x|；
If step S2, Δ≤5, revised measuring value
If step S3,5 ＜ Δ≤10, revised measuring valueIn formula
If step S4,10 ＜ Δ≤15, revised measuring valueIn formula
If step S5, revised measuring valueOutlier is remained as, then repeat step S1~S4 is modified again.
Clustering Ensemble Approaches: An in the step 2 is that minimum is searched in the mahalanobis distance matrix of revised measuring value Distance value, and clustered according to lowest distance value.
In the step 3, if at a time revised measuring value isAverage is u= (u1,u2,···,un)T, then covariance matrix be
Mahalanobis distance is tried to achieve according to covariance matrix：
The specific method of cluster is searches lowest distance value in D, and by two data aggregates corresponding to this lowest distance value For one kind, new mahalanobis distance matrix is then generated, and is clustered again, by clustering several times, obtains clustering value set.
If cluster value set X is expressed asDecision criterion value set ω is expressed as (ω1,ω2,···, ωn), the identification framework Θ of D-S evidence theory is expressed as (L1, L2..., Ln), (L1, L2..., Ln) represent to divide respectively The decision-making of dispensing cluster value, (L1, L2..., Ln) and (ω1,ω2,···,ωn) correspond, specific decision-making distribution Method is：
Step T1, to cluster valueCalculateWith average ωkDistanceAndAnd ωk+1Distance
Step T2, d is compared1With d2；
If d1＞ d2, thenClose to ωk+1,To decision-making Lk+1More trust, the probability distribution function to each decision-making is
(1-d in formula1) representWith ωkSimilarity, (1-d2) representWith ωk+1Similarity,With The weighted factor of probability distribution function, ρ are represented respectively1With ρ2For restrictive factor, for prevent degree of belief it is excessive deviate it is actual；
If d1＜ d2, thenIt is comparatively close to ωk,To decision-making LkMore trust, the probability distribution function to each decision-making is
(1-d in formula1) representWith ωkSimilarity, (1-d2) representWith ωk+1Similarity,With The weighted factor of probability distribution function, ρ are represented respectively1With ρ2For restrictive factor, for prevent degree of belief it is excessive deviate it is actual；
If d1=d2, thenWith ωkAnd ωk+1Similarity it is identical, to the probability distribution function and d of each decision-making1＞ d2Feelings Condition or d1＜ d2In the case of any partition function it is identical；
Step T3, m (Θ)=1-m (L are calculated1)-m(L2)-……-m(Ln), m (Θ) is the uncertainty to metric data；
Step T4, repeat step T1 to T3, willWith ωk+2~ωnIt is compared one by one and calculates the probability assignments letter of each decision-making Number；
Step T5, repeat step T1 to T4 is right one by oneCarry out decision-making distribution.
The restrictive factor ρ1=5, ρ2=3.
Beneficial effect：
1st, the data that the present invention is handled by outlier and Cluster-Fusion gathers to sensor optimize, and effectively reduce measurement number According to conflict spectrum, help to make high-speed decision；
2nd, the fusion accuracy of achievement data and decision-making confidence level in greenhouse can be effectively lifted, while reduces risk of policy making.
Brief description of the drawings
Fig. 1 is the flow chart of embodiment of the present invention；
Fig. 2 is raw measurement data box traction substation；
Fig. 3 is the revised box traction substation of raw measurement data；
Fig. 4 be under minimum range correct after/reject outlier after cluster value comparative result.
Embodiment
Embodiments of the present invention are illustrated below according to accompanying drawing.
A kind of green house control Decision fusion method based on D-S evidence theory, as shown in figure 1, comprising the following steps：
Step 1: the outlier in greenhouse inner sensor measuring value is extracted using box traction substation, and profit is modified to outlier；
Step 2: carrying out Cluster-Fusion to revised measuring value, obtain clustering value set；
Step 3: probability point is carried out to each subset of the identification framework of D-S evidence theory using cluster value and decision criterion value Match somebody with somebody, and establish the Decision fusion framework based on D-S evidence theory, decision-making is carried out by adjustment of the framework to greenhouse.Decision-making base Quasi- value is generated by expert system, is that the general parameter in green house control field compares standard, is prior art, herein no longer Repeat.
The method that the outlier in box traction substation extraction sensor measuring value is utilized in the step 1 is the data that will be measured Arrange from small to large, the data for defining the 50%th are median Q2, the data for defining the 25%th are lower quartile Q1, Q1Also may be used To be positioned as the minimum value of measuring value and Q2Between median, define the 75%th data be upper quartile Q3, Q3Can also It is positioned as the maximum and Q of measuring value2Between median.Then outlier is defined as greater than (Q3+1.5IQR) or less than (Q1- 1.5IQR) measuring value.Modification method to outlier is：
Step S1, outlier x and decision criterion value x is calculatedmThe distance between Δ=| xm-x|；
If step S2, Δ≤5, revised measuring value
If step S3,5 ＜ Δ≤10, revised measuring valueIn formula
If step S4,10 ＜ Δ≤15, revised measuring valueIn formula
If step S5, revised measuring valueOutlier is remained as, then repeat step S1~S4 is modified again.
Clustering Ensemble Approaches: An in the step 2 is that minimum is searched in the mahalanobis distance matrix of revised measuring value Distance value, and clustered according to lowest distance value.If at a time revised measuring value is Average is u=(u1,u2,···,un)T, then covariance matrix be
Mahalanobis distance is tried to achieve according to covariance matrix：
The specific method of cluster is searches lowest distance value in D, and by two data aggregates corresponding to this lowest distance value For one kind, new mahalanobis distance matrix is then generated, and is clustered again, by clustering several times, obtains clustering value set.
In step 3, if cluster value set X is expressed asDecision criterion value set ω is expressed as (ω1, ω2,···,ωn), the identification framework Θ of D-S evidence theory is expressed as (L1, L2..., Ln), (L1, L2..., Ln) The decision-making of cluster value, (L are distributed in expression respectively1, L2..., Ln) and (ω1,ω2,···,ωn) correspond, specifically Decision-making distribution method be：
Step T1, to cluster valueCalculateWith average ωkDistanceAndAnd ωk+1Distance
Step T2, d is compared1With d2；
If d1＞ d2, thenClose to ωk+1,To decision-making Lk+1More trust, the probability distribution function to each decision-making is
(1-d in formula1) representWith ωkSimilarity, (1-d2) representWith ωk+1Similarity,With The weighted factor of probability distribution function, ρ are represented respectively1With ρ2For restrictive factor, for prevent degree of belief it is excessive deviate it is actual；
If d1＜ d2, thenIt is comparatively close to ωk,To decision-making LkMore trust, the probability distribution function to each decision-making is
(1-d in formula1) representWith ωkSimilarity, (1-d2) representWith ωk+1Similarity,WithThe weighted factor of probability distribution function, ρ are represented respectively1With ρ2For restrictive factor, ρ1=5, ρ2=3, for preventing letter Appoint and spend big deviation reality；
If d1=d2, thenWith ωkAnd ωk+1Similarity it is identical, to the probability distribution function and d of each decision-making1＞ d2Feelings Condition or d1＜ d2In the case of any partition function it is identical；
Step T3, m (Θ)=1-m (L are calculated1)-m(L2)-……-m(Ln), m (Θ) is the uncertainty to metric data；
Step T4, repeat step T1 to T3, willWith ωk+2~ωnIt is compared one by one and calculates the probability assignments letter of each decision-making Number；
Step T5, repeat step T1 to T4 is right one by oneCarry out decision-making distribution.
In order to verify the fusion accuracy and decision-making confidence level of the present invention, following emulation experiment is set：
1st, in order to reduce the complexity of emulation, yojan is carried out to greenhouse environment parameter, retening temperature after yojan (/ DEG C), illuminance (/klx), three parameters of carbon dioxide volume fraction (uL/L)；
2nd, 2, time of measuring is set as six moment daily in the morning, afternoon and evening, when being 10 respectively, 12 when, 14 when, 16 when, 18 when and 20 When；Each moment is to each 26 data of parameter measurement；
3rd, the result of decision is divided into four, is to open wound membrane, open wound membrane and start blower fan, start blower fan and wet curtain, nothing respectively Action, represented respectively with m (1), m (2), m (3) and m (4).
Simulation result is as follows.
Analyzed by taking temperature as an example, the box traction substation of six moment measurement temperatures is as shown in Figure 2, it can be seen that each moment There is outlier, the box traction substation of temperature is as shown in figure 3, without the original distribution of change, noon temperature after amendment after amendment Highest, dusk temperature is minimum, overall that normal distribution is presented.Simultaneously it can also be seen that the width of box traction substation casing differs, median Position it is also different, this depend on measurement data degree of scatter and sensor accuracy.It is right after the completion of measurement data amendment The parameter at each moment is clustered, as a result as shown in figure 4, by can relatively be seen with the cluster value after rejecting outlier after amendment Go out to correct outlier and consistent be all intended to decision criterion value with the cluster trend for rejecting outlier.
Probability assignments result in the emulation experiment of table 1
Probability assignments result in emulation experiment is as shown in table 1, and t, c, i are respectively temperature, illuminance and carbon dioxide body in table Fraction, evidence is used as in D-S evidence theory.As can be seen from Table 1, uncertain precision energy of the present invention to metric data Enough reach 10-5~10-4, the convergence rate being exceedingly fast is shown, significantly reduces the uncertainty between evidence, is advantageous to do Go out high-speed decision.
It should also be noted that, herein, such as first and second or the like relational terms are used merely to one Entity or operation make a distinction with another entity or operation, and not necessarily require or imply between these entities or operation Any this actual relation or order be present.Moreover, term " comprising ", "comprising" or its any other variant are intended to contain Lid nonexcludability includes, so that process, method, article or equipment including a series of elements not only will including those Element, but also the other element including being not expressly set out, or it is this process, method, article or equipment also to include Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that Other identical element also be present in process, method, article or equipment including the key element.
The foregoing description of the disclosed embodiments, professional and technical personnel in the field are enable to realize or using the present invention. A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one The most wide scope caused.

Claims (6)

  1. A kind of 1. green house control Decision fusion method based on D-S evidence theory, it is characterised in that：Comprise the following steps：
    Step 1: extracting the outlier in greenhouse inner sensor measuring value using box traction substation, and outlier is modified；
    Step 2: carrying out Cluster-Fusion to revised measuring value, obtain clustering value set；
    Step 3: decision-making distribution is carried out to cluster value by D-S evidence theory with decision criterion value set using value set is clustered.
  2. A kind of 2. green house control Decision fusion method based on D-S evidence theory as claimed in claim 1, it is characterised in that： It is to the modification method of outlier in the step 1：
    Step S1, outlier x and decision criterion value x is calculatedmThe distance between Δ=| xm-x|；
    If step S2, Δ≤5, revised measuring value
    If step S3,5 ＜ Δ≤10, revised measuring valueIn formula
    If step S4,10 ＜ Δ≤15, revised measuring valueIn formula
    If step S5, revised measuring valueOutlier is remained as, then repeat step S1~S4 is modified again.
  3. A kind of 3. green house control Decision fusion method based on D-S evidence theory as claimed in claim 1, it is characterised in that： Clustering Ensemble Approaches: An in the step 2 is to search lowest distance value in the mahalanobis distance matrix of revised measuring value, and Clustered according to lowest distance value.
  4. A kind of 4. green house control Decision fusion method based on D-S evidence theory as claimed in claim 3, it is characterised in that： If at a time revised measuring value isAverage is u=(u1,u2,···,un)T, then association side Poor matrix is
    Mahalanobis distance is tried to achieve according to covariance matrix：
    The specific method of cluster is searches lowest distance value in D, and by two data aggregates corresponding to this lowest distance value For one kind, new mahalanobis distance matrix is then generated, and is clustered again, by clustering several times, obtains clustering value set.
  5. A kind of 5. green house control Decision fusion method based on D-S evidence theory as claimed in claim 1, it is characterised in that：
    In the step 3, if cluster value set X is expressed asDecision criterion value set ω is expressed as (ω1, ω2,···,ωn), the identification framework Θ of D-S evidence theory is expressed as (L1, L2..., Ln), (L1, L2..., Ln) The decision-making of cluster value, (L are distributed in expression respectively1, L2..., Ln) and (ω1,ω2,···,ωn) correspond, specifically Decision-making distribution method be：
    Step T1, to cluster valueCalculateWith average ωkDistanceAndAnd ωk+1Distance
    Step T2, d is compared1With d2；
    If d1＞ d2, thenClose to ωk+1,To decision-making Lk+1More trust, the probability distribution function to each decision-making is
    <mrow> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mn>......</mn> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>-</mo> <msub> <mi>d</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>&amp;CenterDot;</mo> <msup> <mi>e</mi> <mrow> <mo>-</mo> <mfrac> <mrow> <mo>|</mo> <mrow> <msub> <mover> <mi>x</mi> <mo>~</mo> </mover> <mn>1</mn> </msub> <mo>-</mo> <msub> <mi>&amp;omega;</mi> <mi>k</mi> </msub> </mrow> <mo>|</mo> </mrow> <mrow> <msub> <mi>&amp;omega;</mi> <mrow> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>&amp;omega;</mi> <mi>k</mi> </msub> </mrow> </mfrac> <mo>&amp;CenterDot;</mo> <msub> <mi>&amp;rho;</mi> <mn>2</mn> </msub> </mrow> </msup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mrow> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>-</mo> <msub> <mi>d</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mo>&amp;CenterDot;</mo> <msup> <mi>e</mi> <mrow> <mo>-</mo> <mfrac> <mrow> <mo>|</mo> <mrow> <msub> <mover> <mi>x</mi> <mo>~</mo> </mover> <mn>1</mn> </msub> <mo>-</mo> <msub> <mi>&amp;omega;</mi> <mrow> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> </mrow> <mo>|</mo> </mrow> <mrow> <msub> <mi>&amp;omega;</mi> <mrow> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>&amp;omega;</mi> <mi>k</mi> </msub> </mrow> </mfrac> <mo>&amp;CenterDot;</mo> <msub> <mi>&amp;rho;</mi> <mn>1</mn> </msub> </mrow> </msup> </mrow> </mtd> </mtr> <mtr> <mtd> <mn>......</mn> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mrow> <mi>n</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mi>n</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>;</mo> </mrow>
    (1-d in formula1) representWith ωkSimilarity, (1-d2) representWith ωk+1Similarity,With The weighted factor of probability distribution function, ρ are represented respectively1With ρ2For restrictive factor, for prevent degree of belief it is excessive deviate it is actual；
    If d1＜ d2, thenIt is comparatively close to ωk,To decision-making LkMore trust, the probability distribution function to each decision-making is
    <mrow> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mn>......</mn> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>-</mo> <msub> <mi>d</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>&amp;CenterDot;</mo> <msup> <mi>e</mi> <mrow> <mo>-</mo> <mfrac> <mrow> <mo>|</mo> <mrow> <msub> <mover> <mi>x</mi> <mo>~</mo> </mover> <mn>1</mn> </msub> <mo>-</mo> <msub> <mi>&amp;omega;</mi> <mi>k</mi> </msub> </mrow> <mo>|</mo> </mrow> <mrow> <msub> <mi>&amp;omega;</mi> <mrow> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>&amp;omega;</mi> <mi>k</mi> </msub> </mrow> </mfrac> <mo>&amp;CenterDot;</mo> <msub> <mi>&amp;rho;</mi> <mn>2</mn> </msub> </mrow> </msup> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mrow> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>-</mo> <msub> <mi>d</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mo>&amp;CenterDot;</mo> <msup> <mi>e</mi> <mrow> <mo>-</mo> <mfrac> <mrow> <mo>|</mo> <mrow> <msub> <mover> <mi>x</mi> <mo>~</mo> </mover> <mn>1</mn> </msub> <mo>-</mo> <msub> <mi>&amp;omega;</mi> <mrow> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> </mrow> <mo>|</mo> </mrow> <mrow> <msub> <mi>&amp;omega;</mi> <mrow> <mi>k</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>&amp;omega;</mi> <mi>k</mi> </msub> </mrow> </mfrac> <mo>&amp;CenterDot;</mo> <msub> <mi>&amp;rho;</mi> <mn>1</mn> </msub> </mrow> </msup> </mrow> </mtd> </mtr> <mtr> <mtd> <mn>......</mn> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mrow> <mi>n</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>m</mi> <mrow> <mo>(</mo> <msub> <mi>L</mi> <mi>n</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mn>0</mn> </mrow> </mtd> </mtr> </mtable> </mfenced> <mo>;</mo> </mrow>
    (1-d in formula1) representWith ωkSimilarity, (1-d2) representWith ωk+1Similarity,With The weighted factor of probability distribution function, ρ are represented respectively1With ρ2For restrictive factor, for prevent degree of belief it is excessive deviate it is actual；
    If d1=d2, thenWith ωkAnd ωk+1Similarity it is identical, to the probability distribution function and d of each decision-making1＞ d2Situation Or d1＜ d2In the case of any partition function it is identical；
    Step T3, m (Θ)=1-m (L are calculated1)-m(L2)-……-m(Ln), m (Θ) is the uncertainty to metric data；
    Step T4, repeat step T1 to T3, willWith ωk+2~ωnIt is compared one by one and calculates the probability assignments letter of each decision-making Number；
    Step T5, repeat step T1 to T4 is right one by oneCarry out decision-making distribution.
  6. A kind of 6. green house control Decision fusion method based on D-S evidence theory as claimed in claim 5, it is characterised in that： The restrictive factor ρ1=5, ρ2=3.
CN201710812597.3A 2017-09-11 2017-09-11 Greenhouse control decision fusion method based on D-S evidence theory Active CN107644267B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710812597.3A CN107644267B (en) 2017-09-11 2017-09-11 Greenhouse control decision fusion method based on D-S evidence theory

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710812597.3A CN107644267B (en) 2017-09-11 2017-09-11 Greenhouse control decision fusion method based on D-S evidence theory

Publications (2)

Publication Number Publication Date
CN107644267A true CN107644267A (en) 2018-01-30
CN107644267B CN107644267B (en) 2020-04-24

Family

ID=61111086

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710812597.3A Active CN107644267B (en) 2017-09-11 2017-09-11 Greenhouse control decision fusion method based on D-S evidence theory

Country Status (1)

Country Link
CN (1) CN107644267B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110097296A (en) * 2019-05-16 2019-08-06 西南交通大学 The optimal urgent technique screening technique of basin burst water pollution accident, Decision System of Emergency
CN111193742A (en) * 2019-12-31 2020-05-22 广东电网有限责任公司 D-S evidence theory-based power communication network anomaly detection method
CN112785004A (en) * 2021-02-03 2021-05-11 中国计量大学 Greenhouse intelligent decision-making method based on rough set theory and D-S evidence theory

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101282243A (en) * 2008-03-05 2008-10-08 中科院嘉兴中心微系统所分中心 Method for recognizing distributed amalgamation of wireless sensor network
CN101996157A (en) * 2010-10-23 2011-03-30 山东科技大学 Multisource information fusion method in evidence high-conflict environment
CN106154182A (en) * 2016-08-26 2016-11-23 上海电力学院 A kind of based on the lithium battery method for diagnosing faults improving D S evidence theory
US20170063909A1 (en) * 2015-08-31 2017-03-02 Splunk Inc. Detection of Clustering in Graphs in Network Security Analysis

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101282243A (en) * 2008-03-05 2008-10-08 中科院嘉兴中心微系统所分中心 Method for recognizing distributed amalgamation of wireless sensor network
CN101996157A (en) * 2010-10-23 2011-03-30 山东科技大学 Multisource information fusion method in evidence high-conflict environment
US20170063909A1 (en) * 2015-08-31 2017-03-02 Splunk Inc. Detection of Clustering in Graphs in Network Security Analysis
CN106154182A (en) * 2016-08-26 2016-11-23 上海电力学院 A kind of based on the lithium battery method for diagnosing faults improving D S evidence theory

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王俊 等: "《融合粗糙集和证据理论的温室环境控制推理决策方法》", 《农业工程学报》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110097296A (en) * 2019-05-16 2019-08-06 西南交通大学 The optimal urgent technique screening technique of basin burst water pollution accident, Decision System of Emergency
CN110097296B (en) * 2019-05-16 2022-07-05 西南交通大学 Optimal emergency treatment technology screening method and emergency decision-making system for basin sudden water pollution accident
CN111193742A (en) * 2019-12-31 2020-05-22 广东电网有限责任公司 D-S evidence theory-based power communication network anomaly detection method
CN112785004A (en) * 2021-02-03 2021-05-11 中国计量大学 Greenhouse intelligent decision-making method based on rough set theory and D-S evidence theory

Also Published As

Publication number Publication date
CN107644267B (en) 2020-04-24

Similar Documents

Publication Publication Date Title
CN107644267A (en) A kind of green house control Decision fusion method based on D S evidence theories
Achour et al. Technological progresses in modern sustainable greenhouses cultivation as the path towards precision agriculture
Rezvani et al. IoT-based sensor data fusion for determining optimality degrees of microclimate parameters in commercial greenhouse production of tomato
CN107730006A (en) A kind of nearly zero energy consumption controller of building based on regenerative resource big data deep learning
CN110674947B (en) Spectral feature variable selection and optimization method based on Stacking integrated framework
CN108183488B (en) High-permeability distributed energy system intelligent pressure regulating method based on cluster division
CN108229732A (en) ExtremeLearningMachine wind speed ultra-short term prediction method based on error correction
CN109919239A (en) A kind of diseases and pests of agronomic crop intelligent detecting method based on deep learning
CN110119766A (en) A kind of multiple groups close the green pepper greenhouse temperature intelligence prior-warning device of intelligent model
CN106842914A (en) A kind of temperature control energy-saving processing method, apparatus and system
CN114662201B (en) Optimizing method for intelligent regulation and control of natural ventilation
CN106250979A (en) A kind of particle group optimizing method based on mutual information similarity Strategy
CN115453868B (en) Full-growth-period light intensity regulation and control method based on tomato light response difference characteristics
CN109656141A (en) Violation identification and machine behaviour control method, equipment, storage medium based on artificial intelligence technology
Shamshiri et al. Adaptive management framework for evaluating and adjusting microclimate parameters in tropical greenhouse crop production systems
Fan et al. Research on temperature prediction model in greenhouse based on improved SVR
CN107195297A (en) A kind of normalized TSP question flock of birds speech recognition system of fused data
Li et al. Determining optimal CO2 concentration of greenhouse tomato based on PSO-SVM
CN109041951A (en) A kind of agricultural breeding is mechanical and control method
CN108985378A (en) A kind of domain adaptive approach based on mixing interleaving depth network
CN111639804B (en) Method, device, storage medium and growth cabinet for monitoring cultivation space
Akpenpuun et al. Development of a building energy model for selected greenhouse designs cladded with polyolefin under tropical conditions
Gao et al. Application of Artificial Intelligence System Design Based on Genetic Algorithm In Horticultural Cultivation
KR102377963B1 (en) System and method for managing raising seedling area
Morozova Methodology for controlling greenhouse microclimate parameters and yield forecast using neural network technologies

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