CN109669352A - Oily waste water treatment procedure optimization control method based on adaptive multi-objective particle swarm - Google Patents
Oily waste water treatment procedure optimization control method based on adaptive multi-objective particle swarm Download PDFInfo
- Publication number
- CN109669352A CN109669352A CN201710964727.5A CN201710964727A CN109669352A CN 109669352 A CN109669352 A CN 109669352A CN 201710964727 A CN201710964727 A CN 201710964727A CN 109669352 A CN109669352 A CN 109669352A
- Authority
- CN
- China
- Prior art keywords
- waste water
- water treatment
- oily waste
- objective
- optimization
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
Abstract
The present invention relates to a kind of oily waste water treatment procedure optimization control methods based on adaptive multi-objective particle swarm, and it is lower mainly to solve the problems, such as that the particle swarm algorithm of prior art Plays is easy to appear Premature Convergence, search precision.The present invention establishes the objective function of the dissolved oxygen of oily waste water treatment process and the optimal setting value and aeration energy consumption and pumping energy consumption of nitrate nitrogen by using a kind of oily waste water treatment procedure optimization control method based on adaptive multi-objective particle swarm by fuzzy neural network first；Secondly adaptive multi-objective particle swarm optimization method is used, realizes the optimization to oily waste water treatment objective function, while obtaining the optimal setting value of dissolved oxygen and nitrate nitrogen；Tracing control finally is carried out using optimal setting value of the controller to dissolved oxygen and nitrate nitrogen, the technical solution for completing the multiobjective optimal control of oily waste water treatment process preferably solves the above problem, can be used in the control of oily waste water treatment process optimization.
Description
Technical field
The present invention relates to a kind of oily waste water treatment procedure optimization control methods based on adaptive multi-objective particle swarm.This
Invention using based on adaptive multi-objective particle swarm optimal control method realize oily waste water treatment during dissolved oxygen DO and
Nitrate nitrogen SNOThe control of concentration, dissolved oxygen DO and nitrate nitrogen SNOConcentration be the key that ginseng is controlled during oily waste water treatment
Number, effect, effluent quality to oily waste water treatment, the energy consumption of oily waste water treatment process suffer from great influence.It will be based on
The optimal control method of adaptive multi-objective particle swarm is applied during oily waste water treatment, realizes dissolved oxygen DO and nitrate nitrogen
SNOThe optimal control of concentration, investment reduction and operating cost while reducing oily waste water treatment process energy consumption guarantee sewage
The steady efficient operation for the treatment of plant, not only belongs to water treatment field, but also belong to field of intelligent control.
Background technique
With the high speed development of China's economic society, the quickening of petroleum industry process, mankind's activity is caused by water environment
Pollution constantly aggravation, oily wastewater all produce extremely serious influence to the mankind, animal and plant or even the entire ecosystem.
At the same time, the enhancing of the growth of national economy and Public environmental attitude, before having welcome oily waste water treatment automatic technology
The opportunity to develop not having；Water pollution how is prevented and treated, how oily wastewater is timely and effectively handled and utilizes again, become me
The extremely urgent problem of state；However oily waste water treatment process power consumption is big, operating cost is high, research sewage disposal process is excellent
Change control and realize energy-saving significant, is the development trend of the following sewage treatment industry certainty.
The essence of biochemical processing procedure of sewage is organic in the vital movement decomposition sewage using the microorganism in sludge
Pollutant makes to purify the sewage.During oily waste water treatment, the main variable that controls is dissolved oxygen DO and nitrate nitrogen SNOIt is dense
Degree.Dissolved oxygen DO and nitrate nitrogen SNOThe height variation of concentration will have a direct impact on the progress of nitrifying process and denitrification process, in turn
Energy consumption during oily waste water treatment is had an impact.Nitration reaction is mainly to carry out under aerobic conditions, works as dissolved oxygen
When DO concentration becomes larger, downward trend is presented in the concentration for being discharged ammonia nitrogen and total nitrogen, when dissolved oxygen DO concentration rises to a certain range,
The amplitude of variation of water outlet ammonia nitrogen starts to weaken, and total nitrogen is also influenced by nitrate nitrogen simultaneously, and nitrate is total while increase
Nitrogen concentration can also increase.However, anti-nitration reaction is mainly to carry out under anaerobic environment during oily waste water treatment, anoxic
The nitrate nitrogen S in areaNOConcentration is to measure the important indicator of denitrification effect, it reflects the process of anti-nitration reaction process, by nitre state
Nitrogen SNOConcentration controls in a suitable range, can be improved the potentiality of anti-nitration reaction.Therefore, real time dynamic optimization controls
Dissolved oxygen DO and nitrate nitrogen SNOConcentration, it is energy-saving to be necessary for guaranteeing effluent quality.Due to oily wastewater
Suspended matter, coloration content is high, the ingredient diversification of organic matter, non-linear, the time variation of oily waste water treatment process, and dynamic is not true
The features such as determining increases dissolved oxygen DO and nitrate nitrogen SNOControl difficulty；Some scholars use again based on BSM1 in recent years
Multi-objective genetic algorithm (MOGA) optimizes oily waste water treatment process, and aeration energy consumption and pumping energy consumption is made to reach minimum.
But these prioritization schemes belong to static optimization, steady-state optimization mostly, it is difficult to which it is real to carry out dynamic according to the variation of influent quality water
When adjust, and mostly use genetic algorithm to realize greatly.Compared with genetic algorithm, particle swarm algorithm fast convergence rate is not needed multiple
Miscellaneous cross and variation operation, algorithm is simple, parameter is few, is easily achieved, but the particle swarm algorithm of standard is easy to appear precocious receipts
It holds back, the problem that search precision is lower, therefore designs a kind of adaptive multi-objective particle swarm algorithm, improve the convergence precision of algorithm,
So as to realize dissolved oxygen DO and nitrate nitrogen S wellNOThe optimal control of concentration reduces operating cost, has real well
Border application value.
Summary of the invention
The technical problem to be solved by the present invention is to the particle swarm algorithm of prior art Plays be easy to appear Premature Convergence,
The lower problem of search precision provides a kind of new oily waste water treatment process optimization control based on adaptive multi-objective particle swarm
Method processed.This method has the advantages that be not in that Premature Convergence, search precision are higher.
To solve the above problems, The technical solution adopted by the invention is as follows: a kind of based on adaptive multi-objective particle swarm
Oily waste water treatment procedure optimization control method establishes the dissolved oxygen of oily waste water treatment process by fuzzy neural network first
With the optimal setting value and aeration energy consumption of nitrate nitrogen and the objective function of pumping energy consumption；Secondly, holding for standard particle group algorithm
The easily low disadvantage of Premature Convergence and convergence precision is realized to oily wastewater using adaptive multi-objective particle swarm optimization method
The optimization of objective function is managed, while obtaining the optimal setting value of dissolved oxygen and nitrate nitrogen；Finally, using controller to dissolved oxygen and
The optimal setting value of nitrate nitrogen carries out tracing control, completes the multiobjective optimal control of oily waste water treatment process；
Specifically includes the following steps:
1) objective function designed for the control of oily waste water treatment process optimization；
(2) the optimal setting value and aeration energy consumption and pumping energy consumption of dissolved oxygen and nitrate nitrogen are established using fuzzy neural network
Between relational expression；
(3) the constraint processing of effluent quality；
(4) Pareto optimal solution is obtained using adaptive multi-objective particle swarm optimization objective function, specifically:
1. initializing the speed v of populationi(0), position ai(0), inertia weight ωi(0), Studying factors c1i(0) and c2i
(0), and by the initial position of each particle it is set as current history optimal location pi(0), population scale S is concurrently set, maximum is evolved
Algebra M, dimension D；
2. calculating the fitness value of each particle according to objective function, the individual optimal solution p of the t times iteration is determinedi(t),
Its definition are as follows:
Non-dominant disaggregation A (t) is updated by A (t-1), formula are as follows:
Wherein, A (t)=[a1(t),a2(t),…,aQ(t)], Q is the maximum capacity of knowledge base A (t), and K is in knowledge base
Number comprising non-domination solution,Indicate ai(t-1) and pi(t-1) it does not dominate mutually；
3. determining the globally optimal solution gBest (t+1) of the t+1 times iteration
Wherein, gBest (t+1) is the globally optimal solution of the t+1 times iteration, and dgBest (t+1) is the more of the t+1 times iteration
The preferable globally optimal solution of sample, wherein the definition of dgBest (t+1) are as follows:
DgBest (t+1)=a (t), a (t) ∈ Μtbest. (4)
CgBest (t+1) is the globally optimal solution of the better astringency of the t+1 times iteration, definition are as follows:
CgBest (t+1)=argmaxCDt(ai(t)), (5)
CDt(aiIt (t)) is non-domination solution ai(t) the degree of convergence, i=1,2,3 ... K, E (t) are the t times iteration non-domination solutions
The Distribution Entropy of collection, definition are as follows:
Wherein, unIt is the cell of non-domination solution in knowledge base, n=1,2,3 ..., N, N is the total number of cell, pt
(un) it is the t times iteration unit lattice unProbability-distribution function, expression formula are as follows:
mt(un) it is the t times iteration unit lattice unThe number of middle non-domination solution, Mt(un) it is the t times iteration unit lattice unMiddle packet
The disaggregation of all non-domination solutions contained, wherein by the smallest mt(un) it is denoted as mtbest, correspondingly, MtbestIt is that the t times iteration is optimal
Non-dominant disaggregation, in addition, the selection of cgBest (t+1) by be able to reflect dominance relation the degree of convergence judge, the degree of convergence
CDt(ai(t)) is defined as:
Wherein,Be j-th can be by non-domination solution ai(t) solution dominated, DSt(aiIt (t)) is the non-branch of the t times iteration
With solution ai(t) domination intensity, definition are as follows:
DSt(ai(t)) be the t times iteration non-domination solution ai(t) total number of solution can be dominated, A (t) is the t times iteration
Non-dominant disaggregation, A (t-1) is the non-dominant disaggregation of the t-1 times iteration；
4. updating speed and the position of each particle；
5. judging whether to reach maximum evolution number M, such as reach, then terminate, otherwise back to 2.；
(5) it from one group of Pareto optimal solution that adaptive multi-objective particle swarm algorithm obtains, finds under current state
Optimal setting value of one group of Satisfactory optimum solutions as bottom controller；
(6) bottom control strategy is executed, dissolved oxygen and nitrate pass through aeration tank oxygen conversion coefficient K respectivelyLa5With
Interior regurgitant volume QaIt is adjusted.
In above-mentioned technical proposal, it is preferable that controller PID.
In above-mentioned technical proposal, it is preferable that the objective function for the control of oily waste water treatment process optimization:
Wherein, x (k)=[x1(k), x2(k)]TFor the optimized variable at k moment, x1It (k) is the dissolved oxygen DO concentration at k moment
Setting value, x2It (k) is the nitrate setting value at k moment, fAE(x) and fPE(x) be respectively aeration energy consumption, pumping energy consumption with it is excellent
Change the relational expression of variable, g1(x) and g2It (x) is respectively the relational expression for being discharged ammonia nitrogen, total nitrogen concentration and optimized variable,
C1And C2Respectively it is discharged the binding occurrence of ammonia nitrogen and total nitrogen, C1∈[0,4],C2∈[0,18]；WithIt is excellent to respectively indicate dissolved oxygen
Change the lower and upper limit value of setting value, x1∈[0.4,3],WithRespectively indicate nitrate optimal setting value lower limit and
Upper limit value, x2∈ [0.5,2], optimizing cycle 2h.
In above-mentioned technical proposal, it is preferable that the calculation of fuzzy neural network is as follows:
Wherein, x (k)=[x1(k), x2(k)]TFor the input of kth moment fuzzy neural network, cj=[c1j, c2j], σj=
[σ1j, σ2j] be respectively RBF layers j-th of neuron center vector and width vector,For j-th of neuron of kth moment
RBF layer output, P is the neuron number of RBF layers He rules layer；vl(k) defeated for kth moment corresponding first of rules layer
Out, v (k)=[v1(k), v2(k)…vP(k)]TFor kth moment rules layer output vector；w1=[w1 1, w2 1…wP 1] and w2=
[w1 2, w2 2…wP 2] it is weight vector between output neuron and rules layer, y (k) is the output of the neural network,For
The output of sewage disposal system real physical, is obtained based on BSM1 model data；
If the objective function of k moment network adjustment are as follows:
Using gradient descent algorithm, weight more new formula are as follows:
In formula, αq(k)=[θq(k)T cq(k)T σq(k)T]TFor the learning parameter vector of network, e-learning rate η=
0.01；
In above-mentioned technical proposal, it is preferable that handled using Means of Penalty Function Methods the constraint in Optimized model, wherein
Constraint penalty item is defined as:
fpenalty(x)=max { g1(x)-4,0}+max{g2(x)-18,0}, (16)
The aeration energy consumption and pumping power dissipation obj ectives function of penalty term is added are as follows:
It converts the oily waste water treatment process constraints optimization problem of foundation to without constraint multi-objective optimization question, wherein ε
For penalty factor, it is set as biggish positive real number.
In above-mentioned technical proposal, it is preferable that update speed and the position of each particle:
vi(t+1)=ωi(t)vi(t)+c1r1(pi(t)-ai(t))+c2r2(gBestd(t)-ai(t))； (18)
ai(t+1)=ai(t-1)+vi(t+1)；
Wherein, r1And r2Respectively indicate best previous position coefficient and global optimum's position parameter, r1And r2Take [0,1]
Arbitrary number.
In above-mentioned technical proposal, it is preferable that in step (6), execute bottom control strategy, dissolved oxygen and nitrate point
It Tong Guo not the 5th subregion oxygen conversion coefficient K of aeration tankLa5With interior regurgitant volume QaIt is adjusted.
In above-mentioned technical proposal, it is preferable that step 1. in, initialize the speed v of populationi(0), position ai(0), inertia
Weights omegai(0), Studying factors c1i(0) and c2i(0), and by the initial position of each particle it is set as current history optimal location pi
(0), population scale S=40, maximum evolutionary generation M=30, dimension D=2 are concurrently set.
A kind of oily waste water treatment procedure optimization control method based on adaptive multi-objective particle swarm provided by the invention,
The following steps are included:
(1) objective function designed for the control of oily waste water treatment process optimization:
Wherein, x (k)=[x1(k), x2(k)]TFor the optimized variable at k moment, x1It (k) is the dissolved oxygen DO concentration at k moment
Setting value, x2It (k) is the nitrate setting value at k moment, fAE(x) and fPE(x) be respectively aeration energy consumption, pumping energy consumption with
The relational expression of optimized variable, g1(x) and g2It (x) is respectively the relationship expression for being discharged ammonia nitrogen, total nitrogen concentration and optimized variable
Formula, C1And C2Respectively it is discharged the binding occurrence of ammonia nitrogen and total nitrogen, C1∈[0,4],C2∈[0,18]；WithRespectively indicate dissolution
The lower and upper limit value of oxygen optimal setting value, x1∈[0.4,3],WithIt respectively indicates under nitrate optimal setting value
Limit and upper limit value, x2∈ [0.5,2], optimizing cycle 2h.
(2) the optimal setting value and aeration energy consumption and pumping energy consumption of dissolved oxygen and nitrate nitrogen are established using fuzzy neural network
Between relational expression, wherein the calculation of fuzzy neural network is as follows:
Wherein, x (k)=[x1(k), x2(k)]TFor the input of kth moment fuzzy neural network, cj=[c1j, c2j], σj=
[σ1j, σ2j] be respectively RBF layers j-th of neuron center vector and width vector,For j-th of nerve of kth moment
The RBF layer output of member, P is the neuron number of RBF layers He rules layer；vl(k) defeated for kth moment corresponding first of rules layer
Out, v (k)=[v1(k), v2(k)…vP(k)]TFor kth moment rules layer output vector；w1=[w1 1, w2 1…wP 1] and w2=
[w1 2, w2 2…wP 2] it is weight vector between output neuron and rules layer, y (k) is the output of the neural network,For
The output of sewage disposal system real physical, is obtained based on BSM1 model data.
If the objective function of k moment network adjustment are as follows:
Using gradient descent algorithm, weight more new formula are as follows:
In formula, αq(k)=[θq(k)T cq(k)T σq(k)T]TFor the learning parameter vector of network, e-learning rate η=
0.01。
(3) the constraint processing of effluent quality
The constraint in Optimized model is handled using Means of Penalty Function Methods, wherein constraint penalty item is defined as:
fpenalty(x)=max { g1(x)-4,0}+max{g2(x)-18,0}, (7)
The aeration energy consumption and pumping power dissipation obj ectives function of penalty term is added are as follows:
The oily waste water treatment process constraints optimization problem that will be established is converted into without constraint multi-objective optimization question.Its
In, ε is penalty factor, is set as biggish positive real number.
(4) Pareto optimal solution is obtained using adaptive multi-objective particle swarm optimization objective function, specifically:
1. initializing the speed v of populationi(0), position ai(0), inertia weight ωi(0), Studying factors c1i(0) and c2i
(0), and by the initial position of each particle it is set as current history optimal location pi(0).Meanwhile population scale S=40 is set, it is maximum
Evolutionary generation M=30, dimension D=2；
2. calculating the fitness value of each particle according to objective function.Determine the individual optimal solution p of the t times iterationi(t),
Its definition are as follows:
Non-dominant disaggregation A (t) is updated by A (t-1), formula are as follows:
Wherein, A (t)=[a1(t),a2(t),…,aQ(t)], Q is the maximum capacity of knowledge base A (t), and K is in knowledge base
Number comprising non-domination solution,Indicate ai(t-1) and pi(t-1) it does not dominate mutually.
3. determining the globally optimal solution gBest (t+1) of the t+1 times iteration.
Wherein, gBest (t+1) is the globally optimal solution of the t+1 times iteration, and dgBest (t+1) is the more of the t+1 times iteration
The preferable globally optimal solution of sample, wherein the definition of dgBest (t+1) are as follows:
DgBest (t+1)=a (t), a (t) ∈ Μtbest. (12)
CgBest (t+1) is the globally optimal solution of the better astringency of the t+1 times iteration, definition are as follows:
CgBest (t+1)=argmaxCDt(ai(t)), (13)
CDt(aiIt (t)) is non-domination solution ai(t) the degree of convergence, i=1,2,3 ... K, E (t) are the t times iteration non-domination solutions
The Distribution Entropy of collection, definition are as follows:
Wherein, unIt is the cell of non-domination solution in knowledge base, n=1,2,3 ..., N, N is the total number of cell, pt
(un) it is the t times iteration unit lattice unProbability-distribution function, expression formula are as follows:
mt(un) it is the t times iteration unit lattice unThe number of middle non-domination solution, Mt(un) it is the t times iteration unit lattice unMiddle packet
The disaggregation of all non-domination solutions contained.Wherein, by the smallest mt(un) it is denoted as mtbest, correspondingly, MtbestIt is that the t times iteration is optimal
Non-dominant disaggregation.In addition, the selection of cgBest (t+1) is judged by being able to reflect the degree of convergence of dominance relation, the degree of convergence
CDt(ai(t)) is defined as:
Wherein,Be j-th can be by non-domination solution ai(t) solution dominated, DSt(aiIt (t)) is the non-branch of the t times iteration
With solution ai(t) domination intensity, definition are as follows:
DSt(ai(t)) be the t times iteration non-domination solution ai(t) total number of solution can be dominated, A (t) is the t times iteration
Non-dominant disaggregation, A (t-1) is the non-dominant disaggregation of the t-1 times iteration；
4. updating speed and the position of each particle:
vi(t+1)=ωi(t)vi(t)+c1r1(pi(t)-ai(t))+c2r2(gBestd(t)-ai(t))； (18)
ai(t+1)=ai(t-1)+vi(t+1)； (19)
Wherein, r1And r2Respectively indicate best previous position coefficient and global optimum's position parameter, r1And r2Take [0,1]
Arbitrary number；
5. judging whether to reach maximum evolution number M, such as reach, then terminate, otherwise back to 2..
(5) it from one group of Pareto optimal solution that adaptive multi-objective particle swarm algorithm obtains, finds under current state
Optimal setting value of one group of Satisfactory optimum solutions as bottom PID controller.
(6) bottom PID control strategy is executed, dissolved oxygen and nitrate pass through the 5th subregion oxygen of aeration tank respectively and turn
Change COEFFICIENT KLa5With interior regurgitant volume QaIt is adjusted.
Complicated, dynamic, unstable biochemistry of the present invention for current active sludge oily waste water treatment process
The characteristics of reaction process and non-linear, time variation, hysteresis quality；Dissolved oxygen DO and nitrate nitrogen S simultaneouslyNOExist between concentration strong
Coupled relation realizes dissolved oxygen DO and nitrate nitrogen to meet the demand for reducing operation energy consumption while effluent quality is up to standard
SNOThe multi objective control of concentration is realized molten using the oily waste water treatment model predictive control method based on multi-objective particle swarm
Solve oxygen DO and nitrate nitrogen SNOThe control of concentration has the characteristics that control precision is high, stability is good；The present invention is used based on adaptive
The oily waste water treatment model of multi-objective particle swarm is to sewage disposal process dissolved oxygen DO and nitrate nitrogen SNOConcentration optimizes control
System, the optimal control method solve the problems, such as the Optimization Solution of multiple objective functions, controller are made to better meet current environment
Variation, realize dissolved oxygen DO and nitrate nitrogen SNOConcentration real-time closed-loop accurately controls, and avoids current sewage treatment plant's needs
The complex process that multiple controllers are controlled is designed, with the features such as strong real-time, structure is simple, achieves preferable technology
Effect.
Detailed description of the invention
Fig. 1 is adaptive multi-objective particle swarm optimization control system overall structure figure of the invention；
Fig. 2 is control system dissolved oxygen DO concentration results figure of the present invention；
Fig. 3 is control system dissolved oxygen DO concentration error figure of the present invention；
Fig. 4 is control system nitrate nitrogen S of the present inventionNOConcentration results figure；
Fig. 5 is control system nitrate nitrogen S of the present inventionNOConcentration results Error Graph.
The present invention will be further described below by way of examples, but is not limited only to the present embodiment.
Specific embodiment
[embodiment 1]
A kind of oily waste water treatment procedure optimization control method based on adaptive multi-objective particle swarm, as shown in Figure 1, real
Dissolved oxygen DO and nitrate nitrogen S during oily waste water treatment is showedNOThe multiobjective optimal control of concentration；The control method passes through mould
It pastes Neural Network Online modeling and obtains dissolved oxygen DO and nitrate nitrogen SNOThe optimal setting value of concentration and aeration energy consumption, pumping energy consumption,
Functional relation between effluent quality applies the optimal control method based on adaptive multi-objective particle swarm in oily waste water treatment
In the process, dissolved oxygen DO and nitrate nitrogen S is realizedNOThe optimal control of concentration, while reducing oily waste water treatment process energy consumption
Investment reduction and operating cost guarantee the steady efficient operation of sewage treatment plant, not only belong to water treatment field, but also belongs to intelligent control
Field processed.
Present invention employs the following technical solution and realize step:
1. it is a kind of based on adaptive multi-objective particle swarm oily waste water treatment procedure optimization control method design include with
Lower step: for dissolved oxygen DO concentration and nitrate nitrogen S in batch-type interval activated Sludge SystemNOIt is controlled, with aeration energy consumption
It is control amount, dissolved oxygen DO and nitrate nitrogen S with pumping energy consumptionNOConcentration is controlled volume, adaptive multi-objective particle swarm optimization control
Overall system architecture such as Fig. 1；
(1) objective function designed for the control of oily waste water treatment process optimization:
Wherein, x (k)=[x1(k), x2(k)]TFor the optimized variable at k moment, x1(k) it is set for the dissolved oxygen concentration at k moment
Definite value, x2It (k) is the nitrate setting value at k moment, fAE(x) and fPE(x) be respectively aeration energy consumption, pumping energy consumption with it is excellent
Change the relational expression of variable, g1(x) and g2It (x) is respectively the relational expression for being discharged ammonia nitrogen, total nitrogen concentration and optimized variable,
C1And C2Respectively it is discharged the binding occurrence of ammonia nitrogen and total nitrogen, C1∈[0,4],C2∈[0,18]；WithIt is excellent to respectively indicate dissolved oxygen
Change the lower and upper limit value of setting value, x1∈[0.4,3],WithRespectively indicate nitrate optimal setting value lower limit and
Upper limit value, x2∈ [0.5,2], optimizing cycle 2h.
(2) the optimal setting value and aeration energy consumption and pumping energy consumption of dissolved oxygen and nitrate nitrogen are established using fuzzy neural network
Between relational expression, wherein the calculation of fuzzy neural network is as follows:
Wherein, x (k)=[x1(k), x2(k)]TFor the input of kth moment fuzzy neural network, cj=[c1j, c2j], σj=
[σ1j, σ2j] be respectively RBF layers j-th of neuron center vector and width vector,For j-th of nerve of kth moment
The RBF layer output of member, P is the neuron number of RBF layers He rules layer；vl(k) defeated for kth moment corresponding first of rules layer
Out, v (k)=[v1(k), v2(k)…vP(k)]TFor kth moment rules layer output vector；w1=[w1 1, w2 1…wP 1] and w2=
[w1 2, w2 2…wP 2] it is weight vector between output neuron and rules layer, y (k) is the output of the neural network,For
The output of sewage disposal system real physical, is obtained based on BSM1 model data.
If the objective function of k moment network adjustment are as follows:
Using gradient descent algorithm, weight more new formula are as follows:
In formula, αq(k)=[θq(k)T cq(k)T σq(k)T]TFor the learning parameter vector of network, e-learning rate η=
0.01。
(3) the constraint processing of effluent quality
The constraint in Optimized model is handled using Means of Penalty Function Methods, wherein constraint penalty item is defined as:
fpenalty(x)=max { g1(x)-4,0}+max{g2(x)-18,0}, (7)
The aeration energy consumption and pumping power dissipation obj ectives function of penalty term is added are as follows:
The oily waste water treatment process constraints optimization problem that will be established is converted into without constraint multi-objective optimization question.Its
In, ε is penalty factor, is set as biggish positive real number.
(4) Pareto optimal solution is obtained using adaptive multi-objective particle swarm optimization objective function, specifically:
1. initializing the speed v of populationi(0), position ai(0), inertia weight ωi(0), Studying factors c1i(0) and c2i
(0), and by the initial position of each particle it is set as current history optimal location pi(0).Meanwhile population scale S=40 is set, it is maximum
Evolutionary generation M=30, dimension D=2；
2. calculating the fitness value of each particle according to objective function.Determine the individual optimal solution p of the t times iterationi(t),
Its definition are as follows:
Non-dominant disaggregation A (t) is updated by A (t-1), formula are as follows:
Wherein, A (t)=[a1(t),a2(t),…,aQ(t)], Q is the maximum capacity of knowledge base A (t), and K is in knowledge base
Number comprising non-domination solution,Indicate ai(t-1) and pi(t-1) it does not dominate mutually.
3. determining the globally optimal solution gBest (t+1) of the t+1 times iteration.
Wherein, gBest (t+1) is the globally optimal solution of the t+1 times iteration, and dgBest (t+1) is the more of the t+1 times iteration
The preferable globally optimal solution of sample, wherein the definition of dgBest (t+1) are as follows:
DgBest (t+1)=a (t), a (t) ∈ Μtbest. (12)
CgBest (t+1) is the globally optimal solution of the better astringency of the t+1 times iteration, definition are as follows:
CgBest (t+1)=argmaxCDt(ai(t)), (13)
CDt(aiIt (t)) is non-domination solution ai(t) the degree of convergence, i=1,2,3 ... K, E (t) are the t times iteration non-domination solutions
The Distribution Entropy of collection, definition are as follows:
Wherein, unIt is the cell of non-domination solution in knowledge base, n=1,2,3 ..., N, N is the total number of cell, pt
(un) it is the t times iteration unit lattice unProbability-distribution function, expression formula are as follows:
mt(un) it is the t times iteration unit lattice unThe number of middle non-domination solution, Mt(un) it is the t times iteration unit lattice unMiddle packet
The disaggregation of all non-domination solutions contained.Wherein, by the smallest mt(un) it is denoted as mtbest, correspondingly, MtbestIt is that the t times iteration is optimal
Non-dominant disaggregation.In addition, the selection of cgBest (t+1) is judged by being able to reflect the degree of convergence of dominance relation, the degree of convergence
CDt(ai(t)) is defined as:
Wherein,Be j-th can be by non-domination solution ai(t) solution dominated, DSt(aiIt (t)) is the non-branch of the t times iteration
With solution ai(t) domination intensity, definition are as follows:
DSt(ai(t)) be the t times iteration non-domination solution ai(t) total number of solution can be dominated, A (t) is the t times iteration
Non-dominant disaggregation, A (t-1) is the non-dominant disaggregation of the t-1 times iteration；
4. updating speed and the position of each particle:
vi(t+1)=ωi(t)vi(t)+c1r1(pi(t)-ai(t))+c2r2(gBestd(t)-ai(t))； (18)
ai(t+1)=ai(t-1)+vi(t+1)； (19)
Wherein, r1And r2Respectively indicate best previous position coefficient and global optimum's position parameter, r1And r2Take [0,1]
Arbitrary number；5. judging whether to reach maximum evolution number M, such as reach, then terminate, otherwise back to 2..
(5) it from one group of Pareto optimal solution that adaptive multi-objective particle swarm algorithm obtains, finds under current state
Optimal setting value of one group of Satisfactory optimum solutions as bottom PID controller.
(6) bottom PID control strategy, the parameter setting of PID controller are as follows: K are executedP,1=200, KI,1=15, KD,1=2
And KP,2=20000, KI,2=5000, KD,2=400.Dissolved oxygen and nitrate pass through the 5th subregion oxygen of aeration tank respectively
Conversion coefficient KLa5With interior regurgitant volume QaIt is adjusted.
(7) using PID controller to dissolved oxygen DO and nitrate nitrogen SNOConcentration optimization setting value is tracked control, entire to control
The output of system processed is dissolved oxygen DO and nitrate nitrogen SNOThe value optimal setting value and Tracing Control value of concentration；Fig. 2 display system
Dissolved oxygen DO concentration optimization setting value and Tracing Control value, X-axis: time, unit are number of days, and Y-axis: the optimization of dissolved oxygen DO is set
Definite value and Tracing Control value, unit are mg/litres, and solid line is dissolved oxygen DO concentration optimization setting value, and dotted line is practical dissolved oxygen
DO Tracing Control value；Error such as Fig. 3, X of optimal setting dissolved oxygen DO concentration value and practical dissolved oxygen DO Tracing Control concentration value
Axis: time, unit are number of days, and Y-axis: dissolved oxygen DO concentration error value, unit is mg/litre；The nitrate nitrogen S of Fig. 4 display systemNO
Optimal setting value and Tracing Control value, X-axis: time, unit are number of days, Y-axis: nitrate nitrogen SNOOptimal setting value and tracking control
Value processed, unit are mg/litres, and solid line is nitrate nitrogen SNOConcentration optimization setting value, dotted line are nitrate nitrogen SNOTracing Control concentration
Value；Optimal setting nitrate nitrogen SNOConcentration value and practical nitrate nitrogen SNOThe error of Tracing Control concentration value such as Fig. 5, X-axis: the time,
Unit is number of days, Y-axis: nitrate nitrogen SNOConcentration error value, unit are mg/litres, as a result prove the validity of this method.
It is important to note that: the present invention is intended merely to description conveniently, using to dissolved oxygen DO and nitrate nitrogen SNOConcentration
Control, the control etc. of the same invention also applicable sewage disposal process ammonia nitrogen, is controlled as long as using the principle of the present invention
System all should belong to the scope of the present invention.
Claims (8)
1. a kind of oily waste water treatment procedure optimization control method based on adaptive multi-objective particle swarm passes through fuzzy mind first
Through network establish oily waste water treatment process dissolved oxygen and nitrate nitrogen optimal setting value and aeration energy consumption and pump energy consumption
Objective function；Secondly, the disadvantage low for the easy Premature Convergence of standard particle group algorithm and convergence precision, using adaptive more mesh
Particle group optimizing method is marked, realizes optimization to oily waste water treatment objective function, while obtaining the excellent of dissolved oxygen and nitrate nitrogen
Change setting value；Finally, carrying out tracing control using optimal setting value of the controller to dissolved oxygen and nitrate nitrogen, oily wastewater is completed
The multiobjective optimal control for the treatment of process；
Specifically includes the following steps:
(1) objective function designed for the control of oily waste water treatment process optimization；
(2) it is established between the optimal setting value and aeration energy consumption of dissolved oxygen and nitrate nitrogen and pumping energy consumption using fuzzy neural network
Relational expression；
(3) the constraint processing of effluent quality；
(4) Pareto optimal solution is obtained using adaptive multi-objective particle swarm optimization objective function, specifically:
1. initializing the speed v of populationi(0), position ai(0), inertia weight ωi(0), Studying factors c1i(0) and c2i(0), and
The initial position of each particle is set as current history optimal location pi(0), population scale S, maximum evolutionary generation M are concurrently set,
Dimension D；
2. calculating the fitness value of each particle according to objective function, the individual optimal solution p of the t times iteration is determinedi(t), it defines
Formula are as follows:
Non-dominant disaggregation A (t) is updated by A (t-1), formula are as follows:
A (t)=A (t-1) ∪ pi(t-1),if ai(t-1) < > pi(t-1), (2)
Wherein, A (t)=[a1(t),a2(t),…,aQ(t)], Q is the maximum capacity of knowledge base A (t), and K, which is in knowledge base, includes
The number of non-domination solution, ai(t-1) < > pi(t-1) a is indicatedi(t-1) and pi(t-1) it does not dominate mutually；
3. determining the globally optimal solution gBest (t+1) of the t+1 times iteration
Wherein, gBest (t+1) is the globally optimal solution of the t+1 times iteration, and dgBest (t+1) is the diversity of the t+1 times iteration
Preferable globally optimal solution, wherein the definition of dgBest (t+1) are as follows:
DgBest (t+1)=a (t), a (t) ∈ Μtbest. (4)
CgBest (t+1) is the globally optimal solution of the better astringency of the t+1 times iteration, definition are as follows:
CgBest (t+1)=arg maxCDt(ai(t)), (5)
CDt(aiIt (t)) is non-domination solution ai(t) the degree of convergence, i=1,2,3 ... K, E (t) are the non-dominant disaggregation of the t times iteration
Distribution Entropy, definition are as follows:
Wherein, unIt is the cell of non-domination solution in knowledge base, n=1,2,3 ..., N, N is the total number of cell, pt(un) be
The t times iteration unit lattice unProbability-distribution function, expression formula are as follows:
mt(un) it is the t times iteration unit lattice unThe number of middle non-domination solution, Mt(un) it is the t times iteration unit lattice unIn include
The disaggregation of all non-domination solutions, wherein by the smallest mt(un) it is denoted as mtbest, correspondingly, MtbestIt is optimal non-of the t times iteration
Disaggregation is dominated, in addition, the selection of cgBest (t+1) is judged by being able to reflect the degree of convergence of dominance relation, degree of convergence CDt(ai
(t)) is defined as:
Wherein,Be j-th can be by non-domination solution ai(t) solution dominated, DSt(aiIt (t)) is the t times iteration non-domination solution ai
(t) domination intensity, definition are as follows:
DSt(ai(t)) be the t times iteration non-domination solution ai(t) total number of solution can be dominated, A (t) is the non-of the t times iteration
Disaggregation is dominated, A (t-1) is the non-dominant disaggregation of the t-1 times iteration；
4. updating speed and the position of each particle；
5. judging whether to reach maximum evolution number M, such as reach, then terminate, otherwise back to 2.；
(5) from one group of Pareto optimal solution that adaptive multi-objective particle swarm algorithm obtains, one group under current state is found
Optimal setting value of the Satisfactory optimum solutions as bottom controller；
(6) bottom control strategy is executed, dissolved oxygen and nitrate pass through aeration tank oxygen conversion coefficient K respectivelyLa5With interior time
Flow QaIt is adjusted.
2. according to claim 1 based on the oily waste water treatment procedure optimization control method of adaptive multi-objective particle swarm,
It is characterized in that controller is PID.
3. according to claim 1 based on the oily waste water treatment procedure optimization control method of adaptive multi-objective particle swarm,
It is characterized in that the objective function for the control of oily waste water treatment process optimization:
Wherein, x (k)=[x1(k), x2(k)]TFor the optimized variable at k moment, x1(k) it is set for the dissolved oxygen DO concentration at k moment
Value, x2It (k) is the nitrate setting value at k moment, fAE(x) and fPEIt (x) is respectively that aeration energy consumption, pumping energy consumption and optimization become
The relational expression of amount, g1(x) and g2It (x) is respectively the relational expression for being discharged ammonia nitrogen, total nitrogen concentration and optimized variable, C1With
C2Respectively it is discharged the binding occurrence of ammonia nitrogen and total nitrogen, C1∈[0,4],C2∈[0,18]；WithDissolved oxygen optimization is respectively indicated to set
The lower and upper limit value of definite value, x1∈[0.4,3],WithRespectively indicate the lower and upper limit of nitrate optimal setting value
Value, x2∈ [0.5,2], optimizing cycle 2h.
4. according to claim 1 based on the oily waste water treatment procedure optimization control method of adaptive multi-objective particle swarm,
It is characterized in that the calculation of fuzzy neural network is as follows:
Wherein, x (k)=[x1(k), x2(k)]TFor the input of kth moment fuzzy neural network, cj=[c1j, c2j], σj=[σ1j, σ2j]
It is the center vector and width vector of RBF layers of j-th of neuron respectively,For the RBF layer of j-th of neuron of kth moment
Output, P is the neuron number of RBF layers He rules layer；vlIt (k) is corresponding first of rules layer output of kth moment, v (k)=
[v1(k), v2(k)…vP(k)]TFor kth moment rules layer output vector；w1=[w1 1, w2 1…wP 1] and w2=[w1 2, w2 2…wP 2]
It is the weight vector between output neuron and rules layer, y (k) is the output of the neural network,For sewage disposal system
Real physical output, is obtained based on BSM1 model data；
If the objective function of k moment network adjustment are as follows:
Using gradient descent algorithm, weight more new formula are as follows:
In formula, αq(k)=[θq(k)T cq(k)T σq(k)T]TFor the learning parameter vector of network, e-learning rate η=0.01.
5. according to claim 1 based on the oily waste water treatment procedure optimization control method of adaptive multi-objective particle swarm,
It is characterized in that being handled using Means of Penalty Function Methods the constraint in Optimized model, wherein constraint penalty item is defined as:
fpenalty(x)=max { g1(x)-4,0}+max{g2(x)-18,0}, (17)
The aeration energy consumption and pumping power dissipation obj ectives function of penalty term is added are as follows:
It converts the oily waste water treatment process constraints optimization problem of foundation to without constraint multi-objective optimization question, wherein ε is to punish
Penalty factor is set as biggish positive real number.
6. according to claim 1 based on the oily waste water treatment procedure optimization control method of adaptive multi-objective particle swarm,
It is characterized in that updating speed and the position of each particle:
vi(t+1)=ωi(t)vi(t)+c1r1(pi(t)-ai(t))+c2r2(gBestd(t)-ai(t))； (19)
ai(t+1)=ai(t-1)+vi(t+1)； (20)
Wherein, r1And r2Respectively indicate best previous position coefficient and global optimum's position parameter, r1And r2Take any of [0,1]
Number.
7. according to claim 1 based on the oily waste water treatment procedure optimization control method of adaptive multi-objective particle swarm,
It is characterized in that executing bottom control strategy, dissolved oxygen and nitrate pass through the 5th subregion of aeration tank respectively in step (6)
Oxygen conversion coefficient KLa5With interior regurgitant volume QaIt is adjusted.
8. according to claim 1 based on the oily waste water treatment procedure optimization control method of adaptive multi-objective particle swarm,
It is characterized in that step 1. in, initialize the speed v of populationi(0), position ai(0), inertia weight ωi(0), Studying factors c1i
(0) and c2i(0), and by the initial position of each particle it is set as current history optimal location pi(0), population scale S=is concurrently set
40, maximum evolutionary generation M=30, dimension D=2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710964727.5A CN109669352B (en) | 2017-10-17 | 2017-10-17 | Oily sewage treatment process optimization control method based on self-adaptive multi-target particle swarm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710964727.5A CN109669352B (en) | 2017-10-17 | 2017-10-17 | Oily sewage treatment process optimization control method based on self-adaptive multi-target particle swarm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109669352A true CN109669352A (en) | 2019-04-23 |
| CN109669352B CN109669352B (en) | 2022-04-05 |
Family
ID=66139708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710964727.5A Active CN109669352B (en) | 2017-10-17 | 2017-10-17 | Oily sewage treatment process optimization control method based on self-adaptive multi-target particle swarm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109669352B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110716432A (en) * | 2019-10-14 | 2020-01-21 | 北京工业大学 | Multi-objective optimization control method for urban sewage treatment process based on self-adaptive selection strategy |
| CN111399558A (en) * | 2020-04-27 | 2020-07-10 | 北京工业大学 | Knowledge selection-based multi-objective optimization control method for sewage treatment process |
| CN111474854A (en) * | 2020-04-27 | 2020-07-31 | 北京工业大学 | Sewage treatment process optimization control method based on data-knowledge drive |
| CN112183719A (en) * | 2020-09-15 | 2021-01-05 | 北京工业大学 | Intelligent detection method for total nitrogen in effluent based on multi-objective optimization-fuzzy neural network |
| CN112859597A (en) * | 2021-01-07 | 2021-05-28 | 中南大学 | Data-driven optimized control method and system for iron sinking process |
| CN113589684A (en) * | 2021-05-20 | 2021-11-02 | 北京工业大学 | Sewage treatment process optimization control method based on self-adjusting multitask particle swarm algorithm |
| CN113867276A (en) * | 2021-08-27 | 2021-12-31 | 北京工业大学 | Sewage treatment process multitask optimization control method based on self-adaptive knowledge migration strategy |
| CN114114909A (en) * | 2021-11-11 | 2022-03-01 | 海南师范大学 | Intermittent process 2D output feedback prediction control method based on particle swarm optimization |
| CN115356930A (en) * | 2022-08-24 | 2022-11-18 | 东北大学 | Multi-objective optimization control system and method in sewage treatment process |
| CN115356930B (en) * | 2022-08-24 | 2024-04-19 | 东北大学 | Multi-objective optimization control system and method in sewage treatment process |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002250237A (en) * | 2001-02-22 | 2002-09-06 | Ishikawajima Harima Heavy Ind Co Ltd | Adaptation control method for variation of heating value of sludge gas |
| WO2007037985A2 (en) * | 2005-09-23 | 2007-04-05 | Max Rudolf Junghanns | Systems and methods for treating water |
| CN102122134A (en) * | 2011-02-14 | 2011-07-13 | 华南理工大学 | Method and system for wastewater treatment of dissolved oxygen control based on fuzzy neural network |
| CN102917441A (en) * | 2012-09-29 | 2013-02-06 | 北京邮电大学 | Target network selection method on basis of particle swarm algorithm for multi-mode terminals |
| CN103049805A (en) * | 2013-01-18 | 2013-04-17 | 中国测绘科学研究院 | Vehicle route optimization method with time window constraint based on improved particle swarm optimization (PSO) |
| CN103197544A (en) * | 2013-02-25 | 2013-07-10 | 北京工业大学 | Sewage disposal process multi-purpose control method based on nonlinear model prediction |
| CN104360035A (en) * | 2014-11-02 | 2015-02-18 | 北京工业大学 | Sewage TP soft measurement method based on self-organized particle swarm and radial basis function neural network |
| CN105174417A (en) * | 2015-10-13 | 2015-12-23 | 中国石油化工股份有限公司 | Method for pretreating oil-containing sewage in refined oil depot by catalytic oxidation |
| CN105372995A (en) * | 2015-12-17 | 2016-03-02 | 镇江市高等专科学校 | Measurement and control method for sewage disposal system |
| CN105404151A (en) * | 2015-12-12 | 2016-03-16 | 北京工业大学 | Sewage processing process dynamic multi-target optimization control method |
| CN105426954A (en) * | 2015-08-20 | 2016-03-23 | 武汉科技大学 | Particle swarm optimization method based on multi-strategy synergistic function |
| CN105512745A (en) * | 2015-11-05 | 2016-04-20 | 天津大学 | Wind power section prediction method based on particle swarm-BP neural network |
| CN105573115A (en) * | 2015-12-09 | 2016-05-11 | 中山大学 | Sewage treatment process energy-saving optimization control method based on quantum genetic algorithm |
| CN106352244A (en) * | 2016-08-31 | 2017-01-25 | 中国石油化工股份有限公司 | Pipeline leakage detection method based on hierarchical neural network |
| CN106354014A (en) * | 2016-10-27 | 2017-01-25 | 北京工业大学 | Sewage disposal optimal control method based on multi-objective differential evolution algorithm |
| CN106698642A (en) * | 2016-12-29 | 2017-05-24 | 北京工业大学 | Multi-objective real-time optimization control method for sewage treatment process |
| EP3173880A1 (en) * | 2015-11-30 | 2017-05-31 | SUEZ Groupe | Method for generating control signals adapted to be sent to actuators in a water drainage network |
-
2017
- 2017-10-17 CN CN201710964727.5A patent/CN109669352B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002250237A (en) * | 2001-02-22 | 2002-09-06 | Ishikawajima Harima Heavy Ind Co Ltd | Adaptation control method for variation of heating value of sludge gas |
| WO2007037985A2 (en) * | 2005-09-23 | 2007-04-05 | Max Rudolf Junghanns | Systems and methods for treating water |
| CN102122134A (en) * | 2011-02-14 | 2011-07-13 | 华南理工大学 | Method and system for wastewater treatment of dissolved oxygen control based on fuzzy neural network |
| CN102917441A (en) * | 2012-09-29 | 2013-02-06 | 北京邮电大学 | Target network selection method on basis of particle swarm algorithm for multi-mode terminals |
| CN103049805A (en) * | 2013-01-18 | 2013-04-17 | 中国测绘科学研究院 | Vehicle route optimization method with time window constraint based on improved particle swarm optimization (PSO) |
| CN103197544A (en) * | 2013-02-25 | 2013-07-10 | 北京工业大学 | Sewage disposal process multi-purpose control method based on nonlinear model prediction |
| CN104360035A (en) * | 2014-11-02 | 2015-02-18 | 北京工业大学 | Sewage TP soft measurement method based on self-organized particle swarm and radial basis function neural network |
| CN105426954A (en) * | 2015-08-20 | 2016-03-23 | 武汉科技大学 | Particle swarm optimization method based on multi-strategy synergistic function |
| CN105174417A (en) * | 2015-10-13 | 2015-12-23 | 中国石油化工股份有限公司 | Method for pretreating oil-containing sewage in refined oil depot by catalytic oxidation |
| CN105512745A (en) * | 2015-11-05 | 2016-04-20 | 天津大学 | Wind power section prediction method based on particle swarm-BP neural network |
| EP3173880A1 (en) * | 2015-11-30 | 2017-05-31 | SUEZ Groupe | Method for generating control signals adapted to be sent to actuators in a water drainage network |
| CN105573115A (en) * | 2015-12-09 | 2016-05-11 | 中山大学 | Sewage treatment process energy-saving optimization control method based on quantum genetic algorithm |
| CN105404151A (en) * | 2015-12-12 | 2016-03-16 | 北京工业大学 | Sewage processing process dynamic multi-target optimization control method |
| CN105372995A (en) * | 2015-12-17 | 2016-03-02 | 镇江市高等专科学校 | Measurement and control method for sewage disposal system |
| CN106352244A (en) * | 2016-08-31 | 2017-01-25 | 中国石油化工股份有限公司 | Pipeline leakage detection method based on hierarchical neural network |
| CN106354014A (en) * | 2016-10-27 | 2017-01-25 | 北京工业大学 | Sewage disposal optimal control method based on multi-objective differential evolution algorithm |
| CN106698642A (en) * | 2016-12-29 | 2017-05-24 | 北京工业大学 | Multi-objective real-time optimization control method for sewage treatment process |
Non-Patent Citations (1)
| Title |
|---|
| 胡旺 等: "基于Pareto熵的多目标粒子群优化算法", 《软件学报》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110716432B (en) * | 2019-10-14 | 2022-03-15 | 北京工业大学 | Multi-objective optimization control method for urban sewage treatment process based on self-adaptive selection strategy |
| CN110716432A (en) * | 2019-10-14 | 2020-01-21 | 北京工业大学 | Multi-objective optimization control method for urban sewage treatment process based on self-adaptive selection strategy |
| CN111399558B (en) * | 2020-04-27 | 2023-09-22 | 北京工业大学 | Knowledge selection-based multi-objective optimization control method for sewage treatment process |
| CN111474854A (en) * | 2020-04-27 | 2020-07-31 | 北京工业大学 | Sewage treatment process optimization control method based on data-knowledge drive |
| CN111399558A (en) * | 2020-04-27 | 2020-07-10 | 北京工业大学 | Knowledge selection-based multi-objective optimization control method for sewage treatment process |
| CN111474854B (en) * | 2020-04-27 | 2022-05-03 | 北京工业大学 | Sewage treatment process optimization control method based on data-knowledge drive |
| US20220082545A1 (en) * | 2020-09-15 | 2022-03-17 | Beijing University Of Technology | Total Nitrogen Intelligent Detection Method Based on Multi-objective Optimized Fuzzy Neural Network |
| CN112183719A (en) * | 2020-09-15 | 2021-01-05 | 北京工业大学 | Intelligent detection method for total nitrogen in effluent based on multi-objective optimization-fuzzy neural network |
| CN112183719B (en) * | 2020-09-15 | 2024-02-02 | 北京工业大学 | Intelligent detection method for total nitrogen in effluent based on multi-objective optimization-fuzzy neural network |
| CN112859597A (en) * | 2021-01-07 | 2021-05-28 | 中南大学 | Data-driven optimized control method and system for iron sinking process |
| CN113589684A (en) * | 2021-05-20 | 2021-11-02 | 北京工业大学 | Sewage treatment process optimization control method based on self-adjusting multitask particle swarm algorithm |
| CN113589684B (en) * | 2021-05-20 | 2023-11-21 | 北京工业大学 | Sewage treatment process optimization control method based on self-adjusting multi-task particle swarm algorithm |
| CN113867276A (en) * | 2021-08-27 | 2021-12-31 | 北京工业大学 | Sewage treatment process multitask optimization control method based on self-adaptive knowledge migration strategy |
| CN114114909A (en) * | 2021-11-11 | 2022-03-01 | 海南师范大学 | Intermittent process 2D output feedback prediction control method based on particle swarm optimization |
| CN114114909B (en) * | 2021-11-11 | 2024-03-22 | 海南师范大学 | Intermittent process 2D output feedback prediction control method based on particle swarm optimization |
| CN115356930A (en) * | 2022-08-24 | 2022-11-18 | 东北大学 | Multi-objective optimization control system and method in sewage treatment process |
| CN115356930B (en) * | 2022-08-24 | 2024-04-19 | 东北大学 | Multi-objective optimization control system and method in sewage treatment process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109669352B (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109669352A (en) | Oily waste water treatment procedure optimization control method based on adaptive multi-objective particle swarm | |
| CN105404151B (en) | Sewage disposal process dynamic multi-objective optimization control method | |
| AU2021101438A4 (en) | Adaptive control method and system for aeration process | |
| CN108549234B (en) | Multi-objective optimization control method based on dynamic variable values | |
| CN106873379B (en) | Sewage treatment optimal control method based on iterative ADP algorithm | |
| Han et al. | Dynamic MOPSO-based optimal control for wastewater treatment process | |
| CN108445757B (en) | Sewage treatment process optimization control method based on dynamic multi-target particle swarm algorithm | |
| CN102122134A (en) | Method and system for wastewater treatment of dissolved oxygen control based on fuzzy neural network | |
| CN109711070A (en) | A kind of dissolved oxygen concentration optimization method based on activated sludge water process | |
| CN106406094B (en) | A kind of sewage treatment dissolved oxygen concentration tracking and controlling method based on two type fuzzy neural network of section | |
| CN110716432B (en) | Multi-objective optimization control method for urban sewage treatment process based on self-adaptive selection strategy | |
| CN106354014A (en) | Sewage disposal optimal control method based on multi-objective differential evolution algorithm | |
| CN103792844B (en) | A kind of sewage treatment control method based on orderly cluster | |
| CN108427268A (en) | A kind of sewage disposal optimal control method of knowledge based and data information decision | |
| CN108762082A (en) | A kind of sewage disposal process collaboration Optimal Control System | |
| Do et al. | A design of higher-level control based genetic algorithms for wastewater treatment plants | |
| CN110647037A (en) | Cooperative control method for sewage treatment process based on two-type fuzzy neural network | |
| Chen et al. | Smart energy savings for aeration control in wastewater treatment | |
| CN116360366B (en) | Sewage treatment process optimization control method | |
| CN111399558B (en) | Knowledge selection-based multi-objective optimization control method for sewage treatment process | |
| CN111290275B (en) | Sewage treatment optimization control method based on reinforcement learning particle swarm algorithm | |
| Huang et al. | Modeling and optimization of the activated sludge process | |
| Kapumbe et al. | Modeling and simulation of membrane bioreactor model based on ASM3 for domestic wastewater treatment. | |
| CN105138716B (en) | The running optimizatin method of nitrification and nitrosation process | |
| CN113674809A (en) | Sewage treatment carbon source adding method based on predictive control |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220316 Address after: Yanan City, Shandong province Qingdao City three road 266071 No. 218 Applicant after: CHINA PETROLEUM & CHEMICAL Corp. Applicant after: Sinopec Safety Engineering Research Institute Co., Ltd Address before: Yanan City, Shandong province Qingdao City three road 266071 No. 218 Applicant before: CHINA PETROLEUM & CHEMICAL Corp. Applicant before: Qingdao Safety Engineering Research Institute of Sinopec |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |