CN113313230B - Film pollution intelligent decision-making method based on knowledge fuzzy width learning - Google Patents
Film pollution intelligent decision-making method based on knowledge fuzzy width learning Download PDFInfo
- Publication number
- CN113313230B CN113313230B CN202110421204.2A CN202110421204A CN113313230B CN 113313230 B CN113313230 B CN 113313230B CN 202110421204 A CN202110421204 A CN 202110421204A CN 113313230 B CN113313230 B CN 113313230B
- Authority
- CN
- China
- Prior art keywords
- layer
- fuzzy
- iteration
- network
- output
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 210000002569 neuron Anatomy 0.000 claims abstract description 128
- 239000012528 membrane Substances 0.000 claims abstract description 119
- 230000008569 process Effects 0.000 claims abstract description 32
- 239000010865 sewage Substances 0.000 claims abstract description 30
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 88
- 238000013528 artificial neural network Methods 0.000 claims description 78
- 230000035699 permeability Effects 0.000 claims description 33
- 239000010802 sludge Substances 0.000 claims description 30
- 238000010606 normalization Methods 0.000 claims description 27
- 238000004519 manufacturing process Methods 0.000 claims description 22
- 238000005201 scrubbing Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 15
- 238000011084 recovery Methods 0.000 claims description 13
- 238000005273 aeration Methods 0.000 claims description 12
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 12
- 238000004140 cleaning Methods 0.000 claims description 12
- 239000001301 oxygen Substances 0.000 claims description 12
- 229910052760 oxygen Inorganic materials 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000010992 reflux Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 6
- 238000011160 research Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 7
- 230000002401 inhibitory effect Effects 0.000 description 6
- 238000011109 contamination Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000009285 membrane fouling Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Automation & Control Theory (AREA)
- Computational Linguistics (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Activated Sludge Processes (AREA)
Abstract
The invention provides a membrane pollution intelligent decision method based on knowledge fuzzy width learning, which aims at the problems of frequent membrane pollution events, huge harm and the like in a membrane bioreactor-sewage treatment process. According to the invention, the fuzzy width learning network is utilized to establish the membrane pollution decision model, a set of fuzzy neurons are adopted to replace characteristic layer neurons of the width learning network, and the parameters of the fuzzy width learning network decision model are set by using experience knowledge, so that the problem of insufficient data in the actual membrane pollution decision process is solved, the accurate decision of membrane pollution is realized, and the capability of treating membrane pollution is improved. Experimental results show that the method can provide accurate decision opinion, reduce the harm caused by membrane pollution and ensure safe, stable and efficient operation of the sewage treatment process.
Description
Technical Field
The invention builds an intelligent decision model for membrane pollution by utilizing a fuzzy width learning network based on the operation characteristics of a membrane bioreactor-sewage treatment process, and provides decision opinion for inhibiting membrane pollution, wherein a set of fuzzy neurons are adopted to replace characteristic layer neurons of the width learning network, and the parameters of the fuzzy width learning network decision model are set by utilizing experience knowledge, so that the problem of insufficient data in the actual membrane pollution decision process is solved, the accurate decision for membrane pollution is realized, and the treatment capacity for membrane pollution is improved. The intelligent decision method is applied to the sewage treatment process, has important influence on safe, stable and efficient operation of sewage treatment, is an important branch in the technical field of advanced manufacturing, and belongs to the field of water treatment and intelligent control. Therefore, the intelligent decision of membrane pollution is of great significance in the sewage treatment process.
Background
The membrane bioreactor sewage treatment process combines a membrane separation technology with a biological treatment technology, and has the advantages of good solid-liquid separation effect, low sludge load, small occupied area and the like. At present, the technology is greatly popularized in the urban sewage treatment field in China, and a better sewage treatment effect is achieved. However, the problem of membrane pollution has become a bottleneck problem that restricts the safe and stable operation of the membrane bioreactor sewage treatment process, not only can the operation energy consumption be increased, but also the effluent quality can be reduced, and even the whole sewage treatment process can be crashed. Therefore, the membrane pollution phenomenon is deeply analyzed, and the membrane pollution decision method is researched, so that the method has important research significance for ensuring safe and stable operation of the sewage treatment process and improving the sewage treatment efficiency.
At present, research on membrane pollution decision-making has attracted attention from expert scholars at home and abroad, but realization effect is not optimistic. On one hand, the membrane pollution mechanism is complex, and the reaction process is changeable, so that the membrane pollution decision method based on the mechanism model is difficult to meet the requirements of safe and stable operation of the sewage treatment process. On the other hand, although a decision method based on operation data partly achieves a certain effect, the sewage treatment process is a dynamic time-varying system, and involves a plurality of parameters, so that the traditional membrane pollution decision model is difficult to adapt to the dynamic change of working conditions, and cannot achieve the effect of accurate decision. Therefore, the design of the method for deciding the membrane pollution in real time by combining the operation data and expert experience knowledge has important theoretical significance and application value for realizing safe, stable and efficient operation of the sewage treatment process, inhibiting the membrane pollution and improving the water quality of the effluent.
The invention designs a film pollution intelligent decision method based on knowledge fuzzy width learning, which is characterized in that a decision model based on a fuzzy width learning network is constructed, wherein a set of fuzzy neurons are adopted to replace characteristic layer neurons of the width learning network, and the parameters of the fuzzy width learning network decision model are set by using experience knowledge, so that the problem of insufficient data in the actual film pollution decision process is solved, and the film pollution accurate decision is realized. The invention not only solves the problem of membrane pollution inhibition of the sewage treatment plant, but also can improve the quality of effluent water and improve the running safety and stability of the sewage treatment plant.
Disclosure of Invention
The invention obtains a film pollution intelligent decision method based on knowledge fuzzy width learning, and the method constructs a decision model based on a fuzzy width learning network, wherein a set of fuzzy neurons are adopted to replace characteristic layer neurons of the width learning network, and the parameters of the fuzzy width learning network decision model are set by using experience knowledge, so that the problem of insufficient data in the actual film pollution decision process is solved, and the film pollution accurate decision is realized.
The invention adopts the following technical scheme and implementation steps:
1. the intelligent film pollution decision method based on knowledge fuzzy width learning is characterized in that a decision model based on a fuzzy width learning network is established to provide decision support for inhibiting film pollution, wherein a set of fuzzy neurons are adopted to replace characteristic layer neurons of the width learning network, and parameters of the decision model of the fuzzy width learning network are set by using experience knowledge, so that the problem of insufficient data in an actual film pollution decision process is solved, and the accurate decision of film pollution is realized, and the method comprises the following steps:
(1) Determining input and output variables of a membrane pollution decision model: one bottleneck problem of the sewage treatment process of the membrane bioreactor is membrane pollution, and the membrane pollution not only can cause the water quality of effluent to be reduced and the production energy consumption to be improved, but also can cause the breakdown of the sewage treatment process, thereby severely restricting the popularization and the application of the membrane bioreactor. It is therefore necessary to provide decision support for inhibiting membrane fouling. The sewage treatment process of the membrane bioreactor is taken as a research object, the characteristic analysis is carried out on the sewage treatment process variable, and the process variable related to the membrane pollution is selected as the input variable of the intelligent decision model: the water permeability, the water permeability decay rate, the water production flow, the membrane scrubbing air volume, the sludge concentration, the transmembrane pressure difference, the water production turbidity and the water permeability recovery rate; normalizing the acquired input variable to [0,1]; the operation proposal is used as an output variable of the intelligent decision model of membrane pollution; dividing all sample data into two groups, wherein one group comprises P training samples, and the other group comprises M test samples, and P is generally required to be more than M;
(2) Establishing an intelligent decision model based on a fuzzy width learning network: establishing film contamination decisions using fuzzy breadth-learning networksThe model comprises four layers of fuzzy width learning network structures, including an input layer, a fuzzy neural network layer, an enhancement layer and an output layer; the structure is 8-I-J-8, the number of neurons of a model input layer for membrane pollution decision is determined to be 8, the number of sub-networks of a fuzzy neural network layer is I, and the I is 1,10]Any positive integer in between; the number of the enhancement layer neuron groups is J, and J is [2,20]]Any positive integer in between; the number of neurons of the output layer is 8, the fuzzy width learning network is trained by using P training samples, and the input quantity of the membrane pollution decision model is x (t) = [ x ] 1 (t),x 2 (t),…,x P (t)]，x n (t)＝[x 1n (t),x 2n (t),x 3n (t),x 4n (t),x 5n (t),x 6n (t),x 7n (t),x 8n (t)]For the nth sample at the t-th iteration after normalization, n=1, 2, …, P, x 1n (t) is the water permeability, x, in the nth sample at the nth iteration after normalization 2n (t) is the water permeability decay rate, x, in the nth sample at the nth iteration after normalization 3n (t) is the water production flow rate, x in the nth sample at the t th iteration after normalization 4n (t) is the film scrubbing air volume, x in the nth sample at the t th iteration after normalization 5n (t) is the sludge concentration, x in the nth sample at the nth iteration after normalization 6n (t) is the transmembrane pressure difference, x, in the nth sample at the nth iteration after normalization 7n (t) is the turbidity of produced water in the nth sample at the nth iteration after normalization, x 8n (t) the recovery rate of the water permeability in the nth sample at the t th iteration after normalization, and the output quantity of the membrane pollution decision model is the operation proposal Y d (t)＝[Y d1 (t),Y d2 (t),…,Y dP (t)]，Y dn (t)＝[Y 1dn (t),Y 2dn (t),Y 3dn (t),Y 4dn (t),Y 5dn (t),Y 6dn (t),Y 7dn (t),Y 8dn (t)]Suggesting for the operation of the nth sample at the t-th iteration, Y 1dn (t) is operation proposal 1, namely the operation is not suitable for more than 4 hours and the water yield is reduced by 5 to 10 percent, Y 2dn (t) is operation proposal 2, namely, the water yield of the membrane tank is reduced, the transmembrane pressure difference is controlled to be 10-40kPa, Y 3dn (t) is operation suggestion 3, i.e. to increase aeration rate, controlPreparing dissolved oxygen with concentration of 1.5-3.5mg/L, Y 4dn (t) is an operation suggestion 4, namely, checking whether the water quality, the water production flow, the membrane scrubbing air volume and the membrane pool sludge concentration are abnormal or not, Y 5dn (t) is operation proposal 5, namely, the sludge discharge amount of the membrane tank is increased, the reflux ratio of the membrane tank is increased, the sludge concentration of the membrane tank is controlled to be 8000-12000mg/L, Y 6dn (t) is operation suggestion 6, namely, adjusting operation parameters, reducing water yield by 5% -10%, or increasing aeration quantity, controlling dissolved oxygen concentration by 2-4mg/L, Y 7dn (t) is operation suggestion 7, i.e. recently developed on-line physical cleaning, Y 8dn (t) is an operation suggestion 8, namely, on-line chemical cleaning is implemented within 24 hours, and each layer in a decision model based on a fuzzy width learning network is expressed as follows:
fuzzy width learning network input layer: this layer consists of 8 neurons, each outputting the following:
u s (t)＝x s (t),s＝1,2,...,8, (1)
wherein u is s (t) the output value of the s-th neuron of the input layer of the fuzzy width learning network at the t-th iteration;
fuzzy width learning network fuzzy neural network layer: the fuzzy neural network layer consists of I sub-networks, and each fuzzy neural network sub-network structure of the fuzzy neural network layer comprises four layers including an input layer, an hidden layer, a rule layer and an output layer; the structure of the fuzzy neural network is 8-L-L-V, the number of neurons of an input layer of each fuzzy neural network is 8, the number of neurons of an hidden layer is L, the number of neurons of a regular layer is L, and L is any positive integer between [2,20 ]; the number of the neurons of the output layer is V, and V is any positive integer between [2,10 ]; the layer outputs can be expressed as:
fuzzy neural network sub-network input layer: this layer consists of 8 neurons, each outputting the following:
r s (t)＝u s (t), (2)
wherein r is s (t) is the output value of the s-th neuron of the input layer of the fuzzy neural network sub-network at the t-th iteration;
fuzzy neural network sub-network hidden layer: the layer consists of L neurons, and the layer output can be expressed as:
wherein,for the output value of the first neuron of the hidden layer of the fuzzy neural network sub-network at the t-th iteration, c ls (t) is the center of the s-th membership function of the first neuron of the hidden layer at the t-th iteration; sigma (sigma) ls (t) is the width of the s-th membership function of the first neuron of the hidden layer at the t-th iteration;
fuzzy neural network subnetwork rules layer: the layer consists of L neurons, and the layer output can be expressed as:
wherein f l (t) is the output value of the first neuron of the rule layer of the fuzzy neural network sub-network at the t-th iteration;
fuzzy neural network sub-network output layer: the layer consists of V neurons, and the layer output can be expressed as:
wherein o is v (t) is the output value of the v th neuron of the output layer of the fuzzy neural network sub-network at the t-th iteration, w vl (t) is the weight between the v neuron of the output layer and the l neuron of the rule layer at the t iteration;
fuzzy width learning network enhancement layer: the layer consists of J sets of neurons, and the layer output can be expressed as:
H(t)＝[h 1 (t),h 2 (t),...,h J (t)], (6)
h j (t)＝ζ j (O(t)w hj (t)+β hj (t)),j＝1,2,...,J, (7)
wherein H (t) is the output value of the fuzzy width learning network enhancement layer at the t-th iteration, H j (t) is the output value of the jth group of neurons of the enhancement layer at the t-th iteration ζ j () To enhance the activation function of the j-th set of neurons of the layer, O (t) = [ O 1 (t),o 2 (t),…,o I (t)]For the output value o of the fuzzy neural network layer at the t-th iteration i (t)＝[o 1 (t),o 2 (t),…,o V (t)]For the output value of the ith sub-network of the fuzzy neural network layer at the t-th iteration, i=1, 2, …, I, w hj (t) and beta hj (t) weight and bias values between the fuzzy neural network layer and the jth group of neurons of the enhancement layer at the t-th iteration;
fuzzy width learning network output layer: the layer consists of 8 neurons, and the layer output can be expressed as:
wherein Y (t) is the output value of the fuzzy width learning network output layer at the t-th iteration, and w i (t) is the weight value between the output layer of the fuzzy width learning network and the ith sub-network of the fuzzy neural network layer at the t-th iteration, w j (t) is the weight between the jth group of neurons of the fuzzy width learning network output layer and the enhancement layer at the t-th iteration;
(3) Setting an initial structure and parameters of a fuzzy breadth learning network intelligent decision model by using experience knowledge: converting the experience knowledge into a form of fuzzy rule:
wherein,and->For the water permeability x in rule q 1n Lower and upper limit values of ++>And->The film scrubbing air quantity x in the rule q 4n Lower and upper limit values of ++>And->Is the water permeability recovery rate x in the rule q 8n Lower and upper limit values of ++>For the output value of the v-th neuron in the output layer of the fuzzy neural network sub-network in the rule Q, q=1, …, and Q is the number of rules. Setting the number L=Q of hidden layer neurons and regular layer neurons of each fuzzy neural network layer sub-network;
setting initial parameters of an intelligent decision model of the fuzzy breadth learning network by using a formula (9):
wherein c qsn (t) the center of the s-th membership function of the q-th neuron of the hidden layer in the nth sample at the t-th iteration,and->The lower bound and the upper bound of the s-th neuron of the input layer corresponding to the q-th neuron of the hidden layer in the t-th iteration are provided; sigma (sigma) qsn (t) the width of the s membership function of the q-th neuron of the hidden layer in the nth sample at the t-th iteration, ρ is a normal number, and values are randomly taken in the interval (0, 1);
(4) Training a decision model based on a fuzzy width learning network, specifically:
(1) setting the current iteration number t=1, and setting the maximum iteration number of a decision model based on a fuzzy width learning network as K=30;
(2) the number of initial fuzzy neural network layer sub-networks of a given fuzzy width learning network is I, the number of enhancement layer neuron groups is J, the number of hidden layer neurons and regular layer neurons of each fuzzy neural network layer sub-network is Q, and the number of output layer neurons is V;
(3) calculating the output Y (t) of the fuzzy breadth learning network according to the formulas (1) - (10), wherein the accuracy of the output of the fuzzy breadth learning network is expressed as:
A(t)＝TF(t)/P, (12)
wherein A (t) is the output accuracy of the fuzzy width learning network at the t-th iteration, and TF (t) is the number of samples of the fuzzy width learning network output at the t-th iteration, which is the same as the actual value. And (3) adjusting parameters of the two-type model width learning network by using a pseudo-inverse algorithm:
W(t)＝D(t) + Y d (t), (13)
wherein W (t) = [ W i (t)，W j (t)]For the weight between the output layer of the fuzzy width learning network and the fuzzy neural network layer and the enhancement layer at the t-th iteration, W i (t) is the weight between the fuzzy width learning network output layer and the fuzzy neural network layer at the t-th iteration, W j (t) is the weight between the output layer and the enhancement layer of the fuzzy width learning network at the t-th iteration; d (t)＝[O(t)，H(t)]Lambda is a normal number, and is within the interval (0, 1]E is a unit matrix;
(4) let t=t+1, if t is less than or equal to K or a (t) > 0.05, return to step (3); stopping calculating the jump-out circulation if t is more than K and A (t) is less than or equal to 0.05, and finishing training;
(5) Membrane pollution intelligent decision
The trained fuzzy width learning network membrane pollution decision model is utilized, the water permeability decay speed, the produced water flow, the membrane scrubbing air volume, the sludge concentration, the transmembrane pressure difference, the produced water turbidity and the water permeability recovery rate of M test samples are used as input variables of the model, and the membrane pollution type output value of the model is obtained, namely, the operation suggestion corresponding to the type of the sample to be tested is obtained, and the method comprises the following steps: operation advice 1: operation should not exceed 4 hours and reduce water yield by 5% -10%, operation proposal 2: reducing the water yield of the membrane tank, controlling the transmembrane pressure difference to 10-40kPa, and operating recommendation 3: increasing aeration quantity, controlling dissolved oxygen concentration to be 1.5-3.5mg/L, and operating advice to be 4: checking whether the water quality, the water production flow, the membrane scrubbing air quantity and the membrane pool sludge concentration are abnormal or not, and operating advice 5: increasing the sludge discharge amount of the membrane tank, increasing the reflux ratio of the membrane tank, controlling the sludge concentration of the membrane tank to 8000-12000mg/L, and operating the proposal 6: adjusting operation parameters, reducing water yield by 5% -10%, or increasing aeration rate, controlling dissolved oxygen concentration by 2-4mg/L, and operating advice 7: recently, online physical cleaning was developed, and operation advice 8: on-line chemical cleaning is performed within 24 hours, providing decision support for the production process.
The invention mainly comprises the following steps:
(1) Aiming at the problem that the accuracy of obtaining the membrane pollution types based on the operation data means in the current membrane bioreactor sewage treatment is low, the invention provides a membrane pollution intelligent decision method based on knowledge fuzzy width learning, and solves the problem of accurate decision of membrane pollution;
(2) Aiming at the problem of insufficient robustness of the traditional width learning network, the invention provides a fuzzy width learning network structure, and a pair of model neurons are utilized to replace characteristic layer neurons of the width learning network so as to improve the robustness of the network;
(3) Aiming at the problems of the initial setting of the structure and parameters of the fuzzy width learning network, the invention uses the experience knowledge to set the parameters of the fuzzy width learning network decision model, so that the constructed model has proper precision and network structure.
Drawings
FIG. 1 is a topology of a fuzzy breadth-learning network of the present invention;
FIG. 2 is a graph of the film pollution decision training effect of the present invention, wherein the red cross is the actual film pollution type, and the blue circle is the output value of the knowledge-based fuzzy width learning network decision model;
FIG. 3 is a graph showing the effect of film contamination decision test according to the present invention, wherein the red cross is the actual film contamination type, and the blue circle is the output value of the knowledge-based fuzzy width learning network decision model.
Detailed Description
Experimental data were from a sewage treatment plant 2020: the actual detection data of the water permeability, the water permeability decay speed, the water production flow, the membrane scrubbing air volume, the sludge concentration, the transmembrane pressure difference, the water production turbidity and the water permeability recovery rate are respectively taken as process sample data, 100 groups of available data are left after abnormal experimental samples are removed, wherein 60 groups are used as training samples, and the other 40 groups are used as test samples.
The invention adopts the following technical scheme and implementation steps:
1. the intelligent film pollution decision method based on knowledge fuzzy width learning is characterized in that a decision model based on a fuzzy width learning network is established to provide decision support for inhibiting film pollution, wherein a set of fuzzy neurons are adopted to replace characteristic layer neurons of the width learning network, and parameters of the decision model of the fuzzy width learning network are set by using experience knowledge, so that the problem of insufficient data in an actual film pollution decision process is solved, and the accurate decision of film pollution is realized, and the method comprises the following steps:
(1) Determining input and output variables of a membrane pollution decision model: one bottleneck problem of the sewage treatment process of the membrane bioreactor is membrane pollution, and the membrane pollution not only can cause the water quality of effluent to be reduced and the production energy consumption to be improved, but also can cause the breakdown of the sewage treatment process, thereby severely restricting the popularization and the application of the membrane bioreactor. It is therefore necessary to provide decision support for inhibiting membrane fouling. The sewage treatment process of the membrane bioreactor is taken as a research object, the characteristic analysis is carried out on the sewage treatment process variable, and the process variable related to the membrane pollution is selected as the input variable of the intelligent decision model: the water permeability, the water permeability decay rate, the water production flow, the membrane scrubbing air volume, the sludge concentration, the transmembrane pressure difference, the water production turbidity and the water permeability recovery rate; normalizing the acquired input variable to [0,1]; the operation proposal is used as an output variable of the intelligent decision model of membrane pollution; dividing all sample data into two groups, one group containing 60 training samples and the other group containing 40 test samples;
(2) Establishing an intelligent decision model based on a fuzzy width learning network: establishing a membrane pollution decision model by using a fuzzy width learning network, wherein the fuzzy width learning network structure comprises four layers, namely an input layer, a fuzzy neural network layer, an enhancement layer and an output layer; the structure is 8-I-J-8, the number of neurons of a model input layer for membrane pollution decision is determined to be 8, the number of sub-networks of a fuzzy neural network layer is I, and the I is 1,10]Any positive integer in between; the number of the enhancement layer neuron groups is J, and J is [2,20]]Any positive integer in between; the number of neurons of the output layer is 8, 60 training samples are used for training a fuzzy width learning network, and the input quantity of the membrane pollution decision model is x (t) = [ x ] 1 (t),x 2 (t),…,x 60 (t)]，x n (t)＝[x 1n (t),x 2n (t),x 3n (t),x 4n (t),x 5n (t),x 6n (t),x 7n (t),x 8n (t)]For the nth sample at the t-th iteration after normalization, n=1, 2, …,60, x 1n (t) is the water permeability, x, in the nth sample at the nth iteration after normalization 2n (t) is the water permeability decay rate, x, in the nth sample at the nth iteration after normalization 3n (t) is the water production flow rate, x in the nth sample at the t th iteration after normalization 4n (t) is the amount of film scrubbing gas in the nth sample at the nth iteration after normalization，x 5n (t) is the sludge concentration, x in the nth sample at the nth iteration after normalization 6n (t) is the transmembrane pressure difference, x, in the nth sample at the nth iteration after normalization 7n (t) is the turbidity of produced water in the nth sample at the nth iteration after normalization, x 8n (t) the recovery rate of the water permeability in the nth sample at the t th iteration after normalization, and the output quantity of the membrane pollution decision model is the operation proposal Y d (t)＝[Y d1 (t),Y d2 (t),…,Y d60 (t)]，Y dn (t)＝[Y 1dn (t),Y 2dn (t),Y 3dn (t),Y 4dn (t),Y 5dn (t),Y 6dn (t),Y 7dn (t),Y 8dn (t)]Suggesting for the operation of the nth sample at the t-th iteration, Y 1dn (t) is operation proposal 1, namely the operation is not suitable for more than 4 hours and the water yield is reduced by 5 to 10 percent, Y 2dn (t) is operation proposal 2, namely, the water yield of the membrane tank is reduced, the transmembrane pressure difference is controlled to be 10-40kPa, Y 3dn (t) is operation suggestion 3, i.e. increasing aeration rate, controlling dissolved oxygen concentration to 1.5-3.5mg/L, Y 4dn (t) is an operation suggestion 4, namely, checking whether the water quality, the water production flow, the membrane scrubbing air volume and the membrane pool sludge concentration are abnormal or not, Y 5dn (t) is operation proposal 5, namely, the sludge discharge amount of the membrane tank is increased, the reflux ratio of the membrane tank is increased, the sludge concentration of the membrane tank is controlled to be 8000-12000mg/L, Y 6dn (t) is operation suggestion 6, namely, adjusting operation parameters, reducing water yield by 5% -10%, or increasing aeration quantity, controlling dissolved oxygen concentration by 2-4mg/L, Y 7dn (t) is operation suggestion 7, i.e. recently developed on-line physical cleaning, Y 8dn (t) is an operation suggestion 8, namely, on-line chemical cleaning is implemented within 24 hours, and each layer in a decision model based on a fuzzy width learning network is expressed as follows:
fuzzy width learning network input layer: this layer consists of 8 neurons, each outputting the following:
u s (t)＝x s (t),s＝1,2,...,8, (1)
wherein u is s (t) the output value of the s-th neuron of the input layer of the fuzzy width learning network at the t-th iteration;
fuzzy width learning network fuzzy neural network layer: the fuzzy neural network layer consists of I sub-networks, and each fuzzy neural network sub-network structure of the fuzzy neural network layer comprises four layers including an input layer, an hidden layer, a rule layer and an output layer; the structure of the fuzzy neural network is 8-L-L-V, the number of neurons of an input layer of each fuzzy neural network is 8, the number of neurons of an hidden layer is L, the number of neurons of a regular layer is L, and L is any positive integer between [2,20 ]; the number of the neurons of the output layer is V, and V is any positive integer between [2,10 ]; the layer outputs can be expressed as:
fuzzy neural network sub-network input layer: this layer consists of 8 neurons, each outputting the following:
r s (t)＝u s (t), (2)
wherein r is s (t) is the output value of the s-th neuron of the input layer of the fuzzy neural network sub-network at the t-th iteration;
fuzzy neural network sub-network hidden layer: the layer consists of L neurons, and the layer output can be expressed as:
wherein,for the output value of the first neuron of the hidden layer of the fuzzy neural network sub-network at the t-th iteration, c ls (t) is the center of the s-th membership function of the first neuron of the hidden layer at the t-th iteration; sigma (sigma) ls (t) is the width of the s-th membership function of the first neuron of the hidden layer at the t-th iteration;
fuzzy neural network subnetwork rules layer: the layer consists of L neurons, and the layer output can be expressed as:
wherein f l (t) is the output value of the first neuron of the rule layer of the fuzzy neural network sub-network at the t-th iteration;
fuzzy neural network sub-network output layer: the layer consists of V neurons, and the layer output can be expressed as:
wherein o is v (t) is the output value of the v th neuron of the output layer of the fuzzy neural network sub-network at the t-th iteration, w vl (t) is the weight between the v neuron of the output layer and the l neuron of the rule layer at the t iteration;
fuzzy width learning network enhancement layer: the layer consists of J sets of neurons, and the layer output can be expressed as:
H(t)＝[h 1 (t),h 2 (t),...,h J (t)], (6)
h j (t)＝ζ j (O(t)w hj (t)+β hj (t)),j＝1,2,...,J, (7)
wherein H (t) is the output value of the fuzzy width learning network enhancement layer at the t-th iteration, H j (t) is the output value of the jth group of neurons of the enhancement layer at the t-th iteration ζ j () To enhance the activation function of the j-th set of neurons of the layer, O (t) = [ O 1 (t),o 2 (t),…,o I (t)]For the output value o of the fuzzy neural network layer at the t-th iteration i (t)＝[o 1 (t),o 2 (t),…,o V (t)]For the output value of the ith sub-network of the fuzzy neural network layer at the t-th iteration, i=1, 2, …, I, w hj (t) and beta hj (t) weight and bias values between the fuzzy neural network layer and the jth group of neurons of the enhancement layer at the t-th iteration;
fuzzy width learning network output layer: the layer consists of 8 neurons, and the layer output can be expressed as:
wherein Y (t) is the output value of the fuzzy width learning network output layer at the t-th iteration, and w i (t) is the weight value between the output layer of the fuzzy width learning network and the ith sub-network of the fuzzy neural network layer at the t-th iteration, w j (t) is the weight between the jth group of neurons of the fuzzy width learning network output layer and the enhancement layer at the t-th iteration;
(3) Setting an initial structure and parameters of a fuzzy breadth learning network intelligent decision model by using experience knowledge: converting the experience knowledge into a form of fuzzy rule:
wherein,and->For the water permeability x in rule q 1n Lower and upper limit values of ++>And->The film scrubbing air quantity x in the rule q 4n Lower and upper limit values of ++>And->Is the water permeability recovery rate x in the rule q 8n Lower and upper limit values of ++>For fuzzy neural network sub-network output layer v-th neuron output value in rule Q, q=1, …, Q is ruleIs a number of (3). Setting the number L=Q of hidden layer neurons and regular layer neurons of each fuzzy neural network layer sub-network;
setting initial parameters of an intelligent decision model of the fuzzy breadth learning network by using a formula (9):
wherein c qsn (t) the center of the s-th membership function of the q-th neuron of the hidden layer in the nth sample at the t-th iteration,and->The lower bound and the upper bound of the s-th neuron of the input layer corresponding to the q-th neuron of the hidden layer in the t-th iteration are provided; sigma (sigma) qsn (t) the width of the s membership function of the q-th neuron of the hidden layer in the nth sample at the t-th iteration, ρ is a normal number, and values are randomly taken in the interval (0, 1);
(4) Training a decision model based on a fuzzy width learning network, specifically:
(1) setting the current iteration number t=1, and setting the maximum iteration number of a decision model based on a fuzzy width learning network as K=30;
(2) the number of initial fuzzy neural network layer sub-networks of a given fuzzy width learning network is I, the number of enhancement layer neuron groups is J, the number of hidden layer neurons and regular layer neurons of each fuzzy neural network layer sub-network is Q, and the number of output layer neurons is V;
(3) calculating the output Y (t) of the fuzzy breadth learning network according to the formulas (1) - (10), wherein the accuracy of the output of the fuzzy breadth learning network is expressed as:
A(t)＝TF(t)/P, (12)
wherein A (t) is the output accuracy of the fuzzy width learning network at the t-th iteration, and TF (t) is the number of samples of the fuzzy width learning network output at the t-th iteration, which is the same as the actual value. And (3) adjusting parameters of the two-type model width learning network by using a pseudo-inverse algorithm:
W(t)＝D(t) + Y d (t), (13)
wherein W (t) = [ W i (t)，W j (t)]For the weight between the output layer of the fuzzy width learning network and the fuzzy neural network layer and the enhancement layer at the t-th iteration, W i (t) is the weight between the fuzzy width learning network output layer and the fuzzy neural network layer at the t-th iteration, W j (t) is the weight between the output layer and the enhancement layer of the fuzzy width learning network at the t-th iteration; d (t) = [ O (t), H (t)]Lambda is a normal number, and is within the interval (0, 1]E is a unit matrix;
(4) let t=t+1, if t is less than or equal to K or a (t) > 0.05, return to step (3); stopping calculating the jump-out circulation if t is more than K and A (t) is less than or equal to 0.05, and finishing training;
(5) Membrane pollution intelligent decision
Learning a network membrane pollution decision model by using the trained fuzzy width to obtain optimal network parameters and structure of the model, as shown in figure 1; the training result of the intelligent decision method for membrane pollution is shown in fig. 2, and the X axis is as follows: training sample number, Y-axis: training an output value of the membrane pollution type, wherein a red cross is an actual membrane pollution type, and a blue circle is an output value of a knowledge fuzzy width learning network decision model;
the trained membrane pollution decision model is utilized, the water permeability decay rate, the water production flow, the membrane scrubbing air quantity, the sludge concentration, the transmembrane pressure difference, the water production turbidity and the water permeability recovery rate of 40 test samples are used as input variables of the model, and the membrane pollution type output value of the model is obtained, namely, the operation suggestion corresponding to the type to which the sample to be tested belongs is obtained, and the method comprises the following steps: operation advice 1: operation should not exceed 4 hours and reduce water yield by 5% -10%, operation proposal 2: reducing the water yield of the membrane tank, controlling the transmembrane pressure difference to 10-40kPa, and operating recommendation 3: increasing aeration quantity, controlling dissolved oxygen concentration to be 1.5-3.5mg/L, and operating advice to be 4: checking whether the water quality, the water production flow, the membrane scrubbing air quantity and the membrane pool sludge concentration are abnormal or not, and operating advice 5: increasing the sludge discharge amount of the membrane tank, increasing the reflux ratio of the membrane tank, controlling the sludge concentration of the membrane tank to 8000-12000mg/L, and operating the proposal 6: adjusting operation parameters, reducing water yield by 5% -10%, or increasing aeration rate, controlling dissolved oxygen concentration by 2-4mg/L, and operating advice 7: recently, online physical cleaning was developed, and operation advice 8: performing online chemical cleaning within 24 hours; the test result of the intelligent decision method for membrane pollution is shown in fig. 3, and the X axis is as follows: number of test samples, Y axis: the method comprises the steps that a film pollution type test output value, a red cross is an actual film pollution type, and a blue circle is an output value of a knowledge fuzzy width learning network decision model; experimental results show the effectiveness of the network decision method based on knowledge fuzzy width learning.
Claims (1)
1. The intelligent film pollution decision method based on knowledge fuzzy width learning is characterized by comprising the following steps of:
(1) Determining input and output variables of a membrane pollution decision model: the sewage treatment process of the membrane bioreactor is taken as a research object, the characteristic analysis is carried out on the sewage treatment process variable, and the process variable related to the membrane pollution is selected as the input variable of the intelligent decision model: the water permeability, the water permeability decay rate, the water production flow, the membrane scrubbing air volume, the sludge concentration, the transmembrane pressure difference, the water production turbidity and the water permeability recovery rate; normalizing the acquired input variable to [0,1]; the operation proposal is used as an output variable of the intelligent decision model of membrane pollution; dividing all sample data into two groups, wherein one group comprises P training samples, and the other group comprises M test samples, and P is required to be more than M;
(2) Establishing an intelligent decision model based on a fuzzy width learning network: establishing a sludge expansion decision model by using a fuzzy width learning network, wherein the fuzzy width learning network structure has four layers including an input layer and a modelA paste neural network layer, an enhancement layer and an output layer; the structure is 8-I-J-8, the number of neurons of a model input layer for membrane pollution decision is determined to be 8, the number of sub-networks of a fuzzy neural network layer is I, and the I is 1,10]Any positive integer in between; the number of the enhancement layer neuron groups is J, and J is [2,20]]Any positive integer in between; the number of neurons of the output layer is 8, the fuzzy width learning network is trained by using P training samples, and the input quantity of the membrane pollution decision model is x (t) = [ x ] 1 (t),x 2 (t),…,x P (t)]，x n (t)＝[x 1n (t),x 2n (t),x 3n (t),x 4n (t),x 5n (t),x 6n (t),x 7n (t),x 8n (t)]For the nth sample at the t-th iteration after normalization, n=1, 2, …, P, x 1n (t) is the water permeability, x, in the nth sample at the nth iteration after normalization 2n (t) is the water permeability decay rate, x, in the nth sample at the nth iteration after normalization 3n (t) is the water production flow rate, x in the nth sample at the t th iteration after normalization 4n (t) is the film scrubbing air volume, x in the nth sample at the t th iteration after normalization 5n (t) is the sludge concentration, x in the nth sample at the nth iteration after normalization 6n (t) is the transmembrane pressure difference, x, in the nth sample at the nth iteration after normalization 7n (t) is the turbidity of produced water in the nth sample at the nth iteration after normalization, x 8n (t) the recovery rate of the water permeability in the nth sample at the t th iteration after normalization, and the output quantity of the membrane pollution decision model is the operation proposal Y d (t)＝[Y d1 (t),Y d2 (t),…,Y dP (t)]，Y dn (t)＝[Y 1dn (t),Y 2dn (t),Y 3dn (t),Y 4dn (t),Y 5dn (t),Y 6dn (t),Y 7dn (t),Y 8dn (t)]Suggesting for the operation of the nth sample at the t-th iteration, Y 1dn (t) is operation proposal 1, namely the operation is not suitable for more than 4 hours and the water yield is reduced by 5 to 10 percent, Y 2dn (t) is operation proposal 2, namely, the water yield of the membrane tank is reduced, the transmembrane pressure difference is controlled to be 10-40kPa, Y 3dn (t) is operation suggestion 3, i.e. increasing aeration rate, controlling dissolved oxygen concentration to 1.5-3.5mg/L, Y 4dn (t) is the operation proposal 4, namelyChecking whether the water quality, water flow, membrane scrubbing air quantity and membrane pool sludge concentration are abnormal or not, Y 5dn (t) is operation proposal 5, namely, the sludge discharge amount of the membrane tank is increased, the reflux ratio of the membrane tank is increased, the sludge concentration of the membrane tank is controlled to be 8000-12000mg/L, Y 6dn (t) is operation suggestion 6, namely, adjusting operation parameters, reducing water yield by 5% -10%, or increasing aeration quantity, controlling dissolved oxygen concentration by 2-4mg/L, Y 7dn (t) is an operation suggestion 7, i.e. to develop on-line physical cleaning, Y 8dn (t) is an operation suggestion 8, namely, on-line chemical cleaning is implemented within 24 hours, and each layer in a decision model based on a fuzzy width learning network is expressed as follows:
fuzzy width learning network input layer: this layer consists of 8 neurons, each outputting the following:
u s (t)＝x s (t),s＝1,2,...,8, (1)
wherein u is s (t) the output value of the s-th neuron of the input layer of the fuzzy width learning network at the t-th iteration;
fuzzy width learning network fuzzy neural network layer: the fuzzy neural network layer consists of I sub-networks, and each fuzzy neural network sub-network structure of the fuzzy neural network layer comprises four layers including an input layer, an hidden layer, a rule layer and an output layer; the structure of the fuzzy neural network is 8-L-L-V, the number of neurons of an input layer of each fuzzy neural network is 8, the number of neurons of an hidden layer is L, the number of neurons of a regular layer is L, and L is any positive integer between [2,20 ]; the number of the neurons of the output layer is V, and V is any positive integer between [2,10 ]; the layer outputs can be expressed as:
fuzzy neural network sub-network input layer: this layer consists of 8 neurons, each outputting the following:
r s (t)＝u s (t), (2)
wherein r is s (t) is the output value of the s-th neuron of the input layer of the fuzzy neural network sub-network at the t-th iteration;
fuzzy neural network sub-network hidden layer: the layer consists of L neurons, and the layer output can be expressed as:
wherein,for the output value of the first neuron of the hidden layer of the fuzzy neural network sub-network at the t-th iteration, c ls (t) is the center of the s-th membership function of the first neuron of the hidden layer at the t-th iteration; sigma (sigma) ls (t) is the width of the s-th membership function of the first neuron of the hidden layer at the t-th iteration;
fuzzy neural network subnetwork rules layer: the layer consists of L neurons, and the layer output can be expressed as:
wherein f l (t) is the output value of the first neuron of the rule layer of the fuzzy neural network sub-network at the t-th iteration;
fuzzy neural network sub-network output layer: the layer consists of V neurons, and the layer output can be expressed as:
wherein o is v (t) is the output value of the v th neuron of the output layer of the fuzzy neural network sub-network at the t-th iteration, w vl (t) is the weight between the v neuron of the output layer and the l neuron of the rule layer at the t iteration;
fuzzy width learning network enhancement layer: the layer consists of J sets of neurons, and the layer output can be expressed as:
H(t)＝[h 1 (t),h 2 (t),...,h J (t)], (6)
h j (t)＝ζ j (O(t)w hj (t)+β hj (t)),j＝1,2,...,J, (7)
wherein H (t) is the output value of the fuzzy width learning network enhancement layer at the t-th iteration, H j (t) is the output value of the jth group of neurons of the enhancement layer at the t-th iteration ζ j () To enhance the activation function of the j-th set of neurons of the layer, O (t) = [ O 1 (t),o 2 (t),…,o I (t)]For the output value o of the fuzzy neural network layer at the t-th iteration i (t)＝[o 1 (t),o 2 (t),…,o V (t)]For the output value of the ith sub-network of the fuzzy neural network layer at the t-th iteration, i=1, 2, …, I, w hj (t) and beta hj (t) weight and bias values between the fuzzy neural network layer and the jth group of neurons of the enhancement layer at the t-th iteration;
fuzzy width learning network output layer: the layer consists of 8 neurons, and the layer output can be expressed as:
wherein Y (t) is the output value of the fuzzy width learning network output layer at the t-th iteration, and w i (t) is the weight value between the output layer of the fuzzy width learning network and the ith sub-network of the fuzzy neural network layer at the t-th iteration, w j (t) is the weight between the jth group of neurons of the fuzzy width learning network output layer and the enhancement layer at the t-th iteration;
(3) Setting an initial structure and parameters of a fuzzy breadth learning network intelligent decision model by using experience knowledge: converting the experience knowledge into a form of fuzzy rule:
wherein,and->For the water permeability x in rule q 1n Lower and upper limit values of ++>And->The film scrubbing air quantity x in the rule q 4n Lower and upper limit values of ++>And->Is the water permeability recovery rate x in the rule q 8n Lower and upper limit values of ++>For the output value of the v-th neuron in the output layer of the fuzzy neural network sub-network in the rule Q, q=1, …, and Q is the number of the rules; setting the number L=Q of hidden layer neurons and regular layer neurons of each fuzzy neural network layer sub-network;
setting initial parameters of an intelligent decision model of the fuzzy breadth learning network by using a formula (9):
wherein c qsn (t) the center of the s-th membership function of the q-th neuron of the hidden layer in the nth sample at the t-th iteration,and->Hidden layer at the t-th iterationThe lower bound and the upper bound of the s-th neuron of the input layer corresponding to the q neurons; sigma (sigma) qsn (t) the width of the s membership function of the q-th neuron of the hidden layer in the nth sample at the t-th iteration, ρ is a normal number, and values are randomly taken in the interval (0, 1);
(4) Training a decision model based on a fuzzy width learning network, specifically:
(1) setting the current iteration number t=1, and setting the maximum iteration number of a decision model based on a fuzzy width learning network as K=30;
(2) the number of initial fuzzy neural network layer sub-networks of a given fuzzy width learning network is I, the number of enhancement layer neuron groups is J, the number of hidden layer neurons and regular layer neurons of each fuzzy neural network layer sub-network is Q, and the number of output layer neurons is V;
(3) calculating the output Y (t) of the fuzzy breadth learning network according to the formulas (1) - (10), wherein the accuracy of the output of the fuzzy breadth learning network is expressed as:
A(t)＝TF(t)/P, (12)
wherein A (t) is the output accuracy of the fuzzy width learning network at the t-th iteration, and TF (t) is the number of samples of the fuzzy width learning network output at the t-th iteration, which is the same as the actual value; and (3) adjusting parameters of the two-type model width learning network by using a pseudo-inverse algorithm:
W(t)＝D(t) + Y d (t), (13)
wherein W (t) = [ W i (t)，W j (t)]For the weight between the output layer of the fuzzy width learning network and the fuzzy neural network layer and the enhancement layer at the t-th iteration, W i (t) is the weight between the fuzzy width learning network output layer and the fuzzy neural network layer at the t-th iteration, W j (t) is the weight between the output layer and the enhancement layer of the fuzzy width learning network at the t-th iteration; d (t) = [ O (t), H (t)]Lambda is a normal number, and is within the interval (0, 1]E is a unit matrix;
(4) let t=t+1, if t is less than or equal to K or a (t) > 0.05, return to step (3); stopping calculating the jump-out circulation if t is more than K and A (t) is less than or equal to 0.05, and finishing training;
(5) Membrane pollution intelligent decision
The trained fuzzy width learning network membrane pollution decision model is utilized, the water permeability decay speed, the produced water flow, the membrane scrubbing air volume, the sludge concentration, the transmembrane pressure difference, the produced water turbidity and the water permeability recovery rate of M test samples are used as input variables of the model, and the membrane pollution type output value of the model is obtained, namely, the operation suggestion corresponding to the type of the sample to be tested is obtained, and the method comprises the following steps: operation advice 1: operation should not exceed 4 hours and reduce water yield by 5% -10%, operation proposal 2: reducing the water yield of the membrane tank, controlling the transmembrane pressure difference to 10-40kPa, and operating recommendation 3: increasing aeration quantity, controlling dissolved oxygen concentration to be 1.5-3.5mg/L, and operating advice to be 4: checking whether the water quality, the water production flow, the membrane scrubbing air quantity and the membrane pool sludge concentration are abnormal or not, and operating advice 5: increasing the sludge discharge amount of the membrane tank, increasing the reflux ratio of the membrane tank, controlling the sludge concentration of the membrane tank to 8000-12000mg/L, and operating the proposal 6: adjusting operation parameters, reducing water yield by 5% -10%, or increasing aeration rate, controlling dissolved oxygen concentration by 2-4mg/L, and operating advice 7: developing online physical cleaning, and operating advice 8: in-line chemical cleaning was performed within 24 hours.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110421204.2A CN113313230B (en) | 2021-04-19 | 2021-04-19 | Film pollution intelligent decision-making method based on knowledge fuzzy width learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110421204.2A CN113313230B (en) | 2021-04-19 | 2021-04-19 | Film pollution intelligent decision-making method based on knowledge fuzzy width learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113313230A CN113313230A (en) | 2021-08-27 |
| CN113313230B true CN113313230B (en) | 2024-04-16 |
Family
ID=77372547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110421204.2A Active CN113313230B (en) | 2021-04-19 | 2021-04-19 | Film pollution intelligent decision-making method based on knowledge fuzzy width learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113313230B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096730A (en) * | 2016-06-09 | 2016-11-09 | 北京工业大学 | A kind of intelligent detecting method of MBR film permeability rate based on Recurrent RBF Neural Networks |
| CN108375534A (en) * | 2018-02-06 | 2018-08-07 | 北京工业大学 | MBR fouling membrane intelligent early-warning methods |
| CN109133351A (en) * | 2018-08-29 | 2019-01-04 | 北京工业大学 | Membrane bioreactor-MBR fouling membrane intelligent early-warning method |
| CN112101402A (en) * | 2020-07-22 | 2020-12-18 | 北京工业大学 | Membrane pollution early warning method based on knowledge fuzzy learning |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0809443D0 (en) * | 2008-05-23 | 2008-07-02 | Wivenhoe Technology Ltd | A Type-2 fuzzy based system for handling group decisions |
-
2021
- 2021-04-19 CN CN202110421204.2A patent/CN113313230B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096730A (en) * | 2016-06-09 | 2016-11-09 | 北京工业大学 | A kind of intelligent detecting method of MBR film permeability rate based on Recurrent RBF Neural Networks |
| CN108375534A (en) * | 2018-02-06 | 2018-08-07 | 北京工业大学 | MBR fouling membrane intelligent early-warning methods |
| CN109133351A (en) * | 2018-08-29 | 2019-01-04 | 北京工业大学 | Membrane bioreactor-MBR fouling membrane intelligent early-warning method |
| CN112101402A (en) * | 2020-07-22 | 2020-12-18 | 北京工业大学 | Membrane pollution early warning method based on knowledge fuzzy learning |
| 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 |
Non-Patent Citations (3)
| Title |
|---|
| MBR膜污染的智能模拟预测方法研究;闫宏英;李春青;;计算机测量与控制;20130825(第08期);全文 * |
| 一种粗糙模糊神经网络识别器及其应用;赵晓霞;;中北大学学报(自然科学版);20090615(第03期);全文 * |
| 基于自组织模糊神经网络的污水处理出水水质预测建模;马玉芩;姜涛;;信息技术与信息化;20130815(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113313230A (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105510546B (en) | A kind of biochemical oxygen demand (BOD) BOD intelligent detecting methods based on self-organizing Recurrent RBF Neural Networks | |
| CN103744293B (en) | Wastewater treatment monitoring method and system based on fuzzy neural network | |
| CN106295800B (en) | A kind of water outlet total nitrogen TN intelligent detecting method based on recurrence Self organizing RBF Neural Network | |
| CN112183719B (en) | Intelligent detection method for total nitrogen in effluent based on multi-objective optimization-fuzzy neural network | |
| CN101576734B (en) | Dissolved oxygen control method based on dynamic radial basis function neural network | |
| CN102854296B (en) | Sewage-disposal soft measurement method on basis of integrated neural network | |
| CN106096730B (en) | A kind of intelligent detecting method of the MBR film permeability rates based on Recurrent RBF Neural Networks | |
| CN103499982B (en) | A kind of sewage disposal process self-organization control method | |
| CN109473182B (en) | MBR (Membrane biological reactor) membrane water permeability intelligent detection method based on deep belief network | |
| CN102262147A (en) | Soft measurement method and system for effluent chemical oxygen demand (COD) of waste water treatment system | |
| CN108375534A (en) | MBR fouling membrane intelligent early-warning methods | |
| CN112101402B (en) | Membrane pollution early warning method based on knowledge fuzzy learning | |
| CN110928187A (en) | Sewage treatment process fault monitoring method based on fuzzy width self-adaptive learning model | |
| CN112250166B (en) | Printing and dyeing wastewater efficient detoxification gradient treatment method based on intelligent SBR electrode process | |
| CN102879541B (en) | Online biochemical oxygen demand (BOD) soft measurement method based on dynamic feedforward neural network | |
| CN113313230B (en) | Film pollution intelligent decision-making method based on knowledge fuzzy width learning | |
| CN106769748B (en) | Intelligent detection system for water permeability of membrane bioreactor-MBR (Membrane bioreactor) | |
| CN114565154A (en) | Prediction method and optimization algorithm for carbon source adding amount of biochemical section of leachate | |
| CN113156074B (en) | Effluent total nitrogen prediction method based on fuzzy migration | |
| CN112250246B (en) | Intelligent azo dye wastewater detoxification and advanced treatment method | |
| CN111204867B (en) | Membrane bioreactor-MBR membrane pollution intelligent decision-making method | |
| CN110412878B (en) | PID-RBF steady state estimation and LSSVM soft measurement sewage BOD control method | |
| Gharghory et al. | Modified PSO for optimal tuning of fuzzy PID controller | |
| Huang et al. | Modeling and optimization of the activated sludge process | |
| CN114859711B (en) | Urban sewage treatment aeration process control method based on fuzzy second-order sliding mode |
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 |