CN116151121B - Neural network-based effluent NH4-N soft measurement method - Google Patents
Neural network-based effluent NH4-N soft measurement method Download PDFInfo
- Publication number
- CN116151121B CN116151121B CN202310181946.1A CN202310181946A CN116151121B CN 116151121 B CN116151121 B CN 116151121B CN 202310181946 A CN202310181946 A CN 202310181946A CN 116151121 B CN116151121 B CN 116151121B
- Authority
- CN
- China
- Prior art keywords
- network
- sub
- echo state
- weight
- constructing
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 13
- 238000000691 measurement method Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 54
- 239000011159 matrix material Substances 0.000 claims abstract description 24
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 24
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims abstract description 12
- 230000009191 jumping Effects 0.000 claims abstract description 5
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 9
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 9
- 230000033116 oxidation-reduction process Effects 0.000 claims description 9
- 229910052760 oxygen Inorganic materials 0.000 claims description 9
- 239000001301 oxygen Substances 0.000 claims description 9
- 239000007787 solid Substances 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 2
- 239000010865 sewage Substances 0.000 abstract description 13
- 238000004458 analytical method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Crystallography & Structural Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Purification Treatments By Anaerobic Or Anaerobic And Aerobic Bacteria Or Animals (AREA)
Abstract
The invention provides a neural network-based effluent NH4-N soft measurement method, which comprises the following steps: initializing a network structure and network parameters of the constructed echo state network; constructing a sub-reserve pool according to a singular value decomposition method based on the initialized echo state network; optimizing the sub-pool according to the condition number and the differential evolution algorithm; updating the optimized weight, input weight and state matrix of the sub-reserve pool, judging whether the iteration times are smaller than a preset iteration threshold, if so, jumping to the step of constructing the sub-reserve pool according to a singular value decomposition method based on the initialized echo state network; if yes, calculating an output weight; testing the echo state network according to the output weight and the test sample to obtain a determined effluent NH4-N detection model; and inputting the data to be detected into a determined effluent NH4-N detection model to obtain a detection result. The invention provides a high-efficiency and rapid solution for measuring key water quality parameters in the sewage treatment process.
Description
Technical Field
The invention relates to the technical field of water treatment, in particular to a neural network-based effluent NH4-N soft measurement method.
Background
With the rapid development of urban and industrialized production in the current society, the water environment in China is seriously destroyed. The sewage discharge not only seriously affects the daily life of residents, but also destroys the ecological balance of the nature. In order to reduce the discharge amount of sewage and realize the recycling of the water, sewage treatment plants are established in various places nationwide. In the sewage treatment process, the NH4-N concentration is an important parameter for measuring the performance of a sewage treatment process (WWTP), however, the sewage treatment process is a complex system with the characteristics of high nonlinearity, large hysteresis, large time variation, multivariable coupling and the like, and the maintenance cost is high, so that the prediction of the sewage treatment process is still a pending problem. Therefore, it is necessary to predict the concentration of NH4-N in the effluent at low cost and high efficiency for the quality of the effluent to be checked and for the sewage treatment plant to be stably operated.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a neural network-based effluent NH4-N soft measurement method, and the method can predict the ammonia nitrogen concentration in the sewage treatment process by combining a differential evolution algorithm with condition number analysis to construct a novel echo state network.
In order to achieve the above object, the present invention provides the following solutions:
a neural network-based effluent NH4-N soft measurement method comprises the following steps:
constructing an echo state network, and initializing a network structure and network parameters of the echo state network; the input variables of the echo state network comprise water inlet temperature, total solid suspended matters, dissolved oxygen concentration, pH value and water outlet oxidation-reduction potential; the output variables of the echo state network comprise ammonia nitrogen concentration;
constructing a sub-reserve pool according to a singular value decomposition method based on the initialized echo state network;
optimizing the sub-pool according to condition numbers and a differential evolution algorithm;
updating the optimized weight, input weight and state matrix of the sub-reserve pool, judging whether the iteration times are smaller than a preset iteration threshold, if so, jumping to the step of constructing the sub-reserve pool according to a singular value decomposition method based on the initialized echo state network; if yes, calculating an output weight;
testing the echo state network according to the output weight and the sample to be tested to obtain a determined effluent NH4-N detection model;
and inputting the data to be detected into a determined effluent NH4-N detection model to obtain a detection result.
Preferably, initializing a network structure and network parameters of the echo state network includes:
determining the initial structure of the echo state network to be 5-N-1; wherein N represents the number of sub-pool nodes; the size of N is gradually increased;
using a sigmoid function as a network activation function G (·), determining an initial iteration number i=1 and a maximum iteration number i max Training samples less than or equal to 30Wherein u is k Represents the k-th set of input samples, t k Represents the k-th set of actual output values, +.>Representing the dimension of the input samples as n, and L as the total number of samples;
randomly initializing network input weight W in And the pool internal weight W is between (0, 1).
Preferably, the constructing the sub-pool according to the singular value decomposition method based on the initialized echo state network includes:
randomly generating a diagonal matrixTwo orthogonal matrices U i And V i The method comprises the steps of carrying out a first treatment on the surface of the Wherein,for randomly generated values between (0, 1), n k The number of nodes of the sub reserve pool;
constructing sub-reserves Chi W using the diagonal matrix and two of the orthogonal matrices i ＝U i S i V i 。
Preferably, said optimizing said sub-pool according to condition number and differential evolution algorithm comprises:
construction of fitness function fitness (ΔW i )＝κ(H i )-κ(H i-1 ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein, kappa (H) i ) Representing the condition number of the state matrix corresponding to the pool after the new sub-pool is added;
initializing an initial population np=50, mutating operator f=0.7, crossing operator cr=0.5, and initializing the populationWherein n is {1,2 …, NP }, and a maximum iteration number G is set;
according to the formulaObtaining variant individual mu n The method comprises the steps of carrying out a first treatment on the surface of the Wherein r is 1 ,r 2 ,r 3 ∈[1,NP]Are three mutually different integers;
by passing throughFinishing the crossover operation for each individual +.>Obtaining cross subject->Wherein j e {1,2 …,10}, rand e (0, 1) is randomly generated;
and after the algorithm reaches the maximum iteration times, terminating the algorithm flow, returning to the optimal individual, and constructing a new sub-storage pool by using the optimal individual.
Preferably, the optimized weight, input weight and state matrix of the sub-reservoir are updated, and whether the iteration number is smaller than a preset iteration threshold is judged, if yes, the step is skipped to the step of constructing the sub-reservoir according to a singular value decomposition method based on the initialized echo state network; if yes, calculating an output weight, including:
updating the weight of the reserve pool to be
Updating the input weight to
Updating the state matrix to h= [ H ] 1 ,…,H i ]；
If i is more than or equal to i max Executing the next step, otherwise returning to the step of constructing a sub-reserve pool according to a singular value decomposition method based on the initialized echo state network;
by the formula W out ＝H Γ T calculates the output weight W out The method comprises the steps of carrying out a first treatment on the surface of the Wherein Γ represents pseudo-inverse computation, and T is target output data.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a neural network-based effluent NH4-N soft measurement method, which comprises the following steps: constructing an echo state network, and initializing a network structure and network parameters of the echo state network; the input variables of the echo state network comprise water inlet temperature, total solid suspended matters, dissolved oxygen concentration, pH value and water outlet oxidation-reduction potential; the output variables of the echo state network comprise ammonia nitrogen concentration; constructing a sub-reserve pool according to a singular value decomposition method based on the initialized echo state network; optimizing the sub-pool according to condition numbers and a differential evolution algorithm; updating the optimized weight, input weight and state matrix of the sub-reserve pool, judging whether the iteration times are smaller than a preset iteration threshold, if so, jumping to the step of constructing the sub-reserve pool according to a singular value decomposition method based on the initialized echo state network; if yes, calculating an output weight; testing the echo state network according to the output weight and the sample to be tested to obtain a determined effluent NH4-N detection model; and inputting the data to be detected into a determined effluent NH4-N detection model to obtain a detection result. The invention provides a high-efficiency and rapid solution for measuring key water quality parameters in the sewage treatment process.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method according to an embodiment of the present invention;
fig. 2 is a topology structure diagram of a neural network according to an embodiment of the present invention;
FIG. 3 is a graph showing the absolute value distribution of output weights according to an embodiment of the present invention;
FIG. 4 is a graph of the predicted NH4-N concentration result of the effluent provided by the embodiment of the invention;
FIG. 5 is a chart of the prediction error of the NH4-N concentration of the effluent provided by the embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The terms "first," "second," "third," and "fourth" and the like in the description and in the claims of this application and in the drawings, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, inclusion of a list of steps, processes, methods, etc. is not limited to the listed steps but may alternatively include steps not listed or may alternatively include other steps inherent to such processes, methods, products, or apparatus.
The invention aims to provide a neural network-based effluent NH4-N soft measurement method, which can provide a high-efficiency and rapid solution for measuring key water quality parameters in the sewage treatment process.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Fig. 1 is a flowchart of a method provided by an embodiment of the present invention, and as shown in fig. 1, the present invention provides a method for soft measurement of NH4-N in effluent based on a neural network, including:
step 100: constructing an echo state network, and initializing a network structure and network parameters of the echo state network; the input variables of the echo state network comprise water inlet temperature, total solid suspended matters, dissolved oxygen concentration, pH value and water outlet oxidation-reduction potential; the output variables of the echo state network comprise ammonia nitrogen concentration;
step 200: constructing a sub-reserve pool according to a singular value decomposition method based on the initialized echo state network;
step 300: optimizing the sub-pool according to condition numbers and a differential evolution algorithm;
step 400: updating the optimized weight, input weight and state matrix of the sub-reserve pool, judging whether the iteration times are smaller than a preset iteration threshold, if so, jumping to the step of constructing the sub-reserve pool according to a singular value decomposition method based on the initialized echo state network; if yes, calculating an output weight;
step 500: testing the echo state network according to the output weight and the sample to be tested to obtain a determined effluent NH4-N detection model;
step 600: and inputting the data to be detected into a determined effluent NH4-N detection model to obtain a detection result.
Preferably, initializing a network structure and network parameters of the echo state network includes:
determining the initial structure of the echo state network to be 5-N-1; wherein N represents the number of sub-pool nodes; the size of N is gradually increased;
using a sigmoid function as a network activation function G (·), determining an initial iteration number i=1 and a maximum iteration number i max Training samples less than or equal to 30Wherein u is k Represents the k-th set of input samples, t k Represents the k-th set of actual output values, +.>Representing the dimension of the input samples as n, and L as the total number of samples;
randomly initializing network input weight W in And the pool internal weight W is between (0, 1).
Specifically, in the method for soft measurement of effluent NH4-N based on the CNEESN neural network in this embodiment, the network is a continuously growing network, and the main operation flow is as follows: firstly, a small-scale reserve pool is generated, corresponding weights are initialized, singular values randomly generated by a Singular Value Decomposition (SVD) method are optimized and utilized according to condition number analysis and differential evolution algorithm, a new sub-reserve pool is built by utilizing the optimized singular values, and then the new sub-reserve pool is added into a network, as shown in figure 2. In the embodiment, after each sub-reserve tank is added into the network by using condition number analysis and differential evolution algorithm, the condition number of the reserve tank of the network is as small as possible, so that a better output weight is obtained through training, and then the ammonia nitrogen concentration in the sewage treatment process is predicted. The embodiment comprises the following steps:
step 1: initializing network structure and parameters
Step 1.1: initializing a network structure
And taking the water inlet temperature, the total solid suspended matters, the dissolved oxygen concentration, the pH value and the oxidation-reduction potential of the water outlet as input variables, and the ammonia nitrogen concentration as output variables, and determining the initial structure of the echo state network to be 5-N-1, wherein N represents the number of nodes of the sub-reserve pool. The number N of the pool nodes of the typical echo state network is equal to or more than 50 and equal to or less than 1000, but the model proposed by the method is a growth model, and the size of N is gradually increased. The initial N in the network takes 10, namely the network contains 5 input nodes, 10 reserve pool nodes and 1 output node.
Step 1.2: initializing network parameters
Using a sigmoid function as a network activation function G (·), determining an initial iteration number i=1 and a maximum iteration number i max Training samples less than or equal to 30u k Represents the k-th set of input samples, t k Represents the k-th set of actual output values, +.>Representing the dimension of the input samples as n, and L as the total number of samples; randomly initializing network input weight W in And the pool internal weight W is between (0, 1).
Preferably, the constructing the sub-pool according to the singular value decomposition method based on the initialized echo state network includes:
randomly generating a diagonal matrixTwo orthogonal matrices U i And V i The method comprises the steps of carrying out a first treatment on the surface of the Wherein,for randomly generated values between (0, 1), n k The number of nodes of the sub reserve pool;
constructing sub-reserves Chi W using the diagonal matrix and two of the orthogonal matrices i ＝U i S i V i 。
Alternatively, step 2 of the present embodiment is to construct sub-reservoirs from singular value decomposition. The present embodiment randomly generates a diagonal matrixTwo orthogonal matrices U i And V i Using three matrices, a sub-store Chi W can be constructed i ＝U i S i V i . By this means ΔW can be ensured i And S is i With the same singular values, thus guaranteeing ESP characteristics.
Preferably, said optimizing said sub-pool according to condition number and differential evolution algorithm comprises:
construction of fitness function fitness (ΔW i )＝κ(H i )-κ(H i-1 ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein, kappa (H) i ) Representing the condition number of the state matrix corresponding to the pool after the new sub-pool is added;
initializing an initial population np=50, mutating operator f=0.7, crossing operator cr=0.5, and initializing the populationWherein n is {1,2 …, NP }, and a maximum iteration number G is set;
according to the formulaObtaining variant individual mu n The method comprises the steps of carrying out a first treatment on the surface of the Wherein r is 1 ,r 2 ,r 3 ∈[1,NP]Are three mutually different integers;
by passing throughFinishing the crossover operation for each individual +.>Obtaining cross subject->Wherein j e {1,2 …,10}, rand e (0, 1) is randomly generated;
and after the algorithm reaches the maximum iteration times, terminating the algorithm flow, returning to the optimal individual, and constructing a new sub-storage pool by using the optimal individual.
Specifically, step 3 in this embodiment is to optimize the sub-pool according to the condition number and the differential evolution algorithm, and specifically includes the following steps:
step 3.1: the design fitness function is based on the theoretical analysis of the condition number of the matrix, and it is known that the larger the condition number is, the more easily the problem of pathological solution is generated when the operation of the matrix is performed. The present embodiment therefore designs a fitness function to measure the performance of the newly created sub-reservoirs. The specific calculation mode is as follows:
fitness(ΔW i )＝κ(H i )-κ(H i-1 ) (1)
wherein kappa (H) i ) Representing the condition number of the state matrix corresponding to the pool after the addition of the new sub-pool.
Step 3.2: optimizing SVD generated singular values using differential evolutionary algorithm
Initial population np=50, mutation operator f=0.7, crossover operator cr=0.5. Initializing a populationWhere n ε {1,2 …, NP } and set the maximum number of iterations G.
Obtaining variant individuals through a formula (2)μ n
Wherein r is 1 ,r 2 ,r 3 ∈[1,NP]Are three mutually different integers.
Performing a crossover operation by equation (3), σ for each individual j n gives the crossover individual gamma j n
Where j ε {1,2 …,10}, rand ε (0, 1) is randomly generated.
The selection operation is completed by the formula (4)
fitness (·) represents fitness function calculation in equation (1).
And after the algorithm reaches the maximum iteration times, terminating the algorithm flow, and returning to the optimal individual. The individual is used to construct a new sub-pool.
Preferably, the optimized weight, input weight and state matrix of the sub-reservoir are updated, and whether the iteration number is smaller than a preset iteration threshold is judged, if yes, the step is skipped to the step of constructing the sub-reservoir according to a singular value decomposition method based on the initialized echo state network; if yes, calculating an output weight, including:
updating the weight of the reserve pool to be
Updating the input weight to
Updating the state matrix to h= [ H ] 1 ,…,H i ]；
If i is more than or equal to i max Executing the next step, otherwise returning to the step of constructing a sub-reserve pool according to a singular value decomposition method based on the initialized echo state network;
by the formula W out ＝H Γ T calculates the output weight W out The method comprises the steps of carrying out a first treatment on the surface of the Wherein Γ represents pseudo-inverse computation, and T is target output data.
Further, step 4 in this embodiment is to update the structure and parameters of the network. The embodiment updates the weight of the reserve pool asThe input weight is updated to->The state matrix is updated to h= [ H ] 1 ,…,H i ]。
If i is more than or equal to i max Step 5 is executed, otherwise step 2 is returned.
Further, as shown in fig. 3, step 5 in this embodiment: and calculating an output weight. The output weight can be calculated by equation (5):
W out ＝H Γ T(5)
where Γ represents the pseudo-inverse, and T is the target output data.
In addition, step 6 of the present embodiment is a test network, and the output weight W obtained by the above steps is used out And inputting a test sample to test the network. In this example, the tested network was applied to the prediction of NH4-N concentration in the effluent, and the results and errors are shown in FIGS. 4 and 5, respectively.
The data samples in this example are shown below, with tables 1-12 being experimental data for the present invention. Tables 1-5 are training input samples: the water inlet temperature, the aerobic end dissolved oxygen, the total solid suspended matters at the aerobic end, the pH value of the water outlet and the oxidation-reduction potential of the water outlet are shown in a table 6, the concentration of ammonia nitrogen in the water outlet of a training sample, and tables 7-11 are test input samples: the water inlet temperature, the aerobic end dissolved oxygen, the total solid suspended matters at the aerobic end, the pH value of the effluent, the oxidation-reduction potential of the effluent, and the concentration of ammonia nitrogen in the effluent of the test sample are shown in Table 12.
TABLE 1 auxiliary variable inlet Water temperature (. Degree.C.)
TABLE 2 auxiliary variable dissolved oxygen (mg/L)
TABLE 3 auxiliary variable total solids suspension (mg/L)
/>
TABLE 4 auxiliary variable pH
/>
TABLE 5 oxidation-reduction potential of auxiliary variables
/>
Table 6 shows the NH4-N concentration (mg/L)
/>
The test samples were as follows:
TABLE 7 auxiliary variable inlet temperature (. Degree. C.)
| 26.6664 | 25.5925 | 26.0751 | 26.8655 | 24.9307 | 24.9436 | 25.2516 | 25.8255 | 24.9177 | 25.4691 |
| 25.6463 | 23.6239 | 26.7961 | 23.3835 | 25.5664 | 25.6231 | 23.6806 | 24.1833 | 25.5388 | 25.7410 |
| 25.9991 | 25.5576 | 24.9465 | 24.9725 | 24.7418 | 27.2087 | 25.8663 | 26.7136 | 24.9061 | 25.6696 |
| 24.6813 | 23.2770 | 23.8631 | 24.9667 | 26.8065 | 24.4801 | 24.8874 | 25.4850 | 22.9625 | 25.2472 |
| 25.9962 | 27.1094 | 25.6289 | 25.4081 | 24.2291 | 25.4720 | 27.2028 | 25.3994 | 25.5649 | 24.6698 |
| 24.9018 | 24.5476 | 25.3617 | 23.7378 | 24.3022 | 24.9840 | 22.8098 | 25.0100 | 25.2979 | 25.0303 |
| 27.0784 | 24.2721 | 24.4198 | 24.9826 | 25.6667 | 23.0559 | 23.7307 | 25.4778 | 25.3893 | 25.5126 |
| 25.6725 | 25.4067 | 25.0534 | 23.1565 | 25.0881 | 24.9119 | 24.9667 | 24.9480 | 24.8686 | 26.9098 |
| 25.9305 | 23.2841 | 25.3486 | 25.2993 | 24.5188 | 25.4371 | 24.9480 | 27.2933 | 25.9845 | 25.4618 |
| 25.2212 | 27.0562 | 23.1027 | 24.8614 | 25.0852 | 24.5591 | 25.4153 | 25.6260 | 26.9349 | 25.3501 |
| 25.3486 | 24.3796 | 25.2936 | 23.6253 | 24.5404 | 24.2047 | 26.7917 | 24.6051 | 25.6158 | 24.6368 |
| 22.9115 | 24.9047 | 25.2559 | 26.5046 | 27.1331 | 25.9641 | 24.9999 | 26.0429 | 23.6295 | 24.6698 |
| 24.7908 | 24.7490 | 26.0283 | 23.0630 | 25.4952 | 25.1589 | 23.2032 | 23.5598 | 25.6522 | 23.3310 |
| 25.5402 | 23.1551 | 23.8745 | 24.6152 | 26.7858 | 25.1633 | 25.9436 | 23.6295 | 25.1532 | 25.8255 |
| 24.8052 | 25.2950 | 25.1778 | 23.9902 | 27.3334 | 27.1880 | 23.4745 | 26.9556 | 25.3399 | 23.4048 |
| 25.9539 | 26.8153 | 25.6740 | 25.4458 | 26.0400 | 25.1315 | 24.8225 | 24.9494 | 23.4318 | 25.5053 |
| 26.6723 | 26.8212 | 23.0956 | 25.4981 | 25.2299 | 23.5769 | 23.6096 | 23.1381 | 23.7006 | 25.5068 |
| 23.5114 | 25.6405 | 25.1488 | 23.8717 | 26.9763 | 27.2147 | 26.9526 | 25.1040 | 23.6422 | 25.1285 |
| 25.1300 | 23.8477 | 23.4190 | 23.0191 | 24.9595 | 24.1218 | 23.6338 | 25.2849 | 23.6295 | 26.7652 |
Table 8 auxiliary variable dissolved oxygen (mg/L)
| 0.0562 | 0.0366 | 0.0480 | 0.0492 | 0.0497 | 0.0355 | 0.0298 | 0.0680 | 0.0501 | 1.4971 |
| 0.0307 | 0.9334 | 0.0395 | 0.3574 | 0.0322 | 0.0480 | 1.1828 | 0.4821 | 0.0792 | 0.0507 |
| 0.0692 | 0.0401 | 4.8300 | 0.0371 | 0.0606 | 0.0518 | 0.0811 | 0.0602 | 0.0542 | 0.0325 |
| 0.0450 | 0.3821 | 0.8550 | 0.0382 | 0.0559 | 0.3764 | 5.7695 | 1.5715 | 1.0503 | 0.0367 |
| 0.1061 | 0.0507 | 0.0311 | 0.2692 | 0.4867 | 0.0310 | 0.0581 | 0.0504 | 0.0509 | 0.0501 |
| 0.0457 | 0.3747 | 0.0375 | 0.2519 | 0.4357 | 0.0396 | 0.2746 | 0.0319 | 0.0336 | 3.3770 |
| 0.0644 | 0.4701 | 5.4844 | 0.0391 | 0.0305 | 0.5861 | 0.2103 | 0.0344 | 0.5381 | 0.3484 |
| 0.0391 | 2.2688 | 0.0882 | 0.2611 | 0.0321 | 0.0716 | 0.0659 | 0.0359 | 0.0427 | 0.0656 |
| 0.0531 | 0.3268 | 0.0311 | 0.0296 | 5.3460 | 0.1882 | 0.0288 | 0.0394 | 0.0860 | 0.1166 |
| 0.0336 | 0.0735 | 0.3412 | 0.0423 | 0.0567 | 0.1819 | 0.0303 | 0.0308 | 0.0654 | 0.0301 |
| 0.5169 | 0.4193 | 0.0911 | 0.8742 | 0.1841 | 0.4882 | 0.0972 | 0.1170 | 0.0318 | 0.0765 |
| 0.3444 | 0.0666 | 0.0340 | 0.0582 | 0.0585 | 0.0609 | 0.0339 | 0.0683 | 0.9117 | 5.2513 |
| 0.0416 | 0.0291 | 0.0689 | 0.2962 | 0.0333 | 0.0450 | 0.2693 | 0.2476 | 0.0603 | 0.3696 |
| 0.0374 | 0.3343 | 0.5440 | 0.4043 | 0.0587 | 0.0342 | 0.0633 | 0.2651 | 0.0380 | 0.0793 |
| 0.0307 | 0.0460 | 0.0352 | 0.8274 | 0.0383 | 0.0382 | 0.3765 | 0.0484 | 0.0438 | 0.9111 |
| 0.0425 | 0.0411 | 0.0398 | 2.0565 | 0.0398 | 0.0739 | 0.0663 | 0.0301 | 0.3594 | 0.4145 |
| 0.1327 | 0.0987 | 0.2734 | 1.1829 | 0.0315 | 0.4537 | 0.2459 | 0.3024 | 0.5110 | 1.2652 |
| 0.3495 | 0.0317 | 0.0395 | 0.4844 | 0.0470 | 0.0514 | 0.0417 | 0.0336 | 1.2551 | 0.0351 |
| 0.0843 | 0.2665 | 0.7375 | 0.7197 | 0.0962 | 0.7756 | 0.2465 | 0.1265 | 0.8817 | 0.0793 |
TABLE 9 auxiliary variable total solids suspension (mg/L)
TABLE 10 auxiliary variable pH
TABLE 11 oxidation-reduction potential of auxiliary variables
Table 12 shows the NH4-N concentration (mg/L) of water
The beneficial effects of the invention are as follows:
according to the invention, condition number analysis and a differential evolution algorithm are combined to optimize the ESN network structure, so that the problem of pathological solution is avoided, the robustness of the network is improved, and the anti-interference performance of the network is improved.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (2)
1. The water outlet NH4-N soft measurement method based on the neural network is characterized by comprising the following steps of:
constructing an echo state network, and initializing a network structure and network parameters of the echo state network; the input variables of the echo state network comprise water inlet temperature, total solid suspended matters, dissolved oxygen concentration, pH value and water outlet oxidation-reduction potential; the output variables of the echo state network comprise ammonia nitrogen concentration;
constructing a sub-reserve pool according to a singular value decomposition method based on the initialized echo state network;
optimizing the sub-pool according to condition numbers and a differential evolution algorithm;
updating the optimized weight, input weight and state matrix of the sub-reserve pool, judging whether the iteration times are smaller than a preset iteration threshold, if so, jumping to the step of constructing the sub-reserve pool according to a singular value decomposition method based on the initialized echo state network; if yes, calculating an output weight;
testing the echo state network according to the output weight and the sample to be tested to obtain a determined effluent NH4-N detection model;
inputting data to be detected into a determined effluent NH4-N detection model to obtain a detection result;
initializing the network structure and network parameters of the echo state network, including:
determining the initial structure of the echo state network to be 5-N-1; wherein N represents the number of sub-pool nodes; the size of N is gradually increased;
using a sigmoid function as a network activation function G (·), determining an initial iteration number i=1 and a maximum iteration number i max Training samples less than or equal to 30Wherein u is k Represents the k-th set of input samples, t k Represents the k-th set of actual output values, +.>Representing the dimension of the input samples as n, and L as the total number of samples;
randomly initializing network input weight W in And the weight W inside the reservoir is between (0, 1);
the method for constructing the sub-reserve pool based on the initialized echo state network according to the singular value decomposition method comprises the following steps:
randomly generating a diagonal matrixTwo orthogonal matrices U i And V i The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>For randomly generated values between (0, 1), n k The number of nodes of the sub reserve pool;
constructing sub-reserves Chi W using the diagonal matrix and two of the orthogonal matrices i ＝U i S i V i ；
The optimizing the sub-pool according to condition numbers and differential evolution algorithms comprises:
construction of fitness function fitness (ΔW i )＝κ(H i )-κ(H i-1 ) The method comprises the steps of carrying out a first treatment on the surface of the Wherein, kappa (H) i ) Representing the condition number of the state matrix corresponding to the pool after the new sub-pool is added;
initializing an initial population np=50, mutation operatorF=0.7, crossover operator cr=0.5, and initializing populationWherein n is {1,2 …, NP }, and a maximum iteration number G is set;
according to the formulaObtaining variant individual mu n The method comprises the steps of carrying out a first treatment on the surface of the Wherein r is 1 ,r 2 ,r 3 ∈[1,NP]Are three mutually different integers;
by passing throughFinishing the crossover operation for each individual +.>Obtaining crossed individualsWherein j e {1,2 …,10}, rand e (0, 1) is randomly generated;
and after the algorithm reaches the maximum iteration times, terminating the algorithm flow, returning to the optimal individual, and constructing a new sub-storage pool by using the optimal individual.
2. The neural network-based effluent NH4-N soft measurement method of claim 1, wherein the method updates the optimized weights, input weights, and state matrices of the sub-reservoirs, and determines whether the iteration number is less than a preset iteration threshold, and if so, jumps to the step of constructing a sub-reservoir according to a singular value decomposition method based on the initialized echo state network; if yes, calculating an output weight, including:
updating the weight of the reserve pool to be
Updating the input weight to
Updating the state matrix to h= [ H ] 1 ,...,H i ]；
If i is more than or equal to i max Executing the next step, otherwise returning to the step of constructing a sub-reserve pool according to a singular value decomposition method based on the initialized echo state network;
by the formula W out ＝H Γ T calculates the output weight W out The method comprises the steps of carrying out a first treatment on the surface of the Wherein Γ represents pseudo-inverse computation, and T is target output data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310181946.1A CN116151121B (en) | 2023-02-21 | 2023-02-21 | Neural network-based effluent NH4-N soft measurement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310181946.1A CN116151121B (en) | 2023-02-21 | 2023-02-21 | Neural network-based effluent NH4-N soft measurement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116151121A CN116151121A (en) | 2023-05-23 |
| CN116151121B true CN116151121B (en) | 2024-03-26 |
Family
ID=86356179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310181946.1A Active CN116151121B (en) | 2023-02-21 | 2023-02-21 | Neural network-based effluent NH4-N soft measurement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116151121B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104104629A (en) * | 2014-05-27 | 2014-10-15 | 温州大学 | Rapid signal detection method based on echo state network |
| CN110837886A (en) * | 2019-10-28 | 2020-02-25 | 北京工业大学 | Effluent NH4-N soft measurement method based on ELM-SL0 neural network |
| CN115660165A (en) * | 2022-10-23 | 2023-01-31 | 北京工业大学 | Modular neural network effluent ammonia nitrogen concentration multi-step prediction method based on double-layer PSO |
-
2023
- 2023-02-21 CN CN202310181946.1A patent/CN116151121B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104104629A (en) * | 2014-05-27 | 2014-10-15 | 温州大学 | Rapid signal detection method based on echo state network |
| CN110837886A (en) * | 2019-10-28 | 2020-02-25 | 北京工业大学 | Effluent NH4-N soft measurement method based on ELM-SL0 neural network |
| CN115660165A (en) * | 2022-10-23 | 2023-01-31 | 北京工业大学 | Modular neural network effluent ammonia nitrogen concentration multi-step prediction method based on double-layer PSO |
Non-Patent Citations (3)
| Title |
|---|
| An ammonia nitrogen concentration online soft measure method based on the neural network;Ge Zhao 等;《Proceedings of the 36th Chinese Control Conference》;3994-3999 * |
| 回声状态网络优化设计及应用研究;王磊;《中国博士学位论文全文数据库 信息科技辑》(第3期);I140-16 * |
| 改进K-means算法优化RBF神经网络的出水氨氮预测;乔俊飞 等;《控制工程》;第25卷(第3期);375-379 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116151121A (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11346831B2 (en) | Intelligent detection method for biochemical oxygen demand based on a self-organizing recurrent RBF neural network | |
| US10570024B2 (en) | Method for effluent total nitrogen-based on a recurrent self-organizing RBF neural network | |
| CN109408774B (en) | Method for predicting sewage effluent index based on random forest and gradient lifting tree | |
| CN102854296B (en) | Sewage-disposal soft measurement method on basis of integrated neural network | |
| CN108469507B (en) | Effluent BOD soft measurement method based on self-organizing RBF neural network | |
| CN111354423B (en) | Method for predicting ammonia nitrogen concentration of effluent of self-organizing recursive fuzzy neural network based on multivariate time series analysis | |
| CN110824915B (en) | GA-DBN network-based intelligent monitoring method and system for wastewater treatment | |
| CN109657790A (en) | A kind of Recurrent RBF Neural Networks water outlet BOD prediction technique based on PSO | |
| CN112989704A (en) | DE algorithm-based IRFM-CMNN effluent BOD concentration prediction method | |
| CN112765902A (en) | RBF neural network soft measurement modeling method based on TentFWA-GD and application thereof | |
| CN109978024B (en) | Effluent BOD prediction method based on interconnected modular neural network | |
| CN109408896B (en) | Multi-element intelligent real-time monitoring method for anaerobic sewage treatment gas production | |
| CN116151121B (en) | Neural network-based effluent NH4-N soft measurement method | |
| CN113111576B (en) | Mixed coding particle swarm-long-short-term memory neural network-based effluent ammonia nitrogen soft measurement method | |
| CN110705752A (en) | Sewage BOD real-time prediction method based on ANFIS and mechanism model | |
| CN110837886A (en) | Effluent NH4-N soft measurement method based on ELM-SL0 neural network | |
| CN112000004B (en) | Sewage treatment concentration control method utilizing iterative quadratic heuristic programming | |
| CN110991616B (en) | Method for predicting BOD of effluent based on pruning feedforward small-world neural network | |
| CN110909492A (en) | Sewage treatment process soft measurement method based on extreme gradient lifting algorithm | |
| CN115905821A (en) | Urban sewage treatment process state monitoring method based on multi-stage dynamic fuzzy width learning | |
| CN111832873B (en) | Pipe diameter determining method and system for water supply pipeline in old urban area | |
| CN111177971B (en) | Sludge volume index distributed soft measurement method | |
| CN111815151A (en) | Sewage treatment plant methane yield prediction method based on data mining | |
| CN113222324A (en) | Sewage quality monitoring method based on PLS-PSO-RBF neural network model | |
| CN113221436B (en) | Sewage suspended matter concentration soft measurement method based on improved RBF neural network |
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 |