CN115759437B - BP neural network sewage index prediction method based on HGS - Google Patents
BP neural network sewage index prediction method based on HGS Download PDFInfo
- Publication number
- CN115759437B CN115759437B CN202211482168.1A CN202211482168A CN115759437B CN 115759437 B CN115759437 B CN 115759437B CN 202211482168 A CN202211482168 A CN 202211482168A CN 115759437 B CN115759437 B CN 115759437B
- Authority
- CN
- China
- Prior art keywords
- neural network
- population
- fitness
- individual
- optimal
- 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 67
- 239000010865 sewage Substances 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000013598 vector Substances 0.000 claims abstract description 55
- 238000003062 neural network model Methods 0.000 claims abstract description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 13
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims abstract description 10
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims abstract description 5
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims abstract description 5
- 229910052757 nitrogen Inorganic materials 0.000 claims abstract description 5
- 229910052698 phosphorus Inorganic materials 0.000 claims abstract description 5
- 239000011574 phosphorus Substances 0.000 claims abstract description 5
- 210000002569 neuron Anatomy 0.000 claims description 17
- 235000003642 hunger Nutrition 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 16
- 238000012549 training Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000002860 competitive 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
- 230000000694 effects Effects 0.000 description 1
- 238000004817 gas chromatography Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a BP neural network sewage index prediction method based on HGS, which comprises the following steps: step S1: constructing an initial BP neural network; step S2: optimizing the network structure and network parameters of the initial BP neural network by utilizing an HGS algorithm to obtain a population individual vector with optimal fitness; step S3: and optimizing the BP neural network structure and parameters by using the obtained individual vector with the optimal fitness to obtain an optimal BP neural network model, and predicting the sewage data to be detected by using the optimal BP neural network model to obtain a prediction result. The BP neural network is optimized by utilizing the HGS algorithm, and the proposed BP neural network sewage quality index prediction method based on the HGS has the characteristics of simple structure and stable performance, and compared with the traditional BP neural network, the BP neural network has lower data volume requirement, and can realize high-precision prediction of four water quality indexes of COD, ammonia nitrogen, total phosphorus and total nitrogen in water under the condition of low data volume.
Description
Technical Field
The invention belongs to the field of sewage index big data prediction and analysis, and particularly relates to a BP neural network sewage index prediction method based on HGS.
Background
The water quality index of sewage in and out is strictly required in China, so that the real-time monitoring of the key index of the water quality in the sewage treatment process is important, and the current sewage treatment stations in China still take the traditional water quality detection means such as manual detection equipment and the like as the main index, and lack of good real-time performance. In addition, the traditional method also does not have the capability of long-term prediction of water quality indexes in a future period of time.
Because sewage treatment is a very complex nonlinear system, has the characteristics of large hysteresis, strong coupling and the like, a reliable and effective prediction model is difficult to build through process mechanism analysis, intelligent algorithms such as a neural network, machine learning and the like do not depend on a mechanism model, and can be actively learned through existing data, and the nonlinear approximation capability is strong, so that the method can be applied to modeling prediction research of a sewage treatment system.
The Back-propagation neural network (BPNN) has been widely used in various fields as one of the most commonly used machine learning algorithms at present. In the field of sewage index prediction, the BP neural network utilizes a large amount of data to establish a mapping relation between input and output in a training mode, so that multi-index real-time prediction can be effectively realized. However, the conventional BP neural network is easy to fall into the problem of local optimal solution in the training process, so that the network performance after training is not ideal, and particularly when the training data volume is insufficient and index prediction is too much, the error of the BP neural network is larger.
The hunger game search (Hunger Games Search, HGS) is a novel intelligent optimization algorithm which is designed according to animal hunger driving activities and behaviors, has the characteristics of simple structure, strong optimizing capability, high convergence speed and the like, has special stability characteristics, has very competitive performance, and can more effectively solve the problems of constraint and unconstrained.
Disclosure of Invention
Therefore, the invention aims to provide the BP neural network sewage index prediction method based on the HGS, the BP neural network structure and parameters are optimized through a hunger game search algorithm (HGS), the HGS-BPNN algorithm is established, the characteristics of easy convergence, high convergence precision and strong capability of escaping from a local optimal solution are utilized by the HGS algorithm, and a better global optimal solution is found to obtain the BP neural network model with better prediction capability, so that the successful prediction of the water quality index under the condition of low data volume can be realized.
In order to achieve the above purpose, the technical scheme of the invention is realized as follows: a BP neural network sewage index prediction method based on HGS comprises the following steps:
step S1: constructing an initial BP neural network;
step S2: optimizing the network structure and network parameters of the initial BP neural network by utilizing an HGS algorithm to obtain a population individual vector with optimal fitness;
step S3: and optimizing the BP neural network structure and parameters by using the obtained individual vector with the optimal fitness to obtain an optimal BP neural network model, and predicting the sewage data to be detected by using the optimal BP neural network model to obtain a prediction result.
Further, in order to meet the requirement of predicting the main sewage index of the sewage treatment station, in the step S1, the initial neural network is set to be of a 3-layer structure, wherein the number m of neurons of an input layer, the number n of neurons of an output layer and the number S of neurons of a hidden layer are determined by a formula (1);
wherein the function floor () represents a rounding down.
Further, the step S2 specifically includes:
step S2.1, initializing population individuals and parameters; wherein the initializing population individuals comprises initializing population individual number N and population individual vectorThe initialization parameters include: number of data samples K, maximum iteration number Max iter Total hungry, initial hungry;
s2.2, calculating the fitness of each population of individuals by using a fitness function; the fitness function RMSD is the deviation between the output of the neural network optimized by the corresponding population individual vector and the actual data:
wherein k=1, 2, … …, K, T Pred (k) For the output value of the neural network, Y Ture (k) Is the actual data value;
s2.3, sequencing the fitness of the population individuals obtained through calculation from small to large, wherein the individual fitness with the optimal fitness is bF, and the worst individual fitness is wF; if bF is better than the global optimal fitness value BF, updating BF to bF, and storing the individual vector as the individual optimal vector; if the wF is worse than the global worst fitness value WF, updating WF to wF; then, calculating hungry (i) of the population individuals according to formulas (3) to (5);
where i=1, 2, … …, N, allfiltness (i) represents fitness value of each individual, r and r 6 Is [0,1]Random numbers in between, UB and LB represent the upper and lower limits of the search space, respectively; LH is the lower bound for H;
step S2.4, calculating the hunger degree weight of the population individuals according to the formula (6) and the formula (7)
Wherein, SHungry represents the sum of hunger of all individuals, r 3 、r 4 、r 5 Is [0,1]Random numbers in between; l is a set constant;
step S2.5, calculating a new position of each individual according to formulas (8) - (10), and updating individual vectors;
E＝sech(|AllFitness(i)-BF|) (9)
wherein,representing the current individual vector, randn representing the random number satisfying the normal distribution of the standard, t being the current iteration number, +.>Representing a globally optimal individual vector, ">Is between [ -a, a]Is a hyperbolic function, r 1 、r 2 and rand are both [0,1]Random numbers in between;
step S2.6, judging whether the iteration times reach the maximum iteration times, if so, ending the iteration, and calculating the fitness of the updated individual vector to obtain the individual vector with the optimal fitness; otherwise, returning to the step S2.2 to repeat the iterative computation.
Furthermore, the individual vectors of the population must contain all information to be optimized, and the data to be optimized are mainly divided into two types for the invention, one type is a network structure; the other is the optimal initial weight under the specified network structure, so the initializing the population individual vector in step S2.1 includes: defining individual vectors of a populationRandomly generating N population individual vectors; defining individual vectors of the population as a p-dimensional vector, wherein the first dimension represents the number of hidden layers of the neural network; the second dimension to the fourth dimension represent the number s E [1,13] of the neurons of each hidden layer of the neural network]The method comprises the steps of carrying out a first treatment on the surface of the The fourth dimension later represents weights and biases between layers.
Further, in the step S2.2, the fitness function is a multiple-input single-output function, and the function value is the fitness of each individual to the environment. The input of the fitness function of the HGS algorithm is the individual vector and basic parameters of BP neural network training, such as learning rate and maximum iteration times; the main body of the fitness function is a BP neural network defined by a network structure and initial parameters which are analyzed by individual vectors and basic parameters of the BP neural network; the output is the deviation RMSD of the output of the BP neural network from the actual data, optimized by the individual vector.
Furthermore, in order to realize real-time processing of data, the invention also uses a timer, and the timer scans the number of files of a data source folder (a folder for storing data collected by a lower computer) at intervals. If the number of files is increased, the fact that the lower computer sensor collects new data is indicated, and then the new collected data is input into the trained neural network model for prediction. And finally, storing the predicted result in a local designated folder according to a naming rule.
Compared with the prior art, the BP neural network sewage index prediction method based on HGS has the following advantages:
(1) According to the sewage index prediction method, the HGS (hybrid gas chromatography system) is added on the basis of the BP neural network, so that the self-adaptive optimization setting of a large number of parameters such as a hidden layer in the BP neural network algorithm is realized, the algorithm operation efficiency is improved, the global optimal solution can be found, the BP neural network model with better prediction capability is obtained, and the prediction precision is improved.
(2) Compared with the traditional BPNN method, the HGS-BPNN sewage index prediction method provided by the invention has the advantages that the required training data amount is less, the sewage index prediction under the condition of low data amount is realized, in addition, the output of a plurality of sewage prediction indexes is realized under the condition of ensuring the precision, the reduction of manual intervention in the sewage treatment process is facilitated, the running cost of a sewage treatment station is reduced, and the intelligent degree of the sewage treatment station is improved.
(3) The prediction method can realize automatic scanning and judging of the newly acquired data by setting the timer, and inputs the newly acquired data into the neural network model for prediction and storage, thereby realizing real-time data processing and automatic sewage water quality index prediction.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute an undue limitation on the invention.
FIG. 1 is a technical roadmap of a BP neural network sewage index prediction method based on HGS according to the embodiment of the invention;
FIG. 2 is a flowchart of a BP neural network sewage index prediction method based on HGS according to the embodiment of the present invention;
FIG. 3 is a graph showing convergence of two optimization algorithms, HGS-BPNN and PSO-BPNN;
FIG. 4 is a graph of the predicted results of two optimization algorithms, HGS-BPNN and PSO-BPNN; wherein, the HGS-BPNN prediction results of FIG. 4 (a) -FIG. 4 (d), and the PSO-BPNN prediction results of FIG. 4 (e) -FIG. 4 (h).
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
The data used by the invention is derived from the measured data of the sewage treatment station, and the four water quality indexes of COD, ammonia nitrogen, total phosphorus and total nitrogen are predicted by six water quality indexes of PH value, turbidity, conductivity, ORP, UV254 and UV280, so that the multi-target prediction of 6 input and 4 output is realized. As shown in fig. 1-2, the BP neural network sewage index prediction method based on HGS established by the invention mainly comprises an HGS algorithm and a BPNN algorithm, wherein the HGS algorithm is used for searching the optimal network structure and network parameters of the BP neural network, the BPNN algorithm is used for training the network structure and the network parameters obtained by the HGS algorithm, so as to obtain an optimized neural network model, and finally, the trained model is used for predicting new data and storing the prediction result. The method specifically comprises the following steps:
step S1: constructing an initial BP neural network;
in order to meet the requirement of predicting main indexes of sewage in a sewage treatment station, the embodiment of the invention sets an initial BP neural network to be of a 3-layer structure, the number m of neurons of an input layer of the neural network is 6, the number n of neurons of an output layer of the neural network is 4, and the two neurons do not participate in HGS optimization; the number of hidden layers (to-be-optimized amount) of the neural network is 1, and the number s of neurons of the hidden layers is determined by a formula (1);
wherein the function floor () represents a rounding down. Here, a=5 is taken, and the number of hidden layer neurons is 8.
Step S2: optimizing the network structure and network parameters of the initial BP neural network by utilizing an HGS algorithm to obtain a population individual vector with optimal fitness;
step S3: and optimizing the BP neural network structure and parameters by using the obtained individual vector with the optimal fitness to obtain an optimal BP neural network model, and predicting the sewage data to be detected by using the optimal BP neural network model to obtain a prediction result.
Further, the step S2 specifically includes:
step S2.1, initializing population individuals and parameters; wherein the initializing population individuals comprises initializing population individual number N and population individual vectorThe initialization parameters include: number of data samples K, maximum iteration number Max iter Total hungry, initial hungry;
the population individual vectors must contain all information to be optimized, and the data to be optimized are mainly divided into two types, wherein one type is a network structure; another type is the optimal initial weight under the specified network structure, thus defining population individual vectorsThe first dimension is a p-dimensional vector, and the first dimension represents the number of hidden layers of the neural network; the second dimension to the fourth dimension represent the number s E [1,13] of the neurons of each hidden layer of the neural network]The method comprises the steps of carrying out a first treatment on the surface of the The fourth dimension later represents the weight and bias between each layer and randomly generates N population individual vectors;
s2.2, calculating the fitness of each population of individuals by using a fitness function; the fitness function of the HGS algorithm is a multi-input single-output function, and the input is an individual vector and basic parameters of BP neural network training, such as learning rate and maximum iteration times; the function body is a BP neural network defined by a network structure and initial parameters which are analyzed by individual vectors and basic parameters of the BP neural network; the output is the deviation RMSD of the output of the BP neural network optimized by the individual vector from the actual data:
wherein k=1, 2, … …, K, Y Pred (k) As a neural networkOutput value, Y Ture (k) Is the actual data value;
s2.3, sequencing the fitness of the population individuals obtained through calculation from small to large, wherein the individual fitness with the optimal fitness is bF, and the worst individual fitness is wF; if bF is better than the global optimal fitness value BF, updating BF to bF, and storing the individual vector as the individual optimal vector; if the wF is worse than the global worst fitness value WF, updating WF to wF; then, calculating hungry (i) of the population individuals according to formulas (3) to (5);
where i=1, 2, … …, N, allfiltness (i) represents fitness value of each individual, r and r 6 Is [0,1]Random numbers in between, UB and LB represent the upper and lower limits of the search space, respectively; LH is the lower bound for H;
step S2.4, calculating the hunger degree weight of the population individuals according to the formula (6) and the formula (7)
Wherein, SHungry represents the sum of hunger of all individuals, r 3 、r 4 、r 5 In the case of the value of [0 ],1]random numbers in between; l is a set constant;
step S2.5, updating individual vectors according to formulas (8) - (10);
E＝sech(|AllFitness(i)-BF|) (9)
wherein,representing the current individual vector, randn representing the random number satisfying the normal distribution of the standard, t being the current iteration number, +.>Representing a globally optimal individual vector, ">Is between [ -a, a]Is a hyperbolic function,a＝2*(1-t/Max iter )，r 1 、r 2 and rand are both [0,1]Random numbers in between;
step S2.6, judging whether the iteration times reach the maximum iteration times, if so, ending the iteration, and calculating the fitness of the updated individual vector to obtain the individual vector with the optimal fitness; otherwise, returning to the step S2.2 to repeat the iterative computation.
In order to realize real-time processing of data, the invention also uses a timer, and the timer can scan the number of files of a data source folder (a folder for storing collected data of a lower computer) at intervals. If the number of files is increased, the fact that the lower computer sensor collects new data is indicated, and then the new collected data is input into the trained neural network model for prediction. And finally, storing the predicted result in a local designated folder according to a naming rule.
Fig. 3 shows performance analysis of the HGS optimization algorithm, and by comparing convergence curves of the PSO optimization algorithm and the HGS algorithm, it can be seen that the HGS optimization speed is fast, and an output result of the fitness function obtained by optimization is better than a result obtained by the PSO algorithm.
4 (a) - (d) are HGS-BP neural network prediction results; FIGS. 4 (e) - (h) are PSO-BP neural network predictions. As can be seen by comparing fig. 4 (a) and 4 (e), both can well predict the trend of the COD content in the sewage, but the prediction result of the HGS-BPNN algorithm is closer to the actual COD content in the sewage; comparing FIG. 4 (b) with FIG. 4 (f), it can be seen that the predicted ammonia nitrogen result is closest to the real result at each sample point in the present invention; FIG. 4 (c) is a comparison with FIG. 4 (g) to show that although the HGS-BPNN method has lower overall phosphorus content than the PSO-BPNN method in predicting accuracy at sample point 6, the overall accuracy is better than the PSO-BPNN method; as can be seen from the comparison of FIG. 4 (d) and FIG. 4 (h), HGS-BPNN can better predict the variation trend of the total nitrogen content in sewage, and the prediction accuracy is higher than that of the PSO-BPNN method.
According to the embodiment of the invention, the BP neural network is optimized by utilizing the HGS algorithm, and compared with the traditional BP neural network, the BP neural network sewage quality index prediction method based on the HGS has lower data volume requirement, and can realize high-precision prediction of four quality indexes of COD, ammonia nitrogen, total phosphorus and total nitrogen in water under the condition of low data volume.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in implementing the methods of the above embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc.
The above disclosure is only a preferred embodiment of the present invention, and it is needless to say that the scope of the invention is not limited thereto, and therefore, the equivalent changes according to the claims of the present invention still fall within the scope of the present invention.
Claims (7)
1. The BP neural network sewage index prediction method based on HGS is characterized in that: the method comprises the following steps:
step S1: constructing an initial BP neural network;
step S2: optimizing the network structure and network parameters of the initial BP neural network by utilizing an HGS algorithm to obtain a population individual vector with optimal fitness;
step S3: optimizing the BP neural network structure and network parameters by using the population individual vector with the optimal fitness to obtain an optimal BP neural network model, and predicting the sewage data to be detected by using the optimal BP neural network model to obtain a prediction result;
step S2.1, initializing population individuals and parameters; wherein the initializing population individuals comprises initializing population individual number N and population individual vectorThe initialization parameters include: number of data samples K, maximum iteration number Max iter Total hungry, initial hungry;
step S2.2, calculating the fitness of each population of individuals by using a fitness function RMSD;
s2.3, sequencing the fitness of the population individuals obtained through calculation from small to large, wherein the individual fitness with the optimal fitness is bF, and the worst individual fitness is wF; if bF is better than the global optimal fitness value BF, updating BF to bF, and storing the individual vector as the individual optimal vector; if the wF is worse than the global worst fitness value WF, updating WF to wF; then, calculating hungry (i) of the population individuals according to a formula;
where i=1, 2, … …, N, allfiltness (i) represents fitness value of each individual, r and r 6 Is [0,1]Random numbers in between, UB and LB represent the upper and lower limits of the search space, respectively; LH is the lower bound for H;
s2.4, calculating hunger degree weight of population individualsAnd->
Wherein, SHungry represents the sum of hunger of all individuals, r 3 、r 4 、r 5 Is [0,1]Random numbers in between; l is a set constant;
step S2.5, updating individual vectors according to the hunger weights of the population individuals;
E＝sech(|AllFitness(i)-BF|) (9)
wherein,representing the current individual vector, randn representing the random number satisfying the normal distribution of the standard, t being the current iteration number, +.>Representing a globally optimal individual vector, ">Is between [ -a, a]Is a hyperbolic function,a＝2*(1-t/Max iter )，r 1 、r 2 and rand are both [0,1]Random numbers in between;
s2.6, judging whether the iteration times reach the maximum iteration times, if so, ending the iteration, and calculating the fitness of the updated individual vectors to obtain the population individual vectors with optimal fitness; otherwise, returning to the step S2.2 to repeat the iterative computation.
2. The method according to claim 1, wherein the initial BP neural network is set to a 3-layer structure in the step S1, wherein the number of neurons in the input layer m, the number of neurons in the output layer n, and the number of neurons in the hidden layer S are determined by the formula (1);
wherein the function floor () represents a rounding down.
3. The method of claim 2 wherein the initial BP neural network has an input layer neuron number m of 6, an output layer neuron number n of 4, a q value of 5, and a hidden layer neuron number s of 8.
4. The method according to claim 1, wherein initializing the population individual vectors in step S2.1 comprises: defining individual vectors of a populationRandomly generating N population individual vectors;
defining individual vectors of the population as a p-dimensional vector, wherein the first dimension represents the number of hidden layers of the neural network; the second dimension to the fourth dimension represent the number s epsilon [1,13] of neurons of each hidden layer of the neural network; the fourth dimension later represents weights and biases between layers.
5. The method according to claim 1, wherein in the step S2.2, the fitness function RMSD is the deviation of the output of the neural network optimized by the corresponding population individual vector from the actual data:
wherein k=1, 2, … …, K, Y Pred (k) For the output value of the neural network, Y Ture (k) Is the actual data value.
6. The method of claim 1, further comprising a timer for scanning and obtaining the number of files in the data source folder at intervals; if the number of files is increased, new data are acquired, and the new acquired data are input into the BP neural network after optimization for prediction.
7. The method according to claim 1, wherein predicting the sewage data to be measured in step S3 includes: according to six water quality indexes of PH value, turbidity, conductivity, ORP, UV254 and UV280, four water quality indexes of COD, ammonia nitrogen, total phosphorus and total nitrogen are predicted, and multi-target prediction of 6 input and 4 output is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211482168.1A CN115759437B (en) | 2022-11-24 | 2022-11-24 | BP neural network sewage index prediction method based on HGS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211482168.1A CN115759437B (en) | 2022-11-24 | 2022-11-24 | BP neural network sewage index prediction method based on HGS |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115759437A CN115759437A (en) | 2023-03-07 |
| CN115759437B true CN115759437B (en) | 2024-03-01 |
Family
ID=85337621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211482168.1A Active CN115759437B (en) | 2022-11-24 | 2022-11-24 | BP neural network sewage index prediction method based on HGS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115759437B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743011A (en) * | 2021-08-31 | 2021-12-03 | 华中科技大学 | Device life prediction method and system based on PSO-BP neural network |
| CN114037163A (en) * | 2021-11-10 | 2022-02-11 | 南京工业大学 | Sewage treatment effluent quality early warning method based on dynamic weight PSO (particle swarm optimization) optimization BP (Back propagation) neural network |
| CN115271167A (en) * | 2022-06-23 | 2022-11-01 | 合肥工业大学 | BP neural network-based tire vulcanization quality RFV index prediction method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112183719B (en) * | 2020-09-15 | 2024-02-02 | 北京工业大学 | Intelligent detection method for total nitrogen in effluent based on multi-objective optimization-fuzzy neural network |
-
2022
- 2022-11-24 CN CN202211482168.1A patent/CN115759437B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743011A (en) * | 2021-08-31 | 2021-12-03 | 华中科技大学 | Device life prediction method and system based on PSO-BP neural network |
| CN114037163A (en) * | 2021-11-10 | 2022-02-11 | 南京工业大学 | Sewage treatment effluent quality early warning method based on dynamic weight PSO (particle swarm optimization) optimization BP (Back propagation) neural network |
| CN115271167A (en) * | 2022-06-23 | 2022-11-01 | 合肥工业大学 | BP neural network-based tire vulcanization quality RFV index prediction method and system |
Non-Patent Citations (2)
| Title |
|---|
| Hunger games search: Visions, conception, implementation, deep analysis, perspectives, and towards performance shifts;Yang Yutao等;Expert Systems With Applications;第177卷;全文 * |
| 基于PSO优化的灰色神经网络预测算法的研究;江敏;钱磊;苏学满;;宁夏师范学院学报(03);第54-60页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115759437A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112487702B (en) | Method for predicting residual service life of lithium ion battery | |
| CN110110862A (en) | A kind of hyperparameter optimization method based on adaptability model | |
| CN113268611B (en) | Learning path optimization method based on deep knowledge tracking and reinforcement learning | |
| CN110032755B (en) | Multi-objective optimization method for urban sewage treatment process under multiple working conditions | |
| CN116542382A (en) | Sewage treatment dissolved oxygen concentration prediction method based on mixed optimization algorithm | |
| CN114547974A (en) | Dynamic soft measurement modeling method based on input variable selection and LSTM neural network | |
| CN113611356B (en) | Drug relocation prediction method based on self-supervision graph representation learning | |
| CN113722980A (en) | Ocean wave height prediction method, system, computer equipment, storage medium and terminal | |
| CN112765902A (en) | RBF neural network soft measurement modeling method based on TentFWA-GD and application thereof | |
| CN116579371A (en) | Double-layer optimization heterogeneous proxy model assisted multi-objective evolutionary optimization computing method | |
| Chen et al. | LOGER: A learned optimizer towards generating efficient and robust query execution plans | |
| CN115510322A (en) | Multi-objective optimization recommendation method based on deep learning | |
| CN114596726B (en) | Parking berth prediction method based on interpretable space-time attention mechanism | |
| CN102521654A (en) | Supercritical water oxidation reaction kinetic model parameter estimation method employing RNA (Ribonucleic Acid) genetic algorithm | |
| CN115759437B (en) | BP neural network sewage index prediction method based on HGS | |
| CN117034762A (en) | Composite model lithium battery life prediction method based on multi-algorithm weighted sum | |
| CN108829846A (en) | A kind of business recommended platform data cluster optimization system and method based on user characteristics | |
| CN116956160A (en) | Data classification prediction method based on self-adaptive tree species algorithm | |
| CN111310974A (en) | Short-term water demand prediction method based on GA-ELM | |
| CN115619028A (en) | Clustering algorithm fusion-based power load accurate prediction method | |
| CN114357869A (en) | Multi-objective optimization agent model design method and system based on data relation learning and prediction | |
| CN111079995A (en) | Power load nonlinear harmonic comprehensive prediction method, device and storage medium | |
| Furze et al. | Mathematical methods to quantify and characterise the primary elements of trophic systems | |
| CN117912573B (en) | Deep learning-based multi-level biomolecular network construction method | |
| Yu | Hybrid soft computing approach for mining of complex construction databases |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: No.29 Zhujiang Road, Hexi District, Tianjin Applicant after: Tianjin Water Conservancy Engineering Group Co.,Ltd. Address before: No.29 Zhujiang Road, Hexi District, Tianjin Applicant before: TIANJIN MUNICIPAL WATER LIMITED CONSERVANCY |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |