CN113297788B - Water quality soft measurement method and system based on improved neural network - Google Patents
Water quality soft measurement method and system based on improved neural network Download PDFInfo
- Publication number
- CN113297788B CN113297788B CN202110516880.8A CN202110516880A CN113297788B CN 113297788 B CN113297788 B CN 113297788B CN 202110516880 A CN202110516880 A CN 202110516880A CN 113297788 B CN113297788 B CN 113297788B
- Authority
- CN
- China
- Prior art keywords
- neural network
- water quality
- network model
- population
- bat individual
- 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
Images
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
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Automatic Analysis And Handling Materials Therefor (AREA)
Abstract
The invention relates to the technical field of water quality soft measurement, in particular to a water quality soft measurement method and system based on an improved neural network, wherein the method comprises the following steps: firstly, collecting water quality data, determining input variable values and corresponding output variable values of a neural network model, and determining optimized design parameters of the neural network model by using an adaptive bat algorithm; constructing a neural network model through the optimized design parameters to obtain a water quality soft measurement neural network model; the invention can improve the precision of the water quality soft measurement by using the obtained water quality soft measurement neural network model to carry out the water quality soft measurement.
Description
Technical Field
The invention relates to the technical field of water quality soft measurement, in particular to a water quality soft measurement method and system based on an improved neural network.
Background
With the continuous advance of industrialization process in China, many places actively make up industrial parks, and various industrial enterprises are vigorously introduced. With the convergence of various industrial enterprises, the discharge of industrial sewage also affects the water quality of the peripheral areas of industrial parks to a great extent. The biochemical oxygen demand of five days is an important index for measuring the water quality. However, the traditional method for measuring the five-day biochemical oxygen demand has the defects of long time consumption and high cost. Therefore, researchers have proposed a method based on machine learning to determine five-day biochemical oxygen demand [ Schering, Zhao Donghui, Korea & Fei ] research on SVR water quality prediction model based on GA optimization [ J ] environmental engineering, 2020, 38 (3): 123-. The five-day biochemical oxygen demand soft measurement method based on machine learning indirectly measures the value of the five-day biochemical oxygen demand by establishing a mathematical model of the five-day biochemical oxygen demand and other water quality indexes which are easy to directly measure, inputting the acquired relevant water quality indexes into the established mathematical model and calculating the output value of the mathematical model.
The neural network is a common machine learning method, and obtains a satisfactory result in many applications of water quality soft measurement [ Longhua, Zhao, Junxiadong, Duqing, huting, Shaoyyubin ] application of an improved QGA-BP model in total nitrogen prediction of Juque river [ J ] environmental engineering report, 2016,10(11): 6099-.
Disclosure of Invention
The invention aims to provide a method and a system for soft measurement of water quality based on an improved neural network, which are used for solving one or more technical problems in the prior art and at least providing a beneficial selection or creation condition.
In order to achieve the above object, the present invention provides the following technical solutions:
a water quality soft measurement method based on an improved neural network comprises the following steps:
s100, obtaining a water quality data sample set, wherein the water quality data sample set comprises input variable values and corresponding output variable values of a neural network model;
s200, determining optimized design parameters of the neural network model by using an adaptive bat algorithm based on the water quality data sample set;
s300, constructing a neural network model through the optimized design parameters to obtain a water quality soft measurement neural network model;
and S400, performing water quality soft measurement by using the obtained water quality soft measurement neural network model.
Further, the step S200 includes:
step S201, determining the structure of a neural network model;
s202, determining the number DN of the optimization design parameters of the neural network model according to the structure of the neural network model;
step S203, setting a population size BSize, a maximum frequency afr, a minimum frequency ifr and a maximum iteration time mst;
step S204, setting the current iteration time t to be 0;
step S205, randomly generating the current positions and the current speeds of BSize bat individuals, and then forming a population by the BSize bat individuals; wherein, the current position of each bat individual stores DN optimized design parameters of the neural network model;
s206, calculating the adaptive values of the current positions of BSize bat individuals in the population according to the water quality data sample set;
step S207, finding out the bat individual with the minimum adaptive value of the current position in the population, and recording as the optimal bat individual MinDA;
step S208, setting the optimized scaling factor AFR ti Rank (0,1), where subscript ti 1, 2., Bsize; rand (0,1) represents [0,1]]A random real number generating function in between;
step S209, calculating a heuristic factor IR according to the formula (1) ti ：
Wherein exp represents an exponential function with a natural constant e as a base; log represents a logarithmic function based on a natural constant e;
step S210, sorting the adaptive values of the current position of each bat individual in the population from small to large, and setting Rank ti The serial number of the adaptive value of the current position of the ti-th bat individual in the population after sorting;
step S211, calculating the constant-level disturbance amplitude DR according to the formula (2) ti ：
Step S212, calculating the current scaling factor CFR according to the formula (3) ti ：
Wherein rdp is a real number randomly generated between [0,1 ];
step S213, calculating the next generation speed and the next generation position of each bat individual in the population according to formula (4):
wherein dfr ti Representing the current frequency of the ti-th bat individual in the population;
representing the current speed of the ti-th bat individual in the population;
representing the current position of the ti-th bat individual in the population;
representing the next generation speed of the ti-th bat individual in the population;
representing the next generation location of the ti-th bat individual in the population;
step S214, calculating the adaptive value of the next generation position of each bat individual in the population;
step S215, if the next generation position of the ti-th bat individual in the population
Is less than the current position
Then the preferred scaling factor AFR is set ti ＝CFR ti Otherwise, the preferred scaling factor AFR is maintained ti The change is not changed;
s216, finding out the bat individual with the minimum adaptive value of the next generation position in the population and recording the bat individual as cmDA; if the adaptive value of the next generation position of the cmDA is less than the adaptive value of the current position of the optimal bat individual MinDA, then go to step S217, otherwise go to step S218;
step S217, setting the current position of the optimal bat individual MinDA equal to the next generation position of the cmDA, and setting the adaptive value of the current position of the optimal bat individual MinDA equal to the adaptive value of the next generation position of the cmDA;
step S218, after adding 1 to the current iteration number, determining whether the current iteration number is smaller than the maximum iteration number mst, if so, turning to step S209, otherwise, turning to step S219;
and S219, extracting DN optimized design parameters of the neural network model from the optimal bat individual MinDA.
Further, the neural network model is a three-layer perceptron with a 5-6-1 structure.
Further, the calculation method of the adaptive value is as follows:
for the ti-th bat individual in the population, DN optimized design parameters of the stored neural network model are extracted from the ti-th bat individual; then, a neural network model WPM of the ti-th bat individual is constructed ti Calculating the neural network model WPM of the ti-th bat individual ti Mean Square Error (MSE) on water quality data sample set ti (ii) a Setting the adaptive value of the current position of the ti-th bat individual in the population as the mean square error MSE ti Wherein subscript ti ═ 1, 2., Bsize.
Further, the DN optimization design parameters of the neural network model include the weight and threshold of the input layer, the weight and threshold of the hidden layer, and the weight and threshold of the output layer.
Further, the water quality data sample set comprises: chemical oxygen demand, suspended matter, pH value, ammonia nitrogen total nitrogen and five-day biochemical oxygen demand; the input variables of the neural network model are oxygen demand, suspended matters, pH value and total ammonia nitrogen; the output variable is five-day biochemical oxygen demand.
A computer readable storage medium, wherein the computer readable storage medium stores a water quality soft measurement program based on an improved neural network, and when the water quality soft measurement program based on the improved neural network is executed by a processor, the steps of the water quality soft measurement method based on the improved neural network are realized.
A water quality soft measurement system based on an improved neural network, the system comprising:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor is enabled to implement any one of the above methods for improved neural network-based water quality soft measurement.
The invention has the beneficial effects that: the invention discloses a method and a system for soft measurement of water quality based on an improved neural network, wherein the method and the system optimally design parameters of the neural network by using an adaptive bat algorithm, overcome the defects that the traditional neural network is easy to fall into local optimization when applied to soft measurement of water quality and the precision of the soft measurement of water quality is insufficient, realize the soft measurement of water quality by using the improved neural network, and can improve the precision of the soft measurement of water quality.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a water quality soft measurement method based on an improved neural network in an embodiment of the invention;
FIG. 2 is a diagram illustrating the variation of the amplitude of the fixed-level disturbance with the adaptation value in the embodiment of the present invention.
Detailed Description
The conception, specific structure and technical effects of the present application will be described clearly and completely with reference to the following embodiments and the accompanying drawings, so that the purpose, scheme and effects of the present application can be fully understood. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Referring to fig. 1, as shown in fig. 1, a method for measuring water quality based on an improved neural network provided by an embodiment of the present application includes the following steps:
s100, acquiring a water quality data sample set, wherein the water quality data sample set comprises input variable values and corresponding output variable values of a neural network model;
s200, determining an optimized design parameter of the neural network model by utilizing an adaptive bat algorithm based on the water quality data sample set;
s300, constructing a neural network model through the optimized design parameters to obtain a water quality soft measurement neural network model;
and S400, performing water quality soft measurement by using the obtained water quality soft measurement neural network model.
In one embodiment, the water quality data sample set comprises: chemical oxygen demand, suspended matter, pH value, ammonia nitrogen total nitrogen and five-day biochemical oxygen demand; the input variables of the neural network model are oxygen demand, suspended matters, pH value and total ammonia nitrogen; the output variable is five-day biochemical oxygen demand; by acquiring water quality input data (chemical oxygen demand, suspended matters, pH value and ammonia nitrogen total nitrogen) collected in real time, the water quality input data is subjected to water quality soft measurement by adopting the water quality soft measurement neural network model, so that real-time output data (five-day biochemical oxygen demand) is obtained.
In a preferred embodiment, the step S200 includes:
step S201, determining the structure of a neural network model; the neural network model is a three-layer perceptron with a 5-6-1 structure;
s202, determining the number DN of the optimization design parameters of the neural network model according to the structure of the neural network model; in this embodiment, DN ═ 43;
step S203, setting a population size BSize, a maximum frequency afr, a minimum frequency ifr and a maximum iteration time mst; in this embodiment, the population size BSize is set to 50, the maximum frequency afr is set to 2.5, the minimum frequency ifr is set to 0.1, and the maximum iteration number mst is set to 2000;
step S204, setting the current iteration time t to be 0;
step S205, randomly generating the current positions and the current speeds of BSize bat individuals, and then forming a population by the BSize bat individuals; wherein, the current position of each bat individual stores DN optimized design parameters of the neural network model; DN optimization design parameters of the neural network model comprise a weight and a threshold of an input layer, a weight and a threshold of a hidden layer and a weight and a threshold of an output layer;
s206, calculating the adaptive values of the current positions of BSize bat individuals in the population according to the water quality data sample set; the calculation method of the adaptive value comprises the following steps: for the ti-th bat individual in the population, DN optimized design parameters of the stored neural network model are extracted from the ti-th bat individual; then, a neural network model WPM of the ti-th bat individual is constructed ti Calculating the neural network model WPM of the ti-th bat individual ti Mean Square Error (MSE) on water quality data sample set ti (ii) a Setting the adaptive value of the current position of the ti-th bat individual in the population as the mean square error MSE ti Wherein, subscript ti ═ 1, 2.
Step S207, finding out the bat individual with the minimum adaptive value of the current position in the population, and recording as an optimal bat individual MinDA;
step S208, setting the optimized scaling factor AFR ti Rank (0,1), where subscript ti 1, 2., Bsize; rand (0,1) represents [0,1]]A random real number generating function in between;
step S209, calculating a heuristic factor IR according to the formula (1) ti ：
Wherein exp represents an exponential function with a natural constant e as a base; log represents a logarithmic function based on a natural constant e;
step (ii) ofS210, sorting the adaptive values of the current position of each bat individual in the population from small to large, and setting Rank ti The serial number of the adaptive value of the current position of the ti-th bat individual in the population after sorting;
step S211, calculating the constant-level disturbance amplitude DR according to the formula (2) ti ：
The level-fixed disturbance amplitude DR ti The first calculated value of (a) is shown in fig. 2;
step S212, calculating the current scaling factor CFR according to the formula (3) ti ：
Wherein rdp is a real number randomly generated between [0,1 ];
step S213, calculating the next generation speed and the next generation position of each bat individual in the population according to formula (4):
wherein dfr ti Representing the current frequency of the ti-th bat individual in the population;
representing the current speed of the ti-th bat individual in the population;
representing the current position of the ti-th bat individual in the population;
representing the next generation speed of the ti-th bat individual in the population;
representing the next generation location of the ti-th bat individual in the population;
s214, calculating an adaptive value of the next generation position of each bat individual in the population;
step S215, if the next generation position of the ti-th bat individual in the population
Is less than the current position
Then the preferred scaling factor AFR is set ti ＝CFR ti Otherwise, the preferred scaling factor AFR is maintained ti Keeping the original shape;
s216, finding out the bat individual with the minimum adaptive value of the next generation position in the population and recording the bat individual as cmDA; if the adaptive value of the next generation position of the cmDA is less than the adaptive value of the current position of the optimal bat individual MinDA, then go to step S217, otherwise go to step S218;
step S217, setting the current position of the optimal bat individual MinDA equal to the next generation position of the cmDA, and setting the adaptive value of the current position of the optimal bat individual MinDA equal to the adaptive value of the next generation position of the cmDA;
step S218, after adding 1 to the current iteration number, determining whether the current iteration number is smaller than the maximum iteration number mst, if so, turning to step S209, otherwise, turning to step S219;
step S219, DN optimized design parameters of the neural network model are extracted from the optimal bat individual MinDA.
In the embodiment provided by the invention, an adaptive mechanism with fusion of heuristic factors and constant-level disturbance amplitude is designed in an adaptive bat algorithm. On one hand, the heuristic factor can ensure that the adaptive bat algorithm has better global search capability in the early search period, and simultaneously ensure that the adaptive bat algorithm has stronger local search capability in the later search period. On the other hand, the adaptive bat algorithm generates different disturbance amplitudes according to the advantages and disadvantages of the adaptive values to adaptively maintain the diversity of the population, thereby reducing the probability of falling into the local optimum and improving the precision of the water quality soft measurement.
Corresponding to the method of fig. 1, an embodiment of the present invention further provides a computer-readable storage medium, where a water quality soft measurement program based on an improved neural network is stored on the computer-readable storage medium, and when the water quality soft measurement program based on the improved neural network is executed by a processor, the steps of the water quality soft measurement method based on the improved neural network according to any one of the above embodiments are implemented.
Corresponding to the method in fig. 1, an embodiment of the present invention further provides a water quality soft measurement system based on an improved neural network, where the system includes:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor is enabled to implement the improved neural network-based water quality soft measurement method of any one of the above embodiments.
The contents in the above method embodiments are all applicable to the present system embodiment, the functions specifically implemented by the present system embodiment are the same as those in the above method embodiment, and the beneficial effects achieved by the present system embodiment are also the same as those achieved by the above method embodiment.
The Processor may be a Central-Processing Unit (CPU), other general-purpose Processor, a Digital Signal Processor (DSP), an Application-Specific-Integrated-Circuit (ASIC), a Field-Programmable Gate array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, or the like. The general processor can be a microprocessor or the processor can be any conventional processor and the like, the processor is a control center of the water quality soft measurement system based on the improved neural network, and various interfaces and lines are utilized to connect various parts of the whole operable device of the water quality soft measurement system based on the improved neural network.
The memory can be used for storing the computer program and/or the module, and the processor realizes various functions of the water quality soft measurement system based on the improved neural network by operating or executing the computer program and/or the module stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart-Media-Card (SMC), a Secure-Digital (SD) Card, a Flash-memory Card (Flash-Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
While the description of the present application has been made in considerable detail and with particular reference to a few illustrated embodiments, it is not intended to be limited to any such details or embodiments or any particular embodiments, but it is to be construed that the present application effectively covers the intended scope of the application by reference to the appended claims, which are interpreted in view of the broad potential of the prior art. Further, the foregoing describes the present application in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial changes from the present application, not presently foreseen, may nonetheless represent equivalents thereto.
Claims (7)
1. A water quality soft measurement method based on an improved neural network is characterized by comprising the following steps:
s100, obtaining a water quality data sample set, wherein the water quality data sample set comprises input variable values and corresponding output variable values of a neural network model;
s200, determining optimized design parameters of the neural network model by using an adaptive bat algorithm based on the water quality data sample set;
s300, constructing a neural network model through the optimized design parameters to obtain a water quality soft measurement neural network model;
s400, performing water quality soft measurement by using the obtained water quality soft measurement neural network model;
wherein the step S200 includes:
step S201, determining the structure of a neural network model;
step S202, determining the number DN of optimization design parameters of the neural network model according to the structure of the neural network model;
step S203, setting a population size BSize, a maximum frequency afr, a minimum frequency ifr and a maximum iteration time mst;
step S204, setting the current iteration time t to be 0;
step S205, randomly generating the current positions and the current speeds of BSize bat individuals, and then forming a population by the BSize bat individuals; wherein, the current position of each bat individual stores DN optimized design parameters of the neural network model;
s206, calculating the adaptive values of the current positions of BSize bat individuals in the population according to the water quality data sample set;
step S207, finding out the bat individual with the minimum adaptive value of the current position in the population, and recording as the optimal bat individual MinDA;
step S208, setting the optimized scaling factor AFR ti Rank (0,1), where subscript ti 1, 2., Bsize; rand (0,1) represents [0,1]]A random real number generating function in between;
step S209, calculating a heuristic factor IR according to the formula (1) ti ：
Wherein exp represents an exponential function with a natural constant e as a base; log represents a logarithmic function based on a natural constant e;
step S210, sorting the adaptive values of the current position of each bat individual in the population from small to large, and setting Rank ti The serial number of the adaptive value of the current position of the ti-th bat individual in the population after sorting;
step S211, calculating the constant-level disturbance amplitude DR according to the formula (2) ti ：
Step S212, calculating the current scaling factor CFR according to the formula (3) ti ：
Wherein rdp is a real number randomly generated between [0,1 ];
step S213, calculating the next generation speed and the next generation position of each bat individual in the population according to formula (4):
wherein dfr ti Representing the current frequency of the ti-th bat individual in the population;
representing the current speed of the ti-th bat individual in the population;
representing the current position of the ti-th bat individual in the population;
represents the next bat individual ti in the populationGeneration speed;
representing the next generation location of the ti-th bat individual in the population;
s214, calculating an adaptive value of the next generation position of each bat individual in the population;
step S215, if the next generation position of the ti-th bat individual in the population
Is less than the current position
Then the preferred scaling factor AFR is set ti ＝CFR ti Otherwise, the preferred scaling factor AFR is maintained ti Keeping the original shape;
s216, finding out the bat individual with the minimum adaptive value of the next generation position in the population and recording the bat individual as cmDA; if the adaptive value of the next generation position of the cmDA is less than the adaptive value of the current position of the optimal bat individual MinDA, then go to step S217, otherwise go to step S218;
step S217, setting the current position of the optimal bat individual MinDA equal to the next generation position of the cmDA, and setting the adaptive value of the current position of the optimal bat individual MinDA equal to the adaptive value of the next generation position of the cmDA;
step S218, after adding 1 to the current iteration number, determining whether the current iteration number is smaller than the maximum iteration number mst, if so, turning to step S209, otherwise, turning to step S219;
and S219, extracting DN optimized design parameters of the neural network model from the optimal bat individual MinDA.
2. The method for soft measurement of water quality based on the improved neural network as claimed in claim 1, wherein the neural network model is a three-layer sensor with a 5-6-1 structure.
3. The method for soft measurement of water quality based on the improved neural network as claimed in claim 2, wherein the adaptive value is calculated by:
for the ti-th bat individual in the population, DN optimized design parameters of the stored neural network model are extracted from the ti-th bat individual; then, a neural network model WPM of the ti-th bat individual is constructed ti Calculating the neural network model WPM of the tth bat individual ti Mean Square Error (MSE) on water quality data sample set ti (ii) a Setting the adaptive value of the current position of the ti-th bat individual in the population as the mean square error MSE ti Wherein, subscript ti ═ 1, 2.
4. The method as claimed in claim 3, wherein the DN optimized design parameters of the neural network model include weight and threshold of the input layer, weight and threshold of the hidden layer, and weight and threshold of the output layer.
5. The method for soft measurement of water quality based on the improved neural network as claimed in claim 1, wherein the water quality data sample set comprises: chemical oxygen demand, suspended matter, pH value, ammonia nitrogen total nitrogen and five-day biochemical oxygen demand; the input variables of the neural network model are oxygen demand, suspended matters, pH value and total ammonia nitrogen; the output variable is five-day biochemical oxygen demand.
6. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, implements the steps of the improved neural network-based water quality soft measurement method according to any one of claims 1 to 5.
7. A water quality soft measurement system based on an improved neural network is characterized by comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the improved neural network-based water quality soft measurement method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110516880.8A CN113297788B (en) | 2021-05-12 | 2021-05-12 | Water quality soft measurement method and system based on improved neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110516880.8A CN113297788B (en) | 2021-05-12 | 2021-05-12 | Water quality soft measurement method and system based on improved neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113297788A CN113297788A (en) | 2021-08-24 |
| CN113297788B true CN113297788B (en) | 2022-08-23 |
Family
ID=77321539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110516880.8A Active CN113297788B (en) | 2021-05-12 | 2021-05-12 | Water quality soft measurement method and system based on improved neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113297788B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102854296A (en) * | 2012-08-30 | 2013-01-02 | 北京工业大学 | Sewage-disposal soft measurement method on basis of integrated neural network |
| CN106645620A (en) * | 2016-12-23 | 2017-05-10 | 江西理工大学 | Hybrid differential evolution based BOD soft measurement method for farmland water body in rare earth mine lot |
| CN110109904A (en) * | 2019-04-10 | 2019-08-09 | 广东奥博信息产业股份有限公司 | A kind of water quality flexible measurement method towards environmentally friendly big data |
| CN110610261A (en) * | 2019-08-23 | 2019-12-24 | 广东奥博信息产业股份有限公司 | Water body dissolved oxygen prediction method based on neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108088974B (en) * | 2017-11-30 | 2021-03-30 | 华南理工大学 | Soft measurement method for effluent nitrate nitrogen in anaerobic simultaneous denitrification methanogenesis process |
-
2021
- 2021-05-12 CN CN202110516880.8A patent/CN113297788B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102854296A (en) * | 2012-08-30 | 2013-01-02 | 北京工业大学 | Sewage-disposal soft measurement method on basis of integrated neural network |
| CN106645620A (en) * | 2016-12-23 | 2017-05-10 | 江西理工大学 | Hybrid differential evolution based BOD soft measurement method for farmland water body in rare earth mine lot |
| CN110109904A (en) * | 2019-04-10 | 2019-08-09 | 广东奥博信息产业股份有限公司 | A kind of water quality flexible measurement method towards environmentally friendly big data |
| CN110610261A (en) * | 2019-08-23 | 2019-12-24 | 广东奥博信息产业股份有限公司 | Water body dissolved oxygen prediction method based on neural network |
Non-Patent Citations (1)
| Title |
|---|
| 基于PCA-GABP神经网络的BOD软测量方法;冉维丽等;《控制工程》;20040520(第03期);第212页-215页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113297788A (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147760B (en) | Novel efficient electric energy quality disturbance image feature extraction and identification method | |
| Qian et al. | On the effectiveness of sampling for evolutionary optimization in noisy environments | |
| CN110020712B (en) | Optimized particle swarm BP network prediction method and system based on clustering | |
| CN111815432B (en) | Financial service risk prediction method and device | |
| CN114241779B (en) | Short-time prediction method, computer and storage medium for urban expressway traffic flow | |
| CN111564179B (en) | Species biology classification method and system based on triple neural network | |
| CN111047073B (en) | Aquaculture water quality prediction method and system based on neural network | |
| CN113269396A (en) | Water environment risk evaluation method and system based on multilevel grey correlation | |
| CN111931983A (en) | Precipitation prediction method and system | |
| CN109872330A (en) | A kind of two-dimentional Otsu Fast image segmentation method for improving lion group's optimization | |
| CN116699096B (en) | Water quality detection method and system based on deep learning | |
| CN113761805A (en) | Controllable source electromagnetic data denoising method, system, terminal and readable storage medium based on time domain convolution network | |
| CN113988357A (en) | High-rise building wind-induced response prediction method and device based on deep learning | |
| CN113297788B (en) | Water quality soft measurement method and system based on improved neural network | |
| CN113269395A (en) | Water environment risk pre-judging method and system based on pressure state feedback framework | |
| Tang et al. | Seabed mixed sediment classification with multi-beam echo sounder backscatter data in Jiaozhou Bay | |
| CN112614552B (en) | BP neural network-based soil heavy metal content prediction method and system | |
| CN116662893A (en) | Water quality prediction method for optimizing SVM (support vector machine) based on improved goblet sea squirt algorithm | |
| CN110414585B (en) | Real-time particulate matter detection method based on improved embedded platform | |
| CN110569871B (en) | Saddle point identification method based on deep convolutional neural network | |
| Mittermayr et al. | Using CMECS to create benthic habitat maps for Pleasant Bay, Cape Cod, Massachusetts | |
| CN107067397A (en) | A kind of image grading method based on infrared image complexity | |
| CN116503026A (en) | Operation and maintenance risk assessment method, system and storage medium for science and technology items | |
| CN110751400A (en) | Risk assessment method and device | |
| Wu et al. | Estimation of soil pH with geochemical indices in forest soils |
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 |