CN112580740B - Ozone concentration measuring method, ozone concentration measuring device, electronic equipment and storage medium - Google Patents
Ozone concentration measuring method, ozone concentration measuring device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112580740B CN112580740B CN202011583164.3A CN202011583164A CN112580740B CN 112580740 B CN112580740 B CN 112580740B CN 202011583164 A CN202011583164 A CN 202011583164A CN 112580740 B CN112580740 B CN 112580740B
- Authority
- CN
- China
- Prior art keywords
- ozone
- ozone generator
- concentration
- neural network
- artificial neural
- 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
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 title claims abstract description 281
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 79
- 238000012549 training Methods 0.000 claims abstract description 63
- 238000012360 testing method Methods 0.000 claims abstract description 18
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 23
- 239000001301 oxygen Substances 0.000 claims description 23
- 229910052760 oxygen Inorganic materials 0.000 claims description 23
- 238000001514 detection method Methods 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 13
- 230000007786 learning performance Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000000691 measurement method Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims 2
- 238000012423 maintenance Methods 0.000 abstract description 4
- 238000005259 measurement Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- VGGSQFUCUMXWEO-UHFFFAOYSA-N Ethene Chemical compound C=C VGGSQFUCUMXWEO-UHFFFAOYSA-N 0.000 description 6
- 239000005977 Ethylene Substances 0.000 description 6
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010521 absorption reaction Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000007789 gas Substances 0.000 description 3
- NLKNQRATVPKPDG-UHFFFAOYSA-M potassium iodide Chemical compound [K+].[I-] NLKNQRATVPKPDG-UHFFFAOYSA-M 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000007800 oxidant agent Substances 0.000 description 2
- MYMOFIZGZYHOMD-UHFFFAOYSA-N Dioxygen Chemical compound O=O MYMOFIZGZYHOMD-UHFFFAOYSA-N 0.000 description 1
- 230000000844 anti-bacterial effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000003899 bactericide agent Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000009849 deactivation Effects 0.000 description 1
- 239000003989 dielectric material Substances 0.000 description 1
- 238000002848 electrochemical method Methods 0.000 description 1
- 239000007772 electrode material Substances 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005281 excited state Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000004205 output neuron Anatomy 0.000 description 1
- 230000001590 oxidative effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000008399 tap water Substances 0.000 description 1
- 235000020679 tap water Nutrition 0.000 description 1
- 238000004448 titration Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- 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
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides an ozone concentration measuring method, an ozone concentration measuring device, electronic equipment and a storage medium, wherein the measuring method comprises the following steps: acquiring working parameters of the ozone generator under a given working condition; determining the concentration of ozone generated by an ozone generator under a given working condition based on a pre-trained artificial neural network model according to working parameters; wherein, the artificial neural network model includes: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the intermediate layer is determined through training according to the training sample. The invention breaks through the problems of the cost of the hardware, the related service life, maintenance and the like, and reduces the cost required by ozone concentration test.
Description
Technical Field
The present invention relates to the field of ozone concentration measurement technologies, and in particular, to an ozone concentration measurement method, an ozone concentration measurement device, an electronic device, and a storage medium.
Background
Ozone is a green and environment-friendly strong oxidant and bactericide, and is widely applied in the fields of sewage treatment, tap water disinfection, food processing and the like due to the excellent chemical characteristics of the ozone. Ozone molecules are easy to decompose and are required to be produced and used on site. The current methods for preparing ozone include electrochemical methods, ultraviolet irradiation methods, etc., and in industrial applications, dielectric Barrier Discharge (DBD) methods are mainly used for producing ozone. The research of ozone technology is of great significance not only at present but also in the future.
The DBD type ozone generator is widely used, the actual production efficiency and the theoretical calculation value of the DBD type ozone generator have a large gap, and the ozone generator manufactured in China at present mainly has the problems of low single machine output and high energy consumption, which also becomes a hot spot for a plurality of scholars to study.
From the research content of many scholars, an accurate model of the ozone generation process is not researched, the process of producing ozone by a dielectric barrier discharge method is complex, mathematical accurate description is difficult to use, in the production process, ozone concentration, yield and production efficiency are affected by a plurality of factors, and a system can be better controlled only by acquiring an accurate system input-output relationship. The research aims at integrating the input and output models of each influence factor acquisition system so as to better control the ozone production.
At present, two methods of an ethylene chemiluminescence method and an ultraviolet radiation absorption method are the most common methods for detecting the concentration of ozone.
The principle of ethylene chemiluminescence is to react ozone with ethylene in the gas phase to produce formaldehyde and oxygen, the formaldehyde molecules being initially in an excited state, their deactivation being accompanied by photon emission. Since the luminous intensity is proportional to the concentration of ozone, it can be detected by a photomultiplier tube. However, the ethylene chemiluminescence method cannot guarantee an absolute measurement value of ozone concentration, and must be calibrated against a common standard method (such as potassium iodide titration method), and an ethylene gas bottle must be used, so that ethylene is a flammable gas, and therefore, there is a certain danger. Moreover, chemical reactions require time, so we cannot monitor and update data in real time. And requires consumption and therefore has a limited service life.
The ultraviolet radiation absorption method is to measure the ozone concentration by utilizing the characteristics that ozone has the characteristic of absorbing ultraviolet light in a short wave ultraviolet region (200-300 nm) and has the maximum absorption value at the wavelength of 253.7nm, and has the advantages of high measurement precision, good stability, continuous detection, small interference by other oxidants and the like, and is the most commonly used online detection method for the ozone concentration. Although the ultraviolet radiation absorption method has high measurement accuracy and can continuously monitor, the method has high use cost, has the problem of limited service life, and can not play a role in measurement once materials are consumed.
In a word, the current ozone concentration detection method has the problems of high cost and limited service life no matter whether on-line detection is possible or not.
Disclosure of Invention
The invention provides an ozone concentration measuring method, an ozone concentration measuring device, electronic equipment and a storage medium, and aims to reduce ozone concentration detection cost.
The invention provides an ozone concentration measuring method, which is used for measuring the concentration of oxygen generated by an ozone generator, and comprises the following steps: acquiring working parameters of the ozone generator under a given working condition; determining the concentration of ozone generated by the ozone generator under the given working condition based on a pre-trained artificial neural network model according to the working parameters; wherein the pre-trained artificial neural network model comprises: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the intermediate layer is determined through training according to training samples.
According to the ozone concentration measuring method provided by the invention, the working parameters are selected according to parameters related to the output power of the ozone generator.
According to the ozone concentration measuring method provided by the invention, the working parameters comprise one or a combination of the following parameters:
the operating frequency of the ozone generator power supply, the temperature of the ozone generator discharge chamber, the peak voltage of the ozone generator power supply, the pressure of oxygen in the ozone generator, the flow of oxygen in the ozone generator, and the current intensity of the ozone generator power supply.
According to the ozone concentration measuring method provided by the invention, the training sample is obtained through the following steps: collecting working parameters of the ozone generator under a given working condition; measuring the concentration of ozone generated by the ozone generator under each given working condition by adopting an ozone concentration meter; correlating the working parameters under each given working condition with the ozone concentration measured and obtained under the working condition to be used as a training sample.
According to the ozone concentration measuring method provided by the invention, the intermediate layer is determined through training by the following steps: dividing the training sample into a training set, a verification set and a test set; determining model parameters including weights and biases in the artificial neural network model based on the training set; based on the verification set, adjusting the network layer number of the middle layer in the artificial neural network model; and evaluating the learning performance of the artificial neural network model based on the test set.
According to the ozone concentration measuring method provided by the invention, after evaluating the learning performance of the artificial neural network model based on the test set, the method further comprises the following steps: and when the learning performance is lower than a given threshold value, re-executing the steps of determining model parameters including weights and biases in the artificial neural network model and/or adjusting the network layer number of the middle layer in the artificial neural network model.
According to the ozone concentration measuring method provided by the invention, in the training sample, the training set, the verification set and the test set are distributed according to the preset distribution proportion.
The invention also provides an ozone concentration measuring device for measuring the concentration of oxygen generated by an ozone generator, which comprises: the working parameter acquisition module and the ozone concentration determination module. The working parameter acquisition module is used for acquiring working parameters of the ozone generator under a given working condition; the ozone concentration determining module is used for determining the concentration of ozone generated by the ozone generator under the given working condition based on an artificial neural network model which is trained in advance according to the working parameters; wherein the artificial neural network model comprises: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the intermediate layer is determined through training according to training samples.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the steps of the ozone concentration measuring method of the ozone generator are realized when the processor executes the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor realizes the steps of the ozone concentration measuring method of an ozone generator as described above.
The invention carries out concentration measurement on the ozone generated by the ozone generator based on the artificial neural network model, and because the measurement is based on software, the problems of the hardware of the ozone concentration meter, the related service life, maintenance and the like are broken through, and the cost required by ozone concentration measurement is reduced.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an ozone concentration measuring method provided by the invention;
FIG. 2 is a schematic diagram of the logic structure of an artificial neural network model which is trained in advance in the ozone concentration measuring method provided by the invention;
FIG. 3 is a schematic diagram of the training of an artificial neural network model in the ozone concentration measurement method of the present invention;
FIG. 4 is a schematic flow chart of obtaining a test sample in the ozone concentration measuring method of the present invention;
FIG. 5 is a schematic diagram of a process flow of training a model of an artificial neural network based on training samples in the ozone concentration measurement method of the present invention;
FIG. 6 is a schematic diagram of the structure of the ozone concentration measuring device provided by the invention;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, 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.
The ozone concentration measuring method of the present invention is described below with reference to fig. 1 to 5.
Referring to fig. 1, fig. 1 is a flow chart of an ozone concentration measuring method provided by the invention, which is used for measuring the concentration of ozone generated by an ozone generator, and comprises the following steps:
step 110, obtaining working parameters of an ozone generator under a given working condition;
step 120, determining the concentration of ozone generated by the ozone generator under a given working condition based on the artificial neural network model which is trained in advance according to the working parameters.
Wherein the pre-trained artificial neural network model comprises: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the intermediate layer is determined through training according to the training sample.
The concentration detection is performed on the ozone generated by the ozone generator based on the artificial neural network model, and because the detection is based on software, the problems of the hardware of the ozone concentration meter, the related service life, maintenance and the like are broken through, and the cost required by the measurement of the ozone concentration is reduced.
The above steps are further described below.
Step 110, the working parameters of the ozone generator under the given working condition are obtained.
Ozone generators produce high concentrations of ozone based on the high pressure ionization of compressed air or pure oxygen. The operating parameters are selected according to parameters associated with the output power of the ozone generator.
The reason for such selection of the operating parameters is that the operating parameters of the ozone generator are related to their power, which in turn is related to the concentration of ozone produced, and thus the concentration of ozone produced can be predicted indirectly by determining the operating parameters of the power of the ozone generator.
The output power of the ozone generator has the following relation with each parameter of the ozone generator:
wherein:
f is the working frequency of the power supply,
U m is the peak value of the supply voltage,
U z in order to provide a discharge voltage, the voltage is,
C d is equivalent dielectric capacitance of the discharge chamber and is related to factors such as electrode materials, discharge chamber materials and the like
C g Is the equivalent air gap capacitance of the discharge chamber, and is mainly influenced by factors such as oxygen flow, pressure, temperature, dielectric materials, dielectric gaps and the like.
Therefore, in the implementation, the relevant parameter may be selected from the parameters involved in the above formula and the determinants of the parameters involved in the formula as the operation parameters. For example, in one embodiment, the operating parameters may select one or a combination of the following parameters:
A. the operating frequency of the ozone generator power supply;
B. the temperature of the ozone generator discharge chamber;
C. peak voltage of ozone generator power supply;
D. the pressure of the oxygen in the ozone generator;
E. flow of oxygen in the ozone generator.
F. Current intensity of power supply of ozone generator
It should be noted that, as the input information of the input layer of the artificial neural network model, the above parameters may be selected simultaneously or selectively. The invention is not limited in this regard and, in general, the more effective operating parameters, the more accurate the predicted ozone concentration may be.
Step 120, determining the concentration of ozone generated by the ozone generator under a given working condition based on the artificial neural network model which is trained in advance according to the working parameters.
Referring to fig. 2, fig. 2 shows a schematic diagram of a pre-trained artificial neural network model.
The pre-trained artificial neural network model includes: an input layer, an intermediate layer, and an output layer. The working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the intermediate layer is determined through training according to the training sample.
The working parameters accepted by the input layer are as follows: the current intensity of the power supply of the ozone generator, the flow of the oxygen in the ozone generator, the pressure of the oxygen in the ozone generator, the temperature of the discharge chamber of the ozone generator and the working frequency of the power supply of the ozone generator.
The following describes how to train an artificial neural network to obtain the above-described artificial neural network model capable of predicting ozone concentration.
Referring to fig. 3, fig. 3 is a schematic diagram of training an artificial neural network model in the ozone concentration measuring method of the present invention.
Under a certain working condition, the working parameters of the ozone generator are monitored, including the current intensity of a power supply of the ozone generator, the flow of oxygen in the ozone generator, the pressure of oxygen in the ozone generator, the temperature of a discharge chamber of the ozone generator and the working frequency of the power supply of the ozone generator, and the obtained working parameters are input into an artificial neural network model. And outputting the ozone concentration under the current working condition through the operation of the artificial neural network model.
On the other hand, the ozone concentration meter also detects the concentration of the generated ozone.
And adjusting the artificial neural network model through the obtained detection result of the ozone concentration meter, wherein the adjustment can comprise parameter adjustment, layer number adjustment and the like. Then, the working condition of the ozone generator is changed, the generated ozone concentration is continuously predicted by using the improved artificial neural network model, the predicted result is compared with the result measured by the ozone concentration meter, and the parameters or the structure of the artificial neural network model are corrected again. And by analogy, the artificial neural network model is continuously optimized in the mode until the accuracy of oxygen concentration judgment based on the artificial neural network model reaches a certain set threshold value, and the optimization is stopped, so that the currently obtained artificial neural network model is determined to be the artificial neural network model which is trained in advance.
In one embodiment, the training samples may also be obtained by a step flow chart as shown in fig. 4, including:
step 410, collecting working parameters of the ozone generator under a given working condition;
step 420, measuring the concentration of ozone generated by the ozone generator under each given working condition by adopting an ozone concentration meter;
step 430, associating the operating parameters for each given condition with the measured ozone concentration for that condition as a training sample.
According to the above method, a plurality of training samples may be generated.
Referring to fig. 5, fig. 5 is a flowchart showing a step of training a model of an artificial neural network, particularly an intermediate layer, based on a training sample in the ozone concentration measuring method of the present invention, including:
step 510, dividing the training samples into training sets, verification sets and test sets.
In specific implementation, in the training samples, the training set, the verification set and the test set are allocated according to a preset allocation ratio, which may be 6:2:2, for example, for a certain small-scale sample set, 10000 samples are shared, the training set is divided into 6000 samples, the verification set is 2000 samples, and the test set is 2000 samples.
Step 520, determining model parameters including weights and biases in the artificial neural network model based on the training set;
step 530, adjusting the network layer number of the middle layer in the artificial neural network model based on the verification set;
under the condition of network structure determination, the artificial neural network model has two parts, namely common parameters such as weight w and bias b and super parameters such as learning rate and network layer number, which influence the final performance of the model. The performance of the artificial neural network is continuously improved through the above steps 520 and 530.
Step 540, based on the test set, evaluating learning performance of the artificial neural network model.
Step 550, determining whether the learning performance obtained by the evaluation exceeds a given threshold? If not, go to step 560, if yes, go to step 570.
Step 560, return to step 520 and/or step 530.
Step 570, model training of the artificial neural network is ended.
In particular, the artificial neural network model may be selected from various known models, such as FCN, segNet, unet, 3D-Unet, mask-RCNN, ENet, CRFasRNN, PSPNet, parseNet, refineNet, reSeg, LSTM-CF, deepMask, deepLabV1, deep LabV2, deep LabV3, etc., which are not limiting.
In summary, it can be seen that the present invention introduces an artificial neural network, selects typical factors affecting ozone generation by an ozone generator as input information of each neuron in the input layer, uses ozone concentration as output neurons of the artificial neural network, and uses ozone concentration meter to measure ozone concentration as a label. And (3) establishing a mapping model according to the input and the output, and treating the ozone generator as a 'black box'. And finally training a network model capable of predicting the ozone generation concentration through the input and output data of the system. This network model can then be used directly to measure the concentration of ozone on-line. The advantages of this approach are the following:
1) An artificial neural network model is adopted, and the neural network model is trained according to input and output data of the system, so that the system can predict the output ozone concentration.
2) The trained artificial neural network model can directly replace the use of the ozone concentration meter in a hardware form, so that the cost is saved.
Referring to fig. 6, the present invention also provides an ozone concentration measuring apparatus for measuring the concentration of ozone generated by an ozone generator, the apparatus comprising:
an operating parameter obtaining module 62, configured to obtain an operating parameter of the ozone generator under a given operating condition;
the ozone concentration determining module 64 is configured to determine a concentration of ozone generated by the ozone generator under a given operating condition based on an artificial neural network model that has been trained in advance according to an operating parameter.
Wherein, the artificial neural network model includes: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the intermediate layer is determined through training according to the training sample.
The concentration detection is performed on the ozone generated by the ozone generator based on the artificial neural network model, and because the detection is based on software, the problems of the hardware of the ozone concentration meter, the related service life, maintenance and the like are broken through, and the cost required by the measurement of the ozone concentration is reduced.
In one embodiment, the operating parameters are selected in accordance with parameters associated with the ozone generator output power. May include one or a combination of the following parameters:
the operating frequency of the power supply of the ozone generator, the temperature of the discharge chamber of the ozone generator, the peak voltage of the power supply of the ozone generator, the pressure of oxygen in the ozone generator, the flow of oxygen in the ozone generator and the current intensity of the power supply of the ozone generator.
In a preferred embodiment, the training samples are obtained by: collecting working parameters of the ozone generator under a given working condition; measuring the concentration of ozone generated by an ozone generator under each given working condition by adopting an ozone concentration meter; the working parameters under each given working condition are correlated with the ozone concentration measured under the working condition to be used as a training sample.
And, the intermediate layer can be determined by training the following steps: dividing a training sample into a training set, a verification set and a test set; determining model parameters including weights and biases in the artificial neural network model based on the training set; based on the verification set, adjusting the network layer number of the middle layer in the artificial neural network model; based on the test set, the learning performance of the artificial neural network model is evaluated.
In the training samples, the training set, the verification set and the test set are distributed according to preset distribution proportion.
Preferably, after evaluating the learning performance of the artificial neural network model based on the test set, the method further comprises: and when the learning performance is lower than a given threshold value, the step of determining model parameters including weights and biases in the artificial neural network model and/or adjusting the network layer number of the middle layer in the artificial neural network model is re-executed.
Fig. 7 illustrates a physical schematic diagram of an electronic device, as shown in fig. 7, which may include: processor 710, communication interface (Communications Interface) 720, memory 730, and communication bus 740, wherein processor 710, communication interface 720, memory 730 communicate with each other via communication bus 740. Processor 710 may invoke logic instructions in memory 730 to perform the ozone concentration measurement method previously described, including:
acquiring working parameters of the ozone generator under a given working condition; determining the concentration of ozone generated by the ozone generator under the given working condition based on an artificial neural network model which is trained in advance according to the working parameters; wherein the artificial neural network model comprises: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the intermediate layer is determined through training according to training samples.
Further, the logic instructions in the memory 730 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, are capable of executing the methods provided above to perform the ozone concentration measuring method described above, comprising:
acquiring working parameters of the ozone generator under a given working condition; determining the concentration of ozone generated by the ozone generator under the given working condition based on an artificial neural network model which is trained in advance according to the working parameters; wherein the artificial neural network model comprises: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the intermediate layer is determined through training according to training samples.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the foregoing ozone concentration measurement method, comprising:
acquiring working parameters of the ozone generator under a given working condition; determining the concentration of ozone generated by the ozone generator under the given working condition based on an artificial neural network model which is trained in advance according to the working parameters; wherein the artificial neural network model comprises: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the intermediate layer is determined through training according to training samples.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. An ozone concentration measuring method for measuring the concentration of ozone generated by an ozone generator, comprising the steps of:
acquiring working parameters of the ozone generator under a given working condition; the working parameters include: the operating frequency of the ozone generator power supply; the temperature of the ozone generator discharge chamber; peak voltage of ozone generator power supply; the pressure of the oxygen in the ozone generator; the flow of oxygen in the ozone generator; the current intensity of the power supply of the ozone generator; the relation between the concentration of ozone generated by the ozone generator and the working parameter is as follows:
；
wherein,for the output power, the output power influences the ozone generationConcentration of ozone produced by the generator, < >>The operating frequency of the power supply for the ozone generator, < >>Peak voltage of the ozone generator power supply, which is related to the current intensity of the ozone generator power supply, +.>Is the discharge voltage of the ozone generator, < >>Dielectric capacitance equivalent to the discharge chamber of the ozone generator,>an equivalent air gap capacitance of an ozone generator discharge chamber, wherein the equivalent air gap capacitance of the ozone generator discharge chamber is related to the pressure of oxygen in the ozone generator, the temperature of the ozone generator discharge chamber and the flow of oxygen in the ozone generator;
determining the concentration of ozone generated by the ozone generator under the given working condition based on a pre-trained artificial neural network model according to the working parameters;
wherein the pre-trained artificial neural network model comprises: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the middle layer is determined through training according to a training sample;
wherein, after determining the concentration of ozone generated by the ozone generator under the given working condition based on the working parameter and the pre-trained artificial neural network model, the method further comprises:
detecting the concentration of ozone by adopting an ozone concentration meter, and adjusting the artificial neural network model based on the detection result of the ozone concentration meter;
predicting the concentration of the ozone by adopting the adjusted artificial neural network model to obtain a prediction result;
and correcting the adjusted artificial neural network model based on the prediction result and the detection result.
2. The ozone concentration measuring method of claim 1, wherein the operating parameter is selected in accordance with a parameter associated with the ozone generator output power.
3. The ozone concentration measurement method according to any one of claims 1 to 2, characterized in that the training sample is obtained by:
collecting the working parameters of the ozone generator under a given working condition;
measuring the concentration of the ozone generated by the ozone generator under each given working condition by adopting the ozone concentration meter;
correlating the working parameter under each given working condition with the ozone concentration measured and obtained under the working condition to be used as one training sample.
4. The ozone concentration measuring method according to claim 3, wherein the intermediate layer is determined by training:
dividing the training sample into a training set, a verification set and a test set;
determining model parameters including weights and biases in the artificial neural network model based on the training set;
based on the verification set, adjusting the network layer number of the middle layer in the artificial neural network model;
and evaluating the learning performance of the artificial neural network model based on the test set.
5. The ozone concentration measurement method according to claim 4, wherein after evaluating learning performance of the artificial neural network model based on the test set, further comprising:
and when the learning performance is lower than a given threshold value, re-executing the steps of determining model parameters including weights and biases in the artificial neural network model and/or adjusting the network layer number of the middle layer in the artificial neural network model.
6. The method for measuring ozone concentration according to claim 5, wherein,
and in the training samples, the training set, the verification set and the test set are distributed according to preset distribution proportion.
7. An ozone concentration measuring apparatus for measuring the concentration of ozone generated by an ozone generator, comprising:
the working parameter acquisition module is used for acquiring working parameters of the ozone generator under a given working condition; the working parameters include: the operating frequency of the ozone generator power supply; the temperature of the ozone generator discharge chamber; peak voltage of ozone generator power supply; the pressure of the oxygen in the ozone generator; the flow of oxygen in the ozone generator; the current intensity of the power supply of the ozone generator;
the ozone concentration determining module is used for determining the concentration of ozone generated by the ozone generator under the given working condition based on an artificial neural network model which is trained in advance according to the working parameters;
wherein the artificial neural network model comprises: an input layer, an intermediate layer, and an output layer; the working parameters under the given working conditions are used for providing input information for the input layer, and the output information of the output layer is used for representing the concentration of ozone generated by the ozone generator; the middle layer is determined through training according to a training sample;
the ozone concentration measuring device further comprises a correction module, wherein the correction module is used for detecting the concentration of the ozone by adopting an ozone concentration meter, and adjusting the artificial neural network model based on the detection result of the ozone concentration meter; predicting the concentration of the ozone by adopting the adjusted artificial neural network model to obtain a prediction result, and correcting the adjusted artificial neural network model based on the prediction result and the detection result;
wherein, the relation between the concentration of ozone generated by the ozone generator and the working parameter is as follows:
；
wherein,for the output power, said output power influences the concentration of ozone generated by said ozone generator,/->The operating frequency of the power supply for the ozone generator, < >>Peak voltage of the ozone generator power supply, which is related to the current intensity of the ozone generator power supply, +.>Is the discharge voltage of the ozone generator, < >>Dielectric capacitance equivalent to the discharge chamber of the ozone generator,>the equivalent air gap capacitance of the ozone generator discharge chamber is equivalent to the pressure of oxygen in the ozone generator and the ozoneThe temperature of the generator discharge chamber and the flow of oxygen in the ozone generator.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the ozone generator ozone concentration measuring method according to any one of claims 1 to 6 when the program is executed.
9. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the ozone generator ozone concentration measuring method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011583164.3A CN112580740B (en) | 2020-12-28 | 2020-12-28 | Ozone concentration measuring method, ozone concentration measuring device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011583164.3A CN112580740B (en) | 2020-12-28 | 2020-12-28 | Ozone concentration measuring method, ozone concentration measuring device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112580740A CN112580740A (en) | 2021-03-30 |
| CN112580740B true CN112580740B (en) | 2024-03-01 |
Family
ID=75140428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011583164.3A Active CN112580740B (en) | 2020-12-28 | 2020-12-28 | Ozone concentration measuring method, ozone concentration measuring device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112580740B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113791650B (en) * | 2021-08-16 | 2023-12-22 | 北京农业信息技术研究中心 | Ozone concentration adjusting method and system |
| WO2023228126A1 (en) * | 2022-05-25 | 2023-11-30 | Ho Keung Tse | Sterilizing substance concentration info apparatus and method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100952852B1 (en) * | 2009-06-29 | 2010-04-13 | 한국수자원공사 | Apparatus and method for controlling ozone concentration with measuring ozone concentrations at multipoints |
| CN102269980A (en) * | 2010-06-07 | 2011-12-07 | 西安费斯达自动化工程有限公司 | Man-machine interactive health management method of ozone generator |
| CN205528209U (en) * | 2016-01-26 | 2016-08-31 | 临沂高新区鲁润净水设备有限公司 | Ozone purifier intelligence control system based on fuzzy neural network |
| CN108017125A (en) * | 2016-10-29 | 2018-05-11 | 哈尔滨皓威伟业科技发展有限公司 | A kind of ozone sterilization water-purifier intelligence control system |
| CN108073073A (en) * | 2016-11-10 | 2018-05-25 | 哈尔滨皓威伟业科技发展有限公司 | A kind of design method of ozone sterilization water-purifier |
| CN108108836A (en) * | 2017-12-15 | 2018-06-01 | 清华大学 | A kind of ozone concentration distribution forecasting method and system based on space-time deep learning |
| CN108238671A (en) * | 2016-12-23 | 2018-07-03 | 哈尔滨皓威伟业科技发展有限公司 | A kind of Intelligent ozone water purifier design method |
| CN108898261A (en) * | 2018-07-24 | 2018-11-27 | 深圳市源广浩电子有限公司 | A kind of air quality monitoring method and system based on environmentally friendly big data |
| CN109858136A (en) * | 2019-01-26 | 2019-06-07 | 新奥数能科技有限公司 | A kind of determination method and apparatus of gas fired-boiler efficiency |
| CN110826749A (en) * | 2018-08-07 | 2020-02-21 | 中国农业大学 | Dissolved oxygen content prediction method based on SNN, electronic device and system |
| CN111126603A (en) * | 2019-12-25 | 2020-05-08 | 江苏远望仪器集团有限公司 | Equipment fault prediction method, device and equipment based on neural network model |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8851010B2 (en) * | 2011-10-12 | 2014-10-07 | Intermolecular, Inc. | Systems and methods for measuring, monitoring and controlling ozone concentration |
| US8925481B2 (en) * | 2011-10-12 | 2015-01-06 | Intermolecular, Inc. | Systems and methods for measuring, monitoring and controlling ozone concentration |
-
2020
- 2020-12-28 CN CN202011583164.3A patent/CN112580740B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100952852B1 (en) * | 2009-06-29 | 2010-04-13 | 한국수자원공사 | Apparatus and method for controlling ozone concentration with measuring ozone concentrations at multipoints |
| CN102269980A (en) * | 2010-06-07 | 2011-12-07 | 西安费斯达自动化工程有限公司 | Man-machine interactive health management method of ozone generator |
| CN205528209U (en) * | 2016-01-26 | 2016-08-31 | 临沂高新区鲁润净水设备有限公司 | Ozone purifier intelligence control system based on fuzzy neural network |
| CN108017125A (en) * | 2016-10-29 | 2018-05-11 | 哈尔滨皓威伟业科技发展有限公司 | A kind of ozone sterilization water-purifier intelligence control system |
| CN108073073A (en) * | 2016-11-10 | 2018-05-25 | 哈尔滨皓威伟业科技发展有限公司 | A kind of design method of ozone sterilization water-purifier |
| CN108238671A (en) * | 2016-12-23 | 2018-07-03 | 哈尔滨皓威伟业科技发展有限公司 | A kind of Intelligent ozone water purifier design method |
| CN108108836A (en) * | 2017-12-15 | 2018-06-01 | 清华大学 | A kind of ozone concentration distribution forecasting method and system based on space-time deep learning |
| CN108898261A (en) * | 2018-07-24 | 2018-11-27 | 深圳市源广浩电子有限公司 | A kind of air quality monitoring method and system based on environmentally friendly big data |
| CN110826749A (en) * | 2018-08-07 | 2020-02-21 | 中国农业大学 | Dissolved oxygen content prediction method based on SNN, electronic device and system |
| CN109858136A (en) * | 2019-01-26 | 2019-06-07 | 新奥数能科技有限公司 | A kind of determination method and apparatus of gas fired-boiler efficiency |
| CN111126603A (en) * | 2019-12-25 | 2020-05-08 | 江苏远望仪器集团有限公司 | Equipment fault prediction method, device and equipment based on neural network model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112580740A (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112580740B (en) | Ozone concentration measuring method, ozone concentration measuring device, electronic equipment and storage medium | |
| Sun et al. | Transverse momentum dependent evolution: Matching semi-inclusive deep inelastic scattering processes to Drell-Yan and W/Z boson production | |
| CN103793854B (en) | The overhead transmission line operation risk informatization evaluation method that Multiple Combination is optimized | |
| CN106529124A (en) | A transformer insulation state assessment method based on principal component analysis and support vector machines | |
| JP2001500199A (en) | Process for controlling the efficiency of the causticizing process | |
| Cao et al. | A rapid determination method for chemical oxygen demand in aquaculture wastewater using the ultraviolet absorbance spectrum and chemometrics | |
| CN105242155A (en) | Transformer fault diagnosis method based on entropy weight method and grey correlation analysis | |
| Gong et al. | Machine learning assistance for electrochemical curve simulation of corrosion and its application | |
| Zhang et al. | Plant-scale biogas production prediction based on multiple hybrid machine learning technique | |
| CN110070220A (en) | A kind of ammonia nitrogen index flexible measurement method based on neural network algorithm | |
| CN105092493B (en) | A kind of water body COD measuring methods based on water sample type identification | |
| CN101943658A (en) | Method for continuously monitoring water quality by combining principal component analysis theory and spectrum analysis technology | |
| CN104978484A (en) | Fuzzy forecasting model based method for detecting pulp concentration in ore grinding process of dressing plant | |
| Yu et al. | Multi-component spectral detection based on neural network in water quality inspection | |
| CN105911003B (en) | The water quality TOC concentration analysis returned based on RBM | |
| Wang et al. | Machine learning with explainable artificial intelligence vision for characterization of solution conductivity using optical emission spectroscopy of plasma in aqueous solution | |
| Geng et al. | Online rapid total nitrogen detection method based on UV spectrum and spatial interval permutation combination population analysis | |
| CN116818693A (en) | Secondary water supply quality online monitoring method based on ultraviolet-visible spectrum and three-dimensional fluorescence spectrum fusion | |
| CN105241823A (en) | Thermal power plant flue gas spectral quantitative analysis method based on sparse representation | |
| Mukerji et al. | Chaotic map models of soot fluctuations in turbulent diffusion flames | |
| Zhu et al. | Partial derivate contribution plot based on KPLS-KSER for nonlinear process fault diagnosis | |
| CN113029993A (en) | Ultraviolet spectrum rapid total nitrogen online detection method based on attention mechanism | |
| Xing et al. | Dynamic soft sensing of organic pollutants in effluent from UMIC anaerobic reactor for industrial papermaking wastewater | |
| CN110441376A (en) | A kind of COD online test method and device | |
| Liu et al. | ANN-based prediction of ammonia nitrogen for wastewater discharge indicators under carbon neutral trend |
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 |