CN110175397A - A kind of sterilizing parameter selection method and system based on artificial nerve network model - Google Patents
A kind of sterilizing parameter selection method and system based on artificial nerve network model Download PDFInfo
- Publication number
- CN110175397A CN110175397A CN201910439792.5A CN201910439792A CN110175397A CN 110175397 A CN110175397 A CN 110175397A CN 201910439792 A CN201910439792 A CN 201910439792A CN 110175397 A CN110175397 A CN 110175397A
- Authority
- CN
- China
- Prior art keywords
- parameters
- ultrasonic
- network model
- 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.)
- Granted
Links
- 230000001954 sterilising effect Effects 0.000 title claims abstract description 110
- 238000010187 selection method Methods 0.000 title claims abstract description 22
- 210000005036 nerve Anatomy 0.000 title abstract 4
- 238000004659 sterilization and disinfection Methods 0.000 claims abstract description 100
- 238000002604 ultrasonography Methods 0.000 claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 8
- 238000013528 artificial neural network Methods 0.000 claims description 71
- 238000012795 verification Methods 0.000 claims description 44
- 241000894006 Bacteria Species 0.000 claims description 33
- 238000000034 method Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000002474 experimental method Methods 0.000 abstract description 19
- 230000000694 effects Effects 0.000 abstract description 16
- 238000004088 simulation Methods 0.000 abstract description 3
- 239000000523 sample Substances 0.000 description 31
- 230000004083 survival effect Effects 0.000 description 18
- CHADEQDQBURGHL-UHFFFAOYSA-N (6'-acetyloxy-3-oxospiro[2-benzofuran-1,9'-xanthene]-3'-yl) acetate Chemical compound O1C(=O)C2=CC=CC=C2C21C1=CC=C(OC(C)=O)C=C1OC1=CC(OC(=O)C)=CC=C21 CHADEQDQBURGHL-UHFFFAOYSA-N 0.000 description 8
- XJMOSONTPMZWPB-UHFFFAOYSA-M propidium iodide Chemical compound [I-].[I-].C12=CC(N)=CC=C2C2=CC=C(N)C=C2[N+](CCC[N+](C)(CC)CC)=C1C1=CC=CC=C1 XJMOSONTPMZWPB-UHFFFAOYSA-M 0.000 description 8
- 210000000170 cell membrane Anatomy 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000001580 bacterial effect Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000000684 flow cytometry Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 102000004882 Lipase Human genes 0.000 description 1
- 108090001060 Lipase Proteins 0.000 description 1
- 239000004367 Lipase Substances 0.000 description 1
- 241000187479 Mycobacterium tuberculosis Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000007822 coupling agent Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- GNBHRKFJIUUOQI-UHFFFAOYSA-N fluorescein Chemical compound O1C(=O)C2=CC=CC=C2C21C1=CC=C(O)C=C1OC1=CC(O)=CC=C21 GNBHRKFJIUUOQI-UHFFFAOYSA-N 0.000 description 1
- 239000007850 fluorescent dye Substances 0.000 description 1
- 230000003834 intracellular effect Effects 0.000 description 1
- 235000019421 lipase Nutrition 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61L—METHODS OR APPARATUS FOR STERILISING MATERIALS OR OBJECTS IN GENERAL; DISINFECTION, STERILISATION OR DEODORISATION OF AIR; CHEMICAL ASPECTS OF BANDAGES, DRESSINGS, ABSORBENT PADS OR SURGICAL ARTICLES; MATERIALS FOR BANDAGES, DRESSINGS, ABSORBENT PADS OR SURGICAL ARTICLES
- A61L2/00—Methods or apparatus for disinfecting or sterilising materials or objects other than foodstuffs or contact lenses; Accessories therefor
- A61L2/02—Methods or apparatus for disinfecting or sterilising materials or objects other than foodstuffs or contact lenses; Accessories therefor using physical phenomena
- A61L2/025—Ultrasonics
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Epidemiology (AREA)
- Apparatus For Disinfection Or Sterilisation (AREA)
Abstract
The present invention provides a kind of sterilizing parameter selection method and system based on artificial nerve network model, the sterilizing parameter selection method is the following steps are included: obtain sterilizing parameter sample data, sample data set is established according to the sterilizing parameter sample data, the sterilizing parameter sample data includes at least ultrasound parameter and cavitation parameter；The sample data set is trained, artificial nerve network model is established；Artificial nerve network model is verified, optimized parameter is obtained, establishes sterilizing parameter preference pattern；The relationship between optimal ultrasound parameter and cavitation parameter is determined according to the sterilizing parameter preference pattern, completes sterilizing parameter selection；The present invention is through a large number of experiments after sample data training pattern, obtained simulation result or match value, the sterilizing parameter preference pattern so established can choose the good ultrasound parameter of sterilization effect, and the relationship of ultrasonic cavitation effect and sterilization effect is analyzed according to ultrasound parameter.
Description
Technical Field
The invention relates to the field of sterilization, in particular to a sterilization parameter selection method and a sterilization parameter selection system based on an artificial neural network model.
Background
Due to the complexity of the ultrasonic sterilization process, it is difficult to establish an accurate theoretical mathematical model by using the traditional analysis method, namely, the accurate theoretical mathematical model can be established and is often an extremely complex differential equation set. Accordingly, it is not practical to establish an analytical expression of the ultrasonic effect model to select ultrasonic parameters with good sterilization effect, and the ultrasonic cavitation and the sterilization effect cannot be analyzed according to the ultrasonic parameters.
With the research and development of the artificial intelligence discipline, establishing a model of a complex object through system identification has become a common effective means. Compared with other identification methods, the modeling method based on the Artificial Neural Network (ANN) is used for carrying out parameter optimization design on the system, so that the defect of experimental research can be effectively made up, and the experimental research cost is reduced.
Disclosure of Invention
In view of the above drawbacks of the prior art, an object of the present invention is to provide a sterilization parameter selection method and system based on an artificial neural network model, for solving the problems in the prior art that it is impractical to establish an analytic expression of an ultrasonic effect model according to a differential equation set to select ultrasonic parameters with good sterilization effect and analysis of ultrasonic cavitation and sterilization effect cannot be performed according to the ultrasonic parameters.
To achieve the above and other related objects, the present invention provides a sterilization parameter selection method based on an artificial neural network model, the sterilization parameter selection method comprising the steps of:
acquiring sterilization parameter sample data, and establishing a sample data set according to the sterilization parameter sample data, wherein the sterilization parameter sample data at least comprises ultrasonic parameters and cavitation parameters;
training the sample data set, and establishing an artificial neural network model;
verifying the artificial neural network model to obtain optimal parameters, and establishing a sterilization parameter selection model;
and determining the relation between the optimal ultrasonic parameters and the cavitation parameters according to the sterilization parameter selection model to complete sterilization parameter selection.
Optionally, the ultrasound parameters at least include ultrasound intensity and irradiation time, and the cavitation parameters at least include the number of viable bacteria or the number of dead bacteria.
Optionally, the verifying the artificial neural network model includes:
selecting ultrasonic parameters for verification, and inputting the ultrasonic parameters for verification into the artificial neural network model to obtain system result parameters;
acquiring the cavitation parameters corresponding to the ultrasonic parameters for verification;
judging whether the cavitation parameters and the system result parameters meet a preset condition or not;
if so, establishing a sterilization parameter selection model according to the relation between the ultrasonic parameters and the cavitation parameters which accord with the preset conditions;
and if not, reselecting the ultrasonic parameters for verification.
Optionally, when the cavitation parameter and the system result parameter do not conform to a preset condition, the plurality of ultrasonic parameters for verification are processed by a step function or/and processed by using a residual error principle.
The invention also provides a sterilization parameter selection system based on the artificial neural network model, which comprises the following components:
the acquisition module is used for acquiring sterilization parameter sample data and establishing a sample data set according to the sterilization parameter sample data, wherein the sterilization parameter sample data at least comprises ultrasonic parameters and cavitation parameters;
the processing module is used for training the sample data set and establishing an artificial neural network model;
the verification module is used for verifying the artificial neural network model, obtaining optimal parameters and establishing a sterilization parameter selection model;
and the selection module is used for determining the relation between the optimal ultrasonic parameters and the optimal cavitation parameters according to the sterilization parameter selection model so as to complete sterilization parameter selection.
Optionally, the verification module is further configured to select an ultrasound parameter for verification, and input the ultrasound parameter for verification into the artificial neural network model to obtain a system result parameter:
acquiring the cavitation parameters corresponding to the ultrasonic parameters for verification;
judging whether the cavitation parameters and the system result parameters meet a preset condition or not;
if so, establishing a sterilization parameter selection model according to the relation between the ultrasonic parameters and the cavitation parameters which accord with the preset conditions;
and if not, reselecting the ultrasonic parameters for verification.
Optionally, when the cavitation parameter and the system result parameter do not conform to a preset condition, the verification module is further configured to process the multiple ultrasonic parameters for verification through a step function or/and process the multiple ultrasonic parameters for verification using a residual error principle.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the artificial neural network model-based sterilization parameter selection method described above.
The present invention also provides an electronic terminal, comprising: the terminal comprises a processor and a memory, wherein the memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory so as to enable the terminal to execute the artificial neural network model-based sterilization parameter selection method.
As described above, according to the sterilization parameter selection method and system based on the artificial neural network model, the actual ultrasonic parameters and sterilization result parameters are used as references to establish the artificial neural network model, and the artificial neural network is adaptively trained and adjusted according to the system result parameters corresponding to the ultrasonic parameters and the judgment results of the experiment result parameters corresponding to the ultrasonic parameters, so that reliable system parameter results can be output; according to the invention, a simulation result or a fitting value is obtained after a model is trained by a large amount of experimental sample data, the sterilization parameter selection model established in the way can select ultrasonic parameters with good sterilization effect, and the ultrasonic cavitation and the sterilization effect are analyzed according to the ultrasonic parameters.
Drawings
Fig. 1 is a flow chart of a sterilization parameter selection method based on an artificial neural network model according to the present invention.
Fig. 2 is a table showing experimental results of a sterilization parameter selection method based on an artificial neural network model according to the present invention.
Fig. 3 is a block diagram of an artificial neural network model-based sterilization parameter selection system according to the present invention.
FIG. 4 is a graph showing the comparison of experimental result parameters and system result parameters of a sterilization parameter selection method based on an artificial neural network model according to the present invention.
Description of the element reference numerals
10 acquisition module
20 processing module
30 authentication module
40 selection module
S10-S40
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than the number, shape and size of the components in practical implementation, and the type, amount and ratio of the components in practical implementation may be changed arbitrarily, and the layout of the components may be complicated.
Referring to fig. 1, the present invention provides a sterilization parameter selection method based on an artificial neural network model, which includes the following steps:
s10: acquiring sterilization parameter sample data, and establishing a sample data set according to the sterilization parameter sample data, wherein the sterilization parameter sample data at least comprises ultrasonic parameters and cavitation parameters;
s20: training the sample data set, and establishing an artificial neural network model;
s30: verifying the artificial neural network model to obtain optimal parameters, and establishing a sterilization parameter selection model;
s40: and determining the relation between the optimal ultrasonic parameters and the cavitation parameters according to the sterilization parameter selection model to complete sterilization parameter selection.
In certain embodiments, the ultrasound parameters include at least ultrasound intensity and irradiation time, and the cavitation parameters include at least a number of viable bacteria or a number of dead bacteria.
It is to be understood that the sterilization parameter selection model is a validated model of an artificial neural network that can be used for sterilization parameter selection.
In some embodiments, the plurality of ultrasound parameters and the experimental results corresponding to the ultrasound parameters are obtained from actual experiments. For example, taking Mycobacterium tuberculosis as an example, the specific steps of the experiment are as follows: adding the cultured bacterial liquid into a six-hole plate, and uniformly smearing an ultrasonic coupling agent between the plate bottom and an ultrasonic probe to eliminate air interference; the ultrasonic probe with set ultrasonic parameters is used for emitting the cavitation effect caused by the ultrasonic waves to kill bacteria, and optionally, the ultrasonic probe can be used for setting the ultrasonic parameters such as ultrasonic intensity, irradiation time and the like. Generally, after bacteria are labeled with fluorescent dyes FDA (fluorescein diacetate) and PI (Propidium Iodide), the bacteria are killed by ultrasonic irradiation, and then two fluorescence intensities in the bacteria are detected by using a flow cytometer.
It is understood that FDA enters into living cells and is decomposed by intracellular lipase to produce a polar substance capable of producing green fluorescence, i.e., fluorescein, which cannot freely penetrate living cell membranes and accumulate in the cell membranes, thus reflecting the number of living bacteria; PI cannot pass through live cell membranes but can cross broken cell membranes to stain nuclei, reflecting the number of dead bacteria. Generally, FDA is used with PI to stain both live and dead cells, and flow cytometry is used to obtain quantitative results, i.e., cavitation parameters can be rapidly detected and displayed by flow cytometry during the course of an experiment, such as the number of viable or dead bacteria.
In some embodiments, the sterilization test is performed by selecting ultrasound parameters, such as ultrasound intensity and irradiation time of the ultrasound waves, and different values of ultrasound intensity and different values of irradiation time will produce different sterilization results. For example, the irradiation time is 5min (minutes), 10min and 15min respectively with the ultrasonic intensity of 0.14W/m2 (watts per square meter), and in order to ensure the accuracy of the experimental result, each group of ultrasonic parameters is not limited to only one experiment, and of course, there are various ways to select and combine the values of the ultrasonic intensity and the irradiation time. Each group of ultrasonic parameters has a corresponding experimental result, and the survival number of bacteria or the death number of bacteria and the survival rate of bacteria can be obtained according to the experimental result, generally, different error ranges can be set according to different requirements of different experiments. Referring to FIG. 2, taking the table of FIG. 2 as an example, the survival rate of bacteria is 91.96% at 5min of irradiation time with 0.14W/m 2W/m, which is within 2.19% of the allowable error range, i.e., the survival rate of bacteria falls within 91.96 + -2.19%, and the experimental results are confirmed to be reliable. The ultrasonic parameter combination obtained through the experimental result and the experimental result parameter corresponding to the ultrasonic parameter combination are established as a standard database so as to be convenient for verifying the system result parameter in the following.
In some embodiments, the validating the artificial neural network model in step S30 includes:
selecting ultrasonic parameters for verification, and inputting the ultrasonic parameters for verification into the artificial neural network model to obtain system result parameters;
acquiring the cavitation parameters corresponding to the ultrasonic parameters for verification;
judging whether the cavitation parameters and the system result parameters meet a preset condition or not;
if so, establishing a sterilization parameter selection model according to the relation between the ultrasonic parameters and the cavitation parameters which accord with the preset conditions;
and if not, reselecting the ultrasonic parameters for verification.
It is understood that, for example, when the irradiation time is 5min (minutes) with 0.14W/m2 (watts per square meter) ultrasonic intensity, the experiment results in the survival number or death number of bacteria and the survival rate of bacteria, and the survival rate of bacteria is 91.96% when the irradiation time is 5min with 0.14W/m2 (watts per square meter) ultrasonic intensity, the error is allowed to be 2.19%, that is, the survival rate of bacteria falls within the range of 91.96 ± 2.19%, and the experiment results are considered to be reliable. In the process of establishing the artificial neural network model, the sample data set needs to be trained and the artificial neural network model needs to be verified, and ultrasonic parameters for verification need to be selected in the verification process. Taking the ultrasonic parameters of a set of experiments as an example, when the ultrasonic parameters, that is, the ultrasonic intensity is 0.14W/m2 (watts per square meter) and the irradiation time is 5min (minutes), respectively, the ultrasonic parameters for verification may be the ultrasonic intensity is 0.14W/m2 (watts per square meter) and the irradiation time is 5min (minutes), respectively, optionally, the ultrasonic parameters of the set of experiments or the interval value floating based on the ultrasonic parameters of the set of experiments may also be taken as the ultrasonic parameters for verification, such as the ultrasonic intensity of the set of experiments is 0.14W/m2(Watt per square meter), the ultrasound intensity in the input volume of the model may be 0.138-0.142W/m2Any one of (watt per square meter) values, when modeling and modeling verification are carried out, the input quantity can be accurate to a decimal point and then multiple positions are carried out, the limitation is not carried out, and the output result obtained by the value in the range can be regarded as that the ultrasonic intensity is 0.14W/m2(watts per square meter) corresponding system outcome parameters. Referring to the table of FIG. 2, the ultrasonic intensity at 0.14W/m was obtained by experiment2The survival rate of the bacteria at 5min (W/m) was 91.96%, the error was 2.19%, that is, the survival rate of the bacteria fell within 91.96 + -2.19%, and the survival rate was considered as the parameter of the experimental result. As can be appreciated, among the ultrasound parameters used for verificationThe ultrasonic intensity can be 0.138-0.142W/m2Any value in the values (watt per square meter), the irradiation time in the input quantity can be any value in 4.800-5.200 min, and the combination of any values in the two value ranges can be regarded as the system result parameter obtained by the input of the artificial neural network model, and the ultrasonic intensity can be regarded as 0.14W/m2(watts per square meter) and the irradiation time is the system result parameter corresponding to 5 min. In view of the fact that there are multiple sets of values of the ultrasonic parameters for verification, there are multiple obtained system result parameters, and therefore it is necessary to determine whether the cavitation parameters and the system result parameters meet a preset condition, in this embodiment, it is determined whether the obtained multiple system result parameters and the cavitation parameters are the same, that is, whether the system result parameters fall within the range of 91.96 ± 2.19% of the survival rate of bacteria. For example, when the survival rate of bacteria output by a system result parameter, i.e., the artificial neural network model, is 92.01%, and the system result parameter 92.01% falls within the range of 91.96 ± 2.19%, it can be determined that the cavitation parameter and the system result parameter satisfy a predetermined condition, and the survival rate of bacteria 92.01% can be determined as an optimal parameter, i.e., a sterilization parameter selection model can be established according to the relationship between the ultrasonic parameter and the cavitation parameter satisfying the predetermined condition.
It can be understood that, in the above embodiment, only one group of ultrasonic parameters and the cavitation parameters, i.e. experimental results, corresponding to the ultrasonic parameters are used as a control, and in the specific implementation manner, in the process of verifying the artificial neural network model, multiple groups of experimental results can be selected as a control and the artificial neural network model can be verified, so that the accuracy of the constructed sterilization parameter selection model is ensured.
In some embodiments, the preset condition comprises that the cavitation parameter corresponding to the ultrasound parameter is the same as the system result parameter corresponding to the ultrasound parameter; in addition, a tolerance range can be set according to actual requirements, when the system result parameter corresponding to the ultrasonic parameter falls within the tolerance range, the cavitation parameter corresponding to the ultrasonic parameter can be determined to be close to the system result parameter corresponding to the ultrasonic parameter, and at the moment, the cavitation parameter and the system result parameter can also be determined to meet a preset condition. For example, when the difference between the system result parameter corresponding to the ultrasound parameter and the experiment result parameter corresponding to the ultrasound parameter is less than 3% as the preset condition, the system result parameter and the experiment result parameter under the condition can be determined to meet the preset condition.
In certain embodiments, in step S30: verifying the artificial neural network model to obtain optimal parameters, and establishing a sterilization parameter selection model; it is understood that the optimal parameter is the system result parameter when the cavitation parameter and the system result parameter meet a preset condition in the process of verifying the artificial neural network model.
In some embodiments, when the cavitation parameter and the system result parameter do not meet a preset condition, the ultrasound parameters for verification need to be selected again, and multiple sets of ultrasound parameters for verification need to be selected to ensure the richness of sample data and the accuracy of model building. When the number of the ultrasonic parameters for verification is large, the plurality of the ultrasonic parameters for verification can be processed through a step function or/and processed by using a residual error principle.
It can be understood that the sample data set is trained to establish the artificial neural network model, and the sterilization parameter sample data at least comprises ultrasonic parameters and cavitation parameters. It is understood that the input quantities X of the artificial neural network model include the finger ultrasound intensity I and the irradiation time τ, which are expressed by the following formula:
X＝[I,τ](1)
the output Y comprises the sterilization efficiency FDA and PI, and the survival rate zeta of bacteria, wherein, FDA in the formula represents the viable bacteria number, PI represents the dead bacteria number, and is expressed by the following formula:
Y＝[FDA,PI,ζ](2)
the mapping relationship F is expressed by the following formula:
FX＝Y (3)
in some embodiments, reference to a step function results in
ΔFDA＝lFDA,IΔI+lFDA,τ(4a)
ΔPI＝lPI,IΔI+lPI,τΔτ (4b)
Δζ＝lζ,IΔI+lζ,τΔτ (4c)
Where Δ I, Δ τ is the input increment; Δ FDA, Δ PI, Δ ζ is the output increment;is the step response coefficient
Then the following results are obtained:
ΔY＝ΘΔX (5)
wherein
In some embodiments, the ultrasound parameters are processed with reference to a step function, which may be adjusted to change the number of training samples of the system. Therefore, for a plurality of continuous ultrasonic intensity values or irradiation time values, the ultrasonic parameters are processed by referring to the step function, so that the number of training samples of the system can be reduced, and the calculation amount is reduced.
In some embodiments, when the system result parameter corresponding to the ultrasound parameter and the cavitation parameter corresponding to the ultrasound parameter do not meet a preset condition, the mapping relationship of the artificial neural network model needs to be adjusted, and an appropriate amount of sterilization parameter sample data needs to be selected to train the artificial neural network model to find the mapping relationship between the ultrasound parameter and the bacterial survival rate, where the sterilization parameter sample data at least includes the ultrasound parameter and the cavitation parameter. Optionally, a step function may be introduced to process the plurality of ultrasound parameters to reduce the amount of computation, or/and a residual principle may be used to process the plurality of ultrasound parameters to optimize the number of nodes of the hidden layer of the artificial neural network model. The residual error is the difference between the actual value and the model estimated value or the fitting value, and the efficiency of finding the mapping relation of the artificial neural network model is improved by continuously trial and error searching for the algorithm with the fastest residual error reduction.
Referring to fig. 3, the present invention further provides a sterilization parameter selection system based on an artificial neural network model, including:
the acquisition module 10 is configured to acquire sterilization parameter sample data and establish a sample data set according to the sterilization parameter sample data, where the sterilization parameter sample data at least includes an ultrasonic parameter and a cavitation parameter;
the processing module 20 is configured to train the sample data set and establish an artificial neural network model;
the verification module 30 is used for verifying the artificial neural network model, obtaining optimal parameters and establishing a sterilization parameter selection model;
and the selection module 40 is used for determining the relation between the optimal ultrasonic parameters and the optimal cavitation parameters according to the sterilization parameter selection model so as to complete sterilization parameter selection.
The sterilization parameter selection system based on the artificial neural network model provided by the invention can realize the sterilization parameter selection method based on the artificial neural network model, and the corresponding specific implementation and the corresponding beneficial effects are not repeated herein.
Thus, after the artificial neural network model is built, as shown in fig. 4, fig. 4 is a comparison graph of cavitation parameters and system result parameters of the experimental result. It can be verified that the cavitation and the system result parameter are basically fitted under the condition of the same value of the ultrasonic parameter. The ultrasonic parameters are input into the sterilization parameter selection model, so that the survival number, death number and survival rate of bacteria corresponding to the ultrasonic parameters can be obtained without repeated experiments; and the relation between the ultrasonic parameters and the sterilization effect can be researched through a sterilization parameter selection model on the premise of not carrying out experiments, so that the optimal ultrasonic parameters can be screened out.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the artificial neural network model-based sterilization parameter selection method described above.
The present invention also provides an electronic terminal, comprising: a processor and a memory; the memory is used for storing computer programs, and the processor is used for executing the computer programs stored by the memory so as to enable the terminal to execute the artificial neural network model-based sterilization parameter selection method.
As described above, according to the sterilization parameter selection method and system based on the artificial neural network model, the actual ultrasonic parameters and sterilization result parameters are used as references to establish the artificial neural network model, and the artificial neural network is adaptively trained and adjusted according to the system result parameters corresponding to the ultrasonic parameters and the judgment results of the experiment result parameters corresponding to the ultrasonic parameters, so that reliable system parameter results can be output; according to the invention, after a model is trained by a large amount of experimental sample data, a simulation result or a fitting value is obtained, the artificial neural network model established in the way can select ultrasonic parameters with good sterilization effect, and the ultrasonic cavitation and the sterilization effect are analyzed according to the ultrasonic parameters.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which may be accomplished by those skilled in the art without departing from the spirit and scope of the present invention as set forth in the appended claims.
Claims (10)
1. A sterilization parameter selection method based on an artificial neural network model is characterized by comprising the following steps:
acquiring sterilization parameter sample data, and establishing a sample data set according to the sterilization parameter sample data, wherein the sterilization parameter sample data at least comprises ultrasonic parameters and cavitation parameters;
training the sample data set, and establishing an artificial neural network model;
verifying the artificial neural network model to obtain optimal parameters, and establishing a sterilization parameter selection model;
and determining the relation between the optimal ultrasonic parameters and the cavitation parameters according to the sterilization parameter selection model to complete sterilization parameter selection.
2. The artificial neural network model-based sterilization parameter selection method of claim 1, wherein:
the ultrasonic parameters at least comprise ultrasonic intensity and irradiation time;
the cavitation parameters include at least a number of viable bacteria or a number of dead bacteria.
3. The method of claim 1, wherein validating the artificial neural network model comprises:
selecting ultrasonic parameters for verification, and inputting the ultrasonic parameters for verification into the artificial neural network model to obtain system result parameters;
acquiring the cavitation parameters corresponding to the ultrasonic parameters for verification;
judging whether the cavitation parameters and the system result parameters meet a preset condition or not;
if so, establishing a sterilization parameter selection model according to the relation between the ultrasonic parameters and the cavitation parameters which accord with the preset conditions;
and if not, reselecting the ultrasonic parameters for verification.
4. The artificial neural network model-based sterilization parameter selection method of claim 3, comprising:
and when the cavitation parameters and the system result parameters do not accord with a preset condition, processing the ultrasonic parameters for verification through a step function or/and processing the ultrasonic parameters for verification by using a residual error principle.
5. A sterilization parameter selection system based on an artificial neural network model, comprising:
the acquisition module is used for acquiring sterilization parameter sample data and establishing a sample data set according to the sterilization parameter sample data, wherein the sterilization parameter sample data at least comprises ultrasonic parameters and cavitation parameters;
the processing module is used for training the sample data set and establishing an artificial neural network model;
the verification module is used for verifying the artificial neural network model, obtaining optimal parameters and establishing a sterilization parameter selection model;
and the selection module is used for determining the relation between the optimal ultrasonic parameters and the optimal cavitation parameters according to the sterilization parameter selection model so as to complete sterilization parameter selection.
6. The artificial neural network model-based sterilization parameter selection system of claim 5, wherein:
the ultrasonic parameters at least comprise ultrasonic intensity and irradiation time;
the cavitation parameters include at least a number of viable bacteria or a number of dead bacteria.
7. The artificial neural network model-based sterilization parameter selection system of claim 5, wherein the verification module is further configured to select ultrasound parameters for verification and input the ultrasound parameters for verification into the artificial neural network model, resulting in system result parameters:
acquiring the cavitation parameters corresponding to the ultrasonic parameters for verification;
judging whether the cavitation parameters and the system result parameters meet a preset condition or not;
if so, establishing a sterilization parameter selection model according to the relation between the ultrasonic parameters and the cavitation parameters which accord with the preset conditions;
and if not, reselecting the ultrasonic parameters for verification.
8. The artificial neural network model-based sterilization parameter selection system according to claim 7, wherein the verification module is further configured to process the plurality of ultrasound parameters for verification by a step function or/and process the plurality of ultrasound parameters for verification by using a residual error principle when the cavitation parameter and the system result parameter do not meet a preset condition.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method for artificial neural network model-based sterilization parameter selection of any one of claims 1 to 4.
10. An electronic terminal, comprising: a processor and a memory;
the memory is configured to store a computer program, and the processor is configured to execute the computer program stored by the memory to cause the terminal to perform the method for selecting sterilization parameters based on an artificial neural network model according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910439792.5A CN110175397B (en) | 2019-05-24 | 2019-05-24 | Sterilization parameter selection method and system based on artificial neural network model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910439792.5A CN110175397B (en) | 2019-05-24 | 2019-05-24 | Sterilization parameter selection method and system based on artificial neural network model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110175397A true CN110175397A (en) | 2019-08-27 |
| CN110175397B CN110175397B (en) | 2023-08-11 |
Family
ID=67692082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910439792.5A Active CN110175397B (en) | 2019-05-24 | 2019-05-24 | Sterilization parameter selection method and system based on artificial neural network model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110175397B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112869775A (en) * | 2019-11-29 | 2021-06-01 | 无锡祥生医疗科技股份有限公司 | Cavitation processing method, storage medium and ultrasonic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354611A (en) * | 2015-10-08 | 2016-02-24 | 程涛 | Artificial neural network based best quality image scanning method and system |
| CN105929683A (en) * | 2016-06-23 | 2016-09-07 | 东南大学 | Differential adjustable PID controller parameter project adjusting method |
| CN109527060A (en) * | 2018-11-16 | 2019-03-29 | 黑龙江省科学院技术物理研究所 | Preservative free sausage irradiation fresh-keeping method |
-
2019
- 2019-05-24 CN CN201910439792.5A patent/CN110175397B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354611A (en) * | 2015-10-08 | 2016-02-24 | 程涛 | Artificial neural network based best quality image scanning method and system |
| CN105929683A (en) * | 2016-06-23 | 2016-09-07 | 东南大学 | Differential adjustable PID controller parameter project adjusting method |
| CN109527060A (en) * | 2018-11-16 | 2019-03-29 | 黑龙江省科学院技术物理研究所 | Preservative free sausage irradiation fresh-keeping method |
Non-Patent Citations (5)
| Title |
|---|
| HAO YU等: "Cell experimental studies on sonoporation: State of the art and", 《JOURNAL OF CONTROLLED RELEASE》 * |
| 王会荣等: "2,4-二氨基-6-甲基-7-取代苄氨基喹唑啉定量结构活性关系研究", 《运城学院学报》 * |
| 王标诗等: "BP网络对凝结芽孢杆菌芽孢热压协同灭活条件的优化", 《食品科学》 * |
| 苏杭等: "低频低强度超声对耻垢分枝杆菌细胞壁通透性影响的实验研究", 《中国超声医学杂志》 * |
| 郑慧敏等: "低频低强度超声介导质粒转入大肠杆菌的实验研究", 《中国超声医学杂志》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112869775A (en) * | 2019-11-29 | 2021-06-01 | 无锡祥生医疗科技股份有限公司 | Cavitation processing method, storage medium and ultrasonic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110175397B (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107315884B (en) | Building energy consumption modeling method based on linear regression | |
| CN106446942A (en) | Crop disease identification method based on incremental learning | |
| Triantis et al. | Island biogeography is not a single‐variable discipline: the small island effect debate | |
| CN108229490A (en) | Critical point detection method, neural network training method, device and electronic equipment | |
| CN106485316A (en) | Neural network model compression method and device | |
| CN107122375A (en) | The recognition methods of image subject based on characteristics of image | |
| CN109034204B (en) | Weld defect identification method based on improved convolutional neural network | |
| CN106095812A (en) | Intelligent test paper generation method based on similarity measurement | |
| CN108805176A (en) | A kind of fish meal feeding volume prediction technique returned based on random forest | |
| CN109191434A (en) | Image detecting system and detection method in a kind of cell differentiation | |
| CN104156628B (en) | A kind of naval vessel radiation signal recognition methods based on Multiple Kernel Learning discriminant analysis | |
| Albani et al. | Source characterization of airborne pollutant emissions by hybrid metaheuristic/gradient-based optimization techniques | |
| CN103077408A (en) | Method for converting seabed sonar image into acoustic substrate classification based on wavelet neutral network | |
| CN111047073B (en) | Aquaculture water quality prediction method and system based on neural network | |
| CN104732534B (en) | Well-marked target takes method and system in a kind of image | |
| Meroz | Plant tropisms as a window on plant computational processes | |
| CN110175397A (en) | A kind of sterilizing parameter selection method and system based on artificial nerve network model | |
| CN110321936A (en) | A method of realizing that picture two is classified based on VGG16 and SVM | |
| CN111401444B (en) | Method and device for predicting red wine origin, computer equipment and storage medium | |
| CN117607120A (en) | Food additive Raman spectrum detection method and device based on improved Resnext model | |
| CN116883364A (en) | Apple leaf disease identification method based on CNN and Transformer | |
| CN108845075B (en) | Compost maturity real-time prediction method based on deep learning network | |
| CN111738410B (en) | Beef individual growth curve acquisition method, device and storage medium | |
| CN115546157A (en) | Method, device and storage medium for evaluating radiation quality of satellite image | |
| Xiao et al. | Broiler growth performance analysis: from correlation analysis, multiple linear regression, to neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |