CN116870211A - Plasma sterilization and disinfection system and intelligent disinfection cabinet - Google Patents

Plasma sterilization and disinfection system and intelligent disinfection cabinet Download PDF

Info

Publication number
CN116870211A
CN116870211A CN202310855562.3A CN202310855562A CN116870211A CN 116870211 A CN116870211 A CN 116870211A CN 202310855562 A CN202310855562 A CN 202310855562A CN 116870211 A CN116870211 A CN 116870211A
Authority
CN
China
Prior art keywords
disinfection
plasma
data
module
modeling
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
Application number
CN202310855562.3A
Other languages
Chinese (zh)
Other versions
CN116870211B (en
Inventor
谢正中
谢正福
谢国大
杨真
陈晨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Haizhikang Medical Technology Co ltd
Original Assignee
Guangzhou Haizhikang Medical Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Haizhikang Medical Technology Co ltd filed Critical Guangzhou Haizhikang Medical Technology Co ltd
Priority to CN202310855562.3A priority Critical patent/CN116870211B/en
Publication of CN116870211A publication Critical patent/CN116870211A/en
Application granted granted Critical
Publication of CN116870211B publication Critical patent/CN116870211B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61LMETHODS 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
    • A61L2/00Methods or apparatus for disinfecting or sterilising materials or objects other than foodstuffs or contact lenses; Accessories therefor
    • A61L2/02Methods or apparatus for disinfecting or sterilising materials or objects other than foodstuffs or contact lenses; Accessories therefor using physical phenomena
    • A61L2/14Plasma, i.e. ionised gases
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61LMETHODS 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
    • A61L2/00Methods or apparatus for disinfecting or sterilising materials or objects other than foodstuffs or contact lenses; Accessories therefor
    • A61L2/24Apparatus using programmed or automatic operation
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61LMETHODS 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
    • A61L2/00Methods or apparatus for disinfecting or sterilising materials or objects other than foodstuffs or contact lenses; Accessories therefor
    • A61L2/26Accessories or devices or components used for biocidal treatment
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/044Recurrent networks, e.g. Hopfield networks
    • G06N3/0442Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/0499Feedforward networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61LMETHODS 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
    • A61L2202/00Aspects relating to methods or apparatus for disinfecting or sterilising materials or objects
    • A61L2202/10Apparatus features
    • A61L2202/11Apparatus for generating biocidal substances, e.g. vaporisers, UV lamps
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61LMETHODS 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
    • A61L2202/00Aspects relating to methods or apparatus for disinfecting or sterilising materials or objects
    • A61L2202/10Apparatus features
    • A61L2202/14Means for controlling sterilisation processes, data processing, presentation and storage means, e.g. sensors, controllers, programs

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Epidemiology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Plasma & Fusion (AREA)
  • Apparatus For Disinfection Or Sterilisation (AREA)

Abstract

The application provides a plasma sterilization and disinfection system and an intelligent disinfection cabinet, and relates to the technical field of intelligent control. The system comprises: the multiple modeling module is used for obtaining modeling parameters based on the plasma sterilization and disinfection data; the modeling parameter substitution module is used for substituting the modeling parameters into the prediction model; the model training module is used for determining an optimal prediction model; the space matching module is used for determining the installation position of the first plasma generator; the bacteria prediction module is used for inputting the detection result into the optimal prediction model to obtain a bacteria prediction result; the control command generation module is used for generating a control command; the control command execution module is used for converting direct current high voltage generated by the high-voltage power supply based on the control command and transmitting the converted direct current high voltage to the second plasma generator. The aim of controlling the plasma generators at corresponding positions to release plasma in a targeted manner according to the actual condition of the bacterial content of the current disinfection space is fulfilled, so that the disinfection effect of the large-volume space is effectively ensured.

Description

Plasma sterilization and disinfection system and intelligent disinfection cabinet
Technical Field
The application relates to the technical field of intelligent control, in particular to a plasma sterilization and disinfection system and an intelligent disinfection cabinet.
Background
At present, the sterilizing cabinet generally adopts ultraviolet rays, high temperature, ozone and other modes for sterilization and disinfection. Wherein, the ultraviolet sterilization range is limited and the sterilization is not thorough. And high-temperature sterilization energy consumption is high, and some plastic kitchen ware which is not resistant to high temperature cannot be sterilized at high temperature. In addition, ozone has a remarkable sterilizing effect, but has strong pungent odor and certain toxicity. Excessive ozone can strongly stimulate the respiratory tract of people, cause symptoms such as sore throat, chest distress, cough and the like, and possibly cause bronchitis and emphysema. Therefore, the conventional disinfection and sterilization mode has great limitation, and is difficult to cope with the current sterilization requirements.
Aiming at the defects of the traditional disinfection and sterilization mode, the plasma sterilization mode is currently applied in the fields of medical use and the like, and the plasma kills the cell nucleuses by damaging the bacterial envelopes, so that the sterilization and sterilization effect is extremely strong and the action time is short. However, in the existing plasma sterilization and disinfection technology, the plasma cannot be uniformly generated in the large-volume space, so that the plasma cannot be uniformly distributed in the large-volume sterilization space, and the disinfection effect inside the large-volume disinfection device is further affected. The bacteria propagation speed is generally high, and the actual situation of the bacteria content in the current disinfection space cannot be considered in the prior art, so that the plasmas are released in a targeted manner, and the disinfection effect of the large-volume space is further affected.
Disclosure of Invention
In order to solve the above problems, an embodiment of the present disclosure provides a plasma sterilization and disinfection system, including a multiple modeling module, configured to perform multiple modeling by using PLS algorithm based on screened and classified plasma sterilization and disinfection data, to obtain modeling parameters; the modeling parameter substitution module is used for substituting the modeling parameter into a prediction model, and the prediction model comprises a BP neural network model and an LSTM neural network model; the model training module is used for respectively training the BP neural network model and the LSTM neural network model by taking the preprocessed plasma sterilization and disinfection data as training samples, and determining an optimal prediction model from the trained BP neural network model and the trained LSTM neural network model based on a preset model evaluation index; the space matching module is used for acquiring volume data and space types of a target disinfection space, inputting the volume data and the space types into a preset database for matching, and determining the installation position of each first plasma generator; the bacteria prediction module is used for sampling air in the target disinfection space in real time, detecting the air sampled in real time according to a preset time interval to obtain a detection result, and inputting the detection result into the optimal prediction model to obtain a bacteria prediction result; a control command generation module for determining the second plasma generator based on the bacteria prediction result and the installation position of each first plasma generator, and generating a control command at the same time; and the control command execution module is used for converting direct current high voltage generated by the high-voltage power supply based on the control command and transmitting the converted direct current high voltage to the second plasma generator so as to enable the second plasma generator to generate plasma.
In some embodiments, the plasma sterilization/disinfection system further comprises: the pretreatment module is used for acquiring a plurality of plasma sterilization and disinfection data and carrying out pretreatment on the plurality of plasma sterilization and disinfection data; and the screening and classifying module is used for screening and classifying the pretreated plasma sterilization and disinfection data through correlation analysis.
In some embodiments, the preprocessing module includes: the missing value screening unit is used for screening the missing value of the plasma sterilization and disinfection data and determining the missing value; the abnormal value removing unit is used for determining abnormal values according to preset plasma sterilization and disinfection indexes after filling the missing values by adopting a random forest method, and removing the abnormal values; and the abnormal value filling unit is used for filling the removed abnormal values by using a random forest method to obtain the preprocessed plasma sterilization and disinfection data.
In some embodiments, the screening classification module includes: the normal analysis unit is used for carrying out normal analysis on the pretreated plasma sterilization and disinfection data, wherein if the pretreated plasma sterilization and disinfection data accords with normal distribution, the correlation analysis is Pelson correlation analysis, and if the pretreated plasma sterilization and disinfection data does not accord with normal distribution, the correlation analysis is Szerland correlation analysis.
In some embodiments, the multiple modeling module includes: the first modeling fitting data obtaining unit is used for modeling the screened and classified plasma sterilization and disinfection data by utilizing a PLS algorithm to obtain first modeling fitting data; the comparison unit is used for comparing the first modeling fitting data with corresponding plasma sterilization and disinfection data to obtain a comparison result; the second modeling fitting data obtaining unit is used for screening the first modeling fitting data based on the comparison result to obtain second modeling fitting data; and the modeling parameter obtaining unit is used for modeling the second modeling fitting data by utilizing the PLS algorithm to obtain modeling parameters.
In some embodiments, the plasma sterilization/disinfection system further comprises: the virtual space model construction module is used for constructing a corresponding virtual space model according to the volume data and the space types of each test disinfection space; the virtual generator construction module is used for constructing a virtual generator according to the disinfection and sterilization range data of the preset plasma generator; the virtual generator layout module is used for laying at least one virtual generator in a corresponding virtual space model aiming at any test disinfection space, and adjusting the layout number of the virtual generators and the positions of each virtual generator according to the disinfection and sterilization range data so as to obtain a plasma generator installation scheme corresponding to the test disinfection space; and the scheme binding module is used for binding the volume data, the space types and the corresponding plasma generator installation schemes of each test disinfection space and then storing the volume data, the space types and the corresponding plasma generator installation schemes into a preset database.
In some embodiments, the control command execution module includes: and the direct current high voltage conversion unit is used for converting direct current high voltage generated by the high voltage power supply into high voltage pulses through the pulse generator and transmitting the high voltage pulses to the second plasma generator through the pulse generator.
In some embodiments, the calculation formula of the hidden layer node number of the BP neural network model is as followsWherein h is the number of hidden layer nodes, m is the number of input layer nodes, n is the number of output layer nodes, a is an adjustment constant, and a is more than or equal to 1 and less than or equal to 10.
In some embodiments, the output values of the BP neural network modelThe calculation formula of (2) isWherein->Representing the activation value of the layer i neuron,representing the neurons of layer l-1 connected to layer i neurons,/>Representing each +.>Corresponding weights, ++>Is the offset, where n=1, 2,3.
The embodiment of the specification also provides an intelligent disinfection cabinet, which comprises a cabinet body and a side cover plate which are connected with each other, and the intelligent disinfection cabinet also comprises the plasma disinfection system.
The plasma sterilization and disinfection system and the intelligent disinfection cabinet are used for modeling for multiple times by utilizing a PLS algorithm based on the screened and classified plasma sterilization and disinfection data to obtain modeling parameters. Substituting modeling parameters into the BP neural network model and the LSTM neural network model, and respectively training the BP neural network model and the LSTM neural network model by utilizing the preprocessed plasma sterilization and disinfection data so as to determine an optimal prediction model from the trained BP neural network model and the trained LSTM neural network model. When the plasma sterilization and disinfection process is carried out, firstly, the volume data and the space type of the target sterilization space are input into a preset database for matching, so that the plasma generator installation scheme matched with the volume data and the space type of the target sterilization space is determined, and therefore the installation position of each first plasma generator is determined according to the corresponding plasma generator installation scheme. And then detecting the air sampled in real time in the target disinfection space according to a preset time interval to obtain a detection result. And analyzing the detection result by using the optimal prediction model to determine a bacteria prediction result of the current target disinfection space (the bacteria prediction result comprises the bacteria content of the current target disinfection space and the bacteria content after a preset time determined according to the propagation speed of bacteria). The aim of obtaining the actual condition of the bacterial content of the current target disinfection space is achieved. And then, according to the bacteria prediction result and the installation position of each first plasma generator, a control command is sent out so that direct current high voltage generated by the high-voltage power supply is converted and then transmitted to the second plasma generator, and further, the second plasma generator generates plasma for sterilization. Therefore, the aim of controlling the plasma generators at corresponding positions to release plasma in a targeted manner according to the actual condition of the bacterial content in the current disinfection space so as to effectively ensure the disinfection effect of the large-volume space is fulfilled.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a plasma sterilization and disinfection system according to some embodiments of the present disclosure;
FIG. 2 is a schematic illustration of a sterilization process of a plasma sterilization and disinfection system according to some embodiments of the present disclosure;
fig. 3 is a schematic structural view of an intelligent sterilizer according to some embodiments of the present disclosure;
FIG. 4 is a schematic block diagram of an electronic device, shown in accordance with some embodiments of the present description;
FIG. 5 is a block diagram of another plasma sterilization and disinfection system according to some embodiments of the present disclosure;
FIG. 6 is a block diagram illustrating a preprocessing module according to some embodiments of the present disclosure;
FIG. 7 is a block diagram of a multiple modeling module shown in accordance with some embodiments of the present description;
fig. 8 is a block diagram of yet another plasma sterilization and disinfection system according to some embodiments of the present disclosure.
Icon: 110-multiple modeling module; 120-substituting modeling parameters into a module; 130-a model training module; 140-a space matching module; 150-a bacteria prediction module; 160-a control command generation module; 170-a control command execution module; 101-memory; 102-a processor; 103-a communication interface; 2-a cabinet body; 3-side cover plate.
Detailed Description
In order that those skilled in the art will better understand the present application, a detailed description of embodiments of the present application will be provided below, together with the accompanying drawings, wherein it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
Referring to fig. 1 and 2, fig. 1 is a block diagram illustrating a plasma sterilization and disinfection system according to some embodiments of the present disclosure, and fig. 2 is a schematic diagram illustrating a sterilization process of a plasma sterilization and disinfection system according to some embodiments of the present disclosure. The embodiment of the application provides a plasma sterilization and disinfection system, which comprises a multi-time modeling module 110, a modeling parameter substitution module 120, a model training module 130, a space matching module 140, a bacteria prediction module 150, a control command generation module 160 and a control command execution module 170;
the multiple modeling module 110 is configured to perform multiple modeling by using a PLS algorithm based on the screened and classified plasma sterilization and disinfection data, so as to obtain modeling parameters;
referring to fig. 5, fig. 5 is a block diagram illustrating another plasma sterilization and disinfection system according to some embodiments of the present disclosure. In some embodiments, the plasma sterilization system further comprises a pretreatment module and a screening classification module. The pretreatment module is used for acquiring a plurality of plasma sterilization and disinfection data and carrying out pretreatment on the plurality of plasma sterilization and disinfection data. And the screening and classifying module is used for screening and classifying the pretreated plasma sterilization and disinfection data through correlation analysis.
In some embodiments, the plasma sterilization and disinfection data can comprise process data (such as equipment internal temperature data, bacteria content of a disinfection space, sterilization time, disinfection space volume and the like) generated in the actual application process of various plasma sterilization and disinfection equipment and network data (such as technical parameters of a plasma sterilizer, disinfection experiment data of the plasma sterilizer and the like) obtained through network inquiry.
Referring to fig. 6, fig. 6 is a block diagram illustrating a preprocessing module according to some embodiments of the present disclosure. In some embodiments, the preprocessing module includes a missing value screening unit, an outlier rejection unit, and an outlier shim unit. The missing value screening unit is used for screening the missing value of the plasma sterilization and disinfection data and determining the missing value. And the abnormal value removing unit is used for determining abnormal values according to preset plasma sterilization and disinfection indexes after filling the missing values by adopting a random forest method and removing the abnormal values. And the abnormal value filling unit is used for filling the removed abnormal values by using a random forest method to obtain the preprocessed plasma sterilization and disinfection data.
In some embodiments, there will typically be missing values in the acquired plasma sterilization/disinfection data, for example, one or more of the internal temperature data of the apparatus, the bacteria content of the sterilization space, the sterilization time and the volume of the sterilization space may be missing from the process data generated during the actual application of the various plasma sterilization/disinfection apparatuses.
In some embodiments, firstly filling the selected missing values by adopting a random forest method, wherein the plasma sterilization and disinfection data filled with the missing values are regarded as complete data, but because the filled missing values possibly do not accord with the actual condition of the plasma sterilization and disinfection process, the abnormal values in the plasma sterilization and disinfection data filled with the missing values are determined based on the preset plasma sterilization and disinfection indexes, and then the abnormal values are removed, and then the random forest is filled with the removed abnormal values, so that the pretreatment of the plasma sterilization and disinfection data is completed, the integrity of the plasma sterilization and disinfection data after pretreatment is ensured, and the plasma sterilization and disinfection data after pretreatment accords with the preset plasma sterilization and disinfection indexes, and the reliability of the plasma sterilization and disinfection data after pretreatment is ensured.
In some embodiments, the screening classification module includes a normalization analysis unit. The normal analysis unit is used for carrying out normal analysis on the pretreated plasma sterilization and disinfection data, wherein if the pretreated plasma sterilization and disinfection data accords with normal distribution, the correlation analysis is Pelson correlation analysis, and if the pretreated plasma sterilization and disinfection data does not accord with normal distribution, the correlation analysis is Szerland correlation analysis.
In some embodiments, the pre-processed plasma sterilization data is subjected to a normalization analysis prior to the correlation analysis. If the normal distribution is met, the Peltern grand correlation analysis is selected. If the normal distribution is not met, the Spekerman correlation analysis is selected.
Referring to fig. 7, fig. 7 is a block diagram illustrating a multiple modeling module according to some embodiments of the present disclosure. In some embodiments, the multiple modeling module 110 includes a first modeling fit data obtaining unit, a comparison unit, a second modeling fit data obtaining unit, and a modeling parameter obtaining unit. The first modeling fitting data obtaining unit is used for modeling the screened and classified plasma sterilization and disinfection data by using a PLS algorithm to obtain first modeling fitting data. And the comparison unit is used for comparing the first modeling fitting data with corresponding plasma sterilization and disinfection data to obtain a comparison result. The second modeling fitting data obtaining unit is used for screening the first modeling fitting data based on the comparison result to obtain second modeling fitting data. And the modeling parameter obtaining unit is used for modeling the second modeling fitting data by utilizing the PLS algorithm to obtain modeling parameters.
In some embodiments, the PLS algorithm is a partial least squares method, which has the following advantages: (1) Regression modeling can be performed under the condition that independent variables have serious multiple correlations; (2) Allowing regression modeling under the condition that the number of sample points is less than the number of variables; (3) Partial least squares regression will contain all original independent variables in the final model; (4) The partial least squares regression model is easier to identify system information and noise (even some non-random noise); (5) In the partial least squares regression model, the regression coefficients for each independent variable will be easier to interpret. Then regression modeling of multiple parameters with correlation can be performed using PLS algorithm.
In some embodiments, the screened categorized plasma sterilization data has a correlation. And modeling the screened and classified plasma sterilization and disinfection data by using a PLS algorithm to obtain first modeling fitting data. And then comparing the difference between the first modeling fitting data and the corresponding plasma sterilization and disinfection data, and screening out the first modeling fitting data with the difference smaller than the preset difference as second modeling fitting data. And modeling the second modeling fitting data again by using the PLS algorithm to obtain modeling parameters.
The modeling parameter substitution module 120 is configured to substitute the modeling parameter into a prediction model, where the prediction model includes a BP neural network model and an LSTM neural network model;
in some embodiments, the predictive model includes a BP neural network and a Long Short-Term Memory neural network (LSTM). The BP neural network is a multi-layer feedforward neural network and consists of an input layer, an hidden layer and an output layer. A3-layer BP neural network model can be highly fitted to any function, and can learn the nonlinear relationship between plasma sterilization and disinfection data. The LSTM model is a neural network which is improved on the basis of a cyclic neural network, and overcomes the defect that RNNs cannot process long-sequence data. LSTM neural networks control the transmission of information by incorporating memory gates, learning gates, forget gates.
The BP neural network comprises two processes of forward propagation of signals and backward propagation of errors. That is, the calculation of the error output is performed in the direction from the input to the output, and the adjustment of the weight and the threshold value is performed in the direction from the output to the input. In BP neural network, the number of nodes of input layer and output layer are determined, and the calculation formula of the number of nodes of hidden layer isWherein h is the number of hidden layer nodes, m is the number of input layer nodes, n is the number of output layer nodes, and a is an adjustment constant between 1 and 10.
In the forward propagation of the signal, the output valueThe calculation formula of (2) isWherein->Representing the activation value of the layer i neuron,(wherein n=1, 2, 3.) represents a neuron of layer l-1 connected to a neuron of layer i, +.>(wherein n=1, 2, 3.) means each +.>(wherein n=1, 2, 3.) corresponding weights,/-for example>Is the offset. Output value->The calculation formula of (1) can be understood as the activation value of the layer i neuron +.>Equal to +.about.every neuron connected to the previous layer>(wherein n=1, 2, 3.) times a weight +.>(where n=1, 2, 3.) then the products add, plus an offsetQuantity->The resulting value is output at layer l via function f. Wherein the function f can be a sigmod function, then +.>Then
In the back propagation of errors, the specific steps are as follows: (1) Calculating the state and activation values for each layer until the last layer (i.e., the signal is forward propagating); (2) The error of each layer is calculated, and the calculation process of the error is advanced from the last layer. (3) And updating parameters according to the calculation result of the error so as to reduce the error. Iterating steps (1) to (3) until a stopping criterion is met (e.g. the difference in the errors of two adjacent iterations reaches a preset difference).
The model training module 130 is configured to train the BP neural network model and the LSTM neural network model respectively using the preprocessed plurality of plasma sterilization and disinfection data as training samples, and determine an optimal prediction model from the trained BP neural network model and the trained LSTM neural network model based on a preset model evaluation index;
in some embodiments, the predetermined model evaluation index may include a root mean square error RMSE and a determination coefficient R 2 . In some embodiments, the coefficient R is determined from the root mean square error RMSE and the coefficient R of the two neural network models 2 Numerical value, model screening is carried out in a trained BP neural network model and a trained LSTM neural network model, R 2 And the higher the RMSE value, the higher the model goodness of fit. Thereby screening out the optimal prediction model.
The space matching module 140 is used for acquiring volume data and space types of the target disinfection space, inputting the volume data and the space types into a preset database for matching, and determining the installation position of each first plasma generator;
in some embodiments, the preset database contains a rich volume of sterilization space, space type, and corresponding plasma generator installation scheme.
In some embodiments, the volume data and the space type of the target sterilization space are input into a preset database to be matched, and a plasma generator installation scheme matched with the volume data and the space type of the target sterilization space can be determined, so that the installation position of each first plasma generator (the first plasma generator represents the plasma generator installed in the target sterilization space) is determined according to the corresponding plasma generator installation scheme.
The bacteria prediction module 150 is configured to sample air in the target disinfection space in real time, detect the air sampled in real time according to a preset time interval to obtain a detection result, and input the detection result into an optimal prediction model to obtain a bacteria prediction result;
in some embodiments, the predetermined time interval may be 10 seconds.
In some embodiments, the detection result may be obtained by detecting air sampled in real time through an air quality monitoring device (such as an air quality monitor). And then analyzing the detection result by using the optimal prediction model to determine a bacteria prediction result of the current target disinfection space (the bacteria prediction result comprises the bacteria content of the current target disinfection space and the bacteria content after a preset time determined according to the propagation speed of bacteria). The aim of obtaining the actual condition of the bacterial content of the current target disinfection space is achieved.
A control command generation module 160 for determining the second plasma generator based on the bacteria prediction result and the installation position of each first plasma generator, and generating a control command at the same time;
the control command execution module 170 is configured to convert the dc high voltage generated by the high voltage power supply based on the control command and transmit the converted dc high voltage to the second plasma generator, so that the second plasma generator generates plasma.
In some embodiments, the control command execution module 170 includes a dc high voltage conversion unit. And the direct current high voltage conversion unit is used for converting direct current high voltage generated by the high voltage power supply into high voltage pulses through the pulse generator and transmitting the high voltage pulses to the second plasma generator through the pulse generator.
In the implementation process, the system performs multiple modeling by using a PLS algorithm based on the screened and classified plasma sterilization and disinfection data to obtain modeling parameters. Substituting modeling parameters into the BP neural network model and the LSTM neural network model, and respectively training the BP neural network model and the LSTM neural network model by utilizing the preprocessed plasma sterilization and disinfection data so as to determine an optimal prediction model from the trained BP neural network model and the trained LSTM neural network model. When the plasma sterilization and disinfection process is carried out, firstly, the volume data and the space type of the target sterilization space are input into a preset database for matching, so that the plasma generator installation scheme matched with the volume data and the space type of the target sterilization space is determined, and therefore the installation position of each first plasma generator is determined according to the corresponding plasma generator installation scheme. And then detecting the air sampled in real time in the target disinfection space according to a preset time interval to obtain a detection result. And analyzing the detection result by using the optimal prediction model to determine a bacteria prediction result of the current target disinfection space (the bacteria prediction result comprises the bacteria content of the current target disinfection space and the bacteria content after a preset time determined according to the propagation speed of bacteria). The aim of obtaining the actual condition of the bacterial content of the current target disinfection space is achieved. And then, according to the bacteria prediction result and the installation position of each first plasma generator, a control command is sent out so that direct current high voltage generated by the high-voltage power supply is converted and then transmitted to the second plasma generator, and further, the second plasma generator generates plasma for sterilization. Therefore, the aim of controlling the plasma generators at corresponding positions to release plasma in a targeted manner according to the actual condition of the bacterial content in the current disinfection space so as to effectively ensure the disinfection effect of the large-volume space is fulfilled.
Referring to fig. 8, fig. 8 is a block diagram illustrating a further plasma sterilization and disinfection system according to some embodiments of the present disclosure. In some embodiments, the plasma sterilization/disinfection system further comprises:
the virtual space model construction module is used for constructing a corresponding virtual space model according to the volume data and the space types of each test disinfection space;
the virtual generator construction module is used for constructing a virtual generator according to the disinfection and sterilization range data of the preset plasma generator;
the virtual generator layout module is used for laying at least one virtual generator in a corresponding virtual space model aiming at any test disinfection space, and adjusting the layout number of the virtual generators and the positions of each virtual generator according to the disinfection and sterilization range data so as to obtain a plasma generator installation scheme corresponding to the test disinfection space;
and the scheme binding module is used for binding the volume data, the space types and the corresponding plasma generator installation schemes of each test disinfection space and then storing the volume data, the space types and the corresponding plasma generator installation schemes into a preset database. Thereby realizing the purposes that the preset database contains abundant volume data of the disinfection space, space types and corresponding plasma generator installation schemes.
Referring to fig. 4, fig. 4 is a schematic block diagram of an electronic device according to an embodiment of the application. The electronic device comprises a memory 101, a processor 102 and a communication interface 103, wherein the memory 101, the processor 102 and the communication interface 103 are electrically connected with each other directly or indirectly to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules, such as program instructions/modules corresponding to a plasma sterilization and disinfection system provided in an embodiment of the present application, and the processor 102 executes the software programs and modules stored in the memory 101, thereby performing various functional applications and data processing. The communication interface 103 may be used for communication of signaling or data with other node devices.
In some embodiments, memory 101 may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), and the like.
The processor 102 may be an integrated circuit chip with signal processing capabilities. The processor 102 may be a general purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
It will be appreciated that the configuration shown in fig. 4 is merely illustrative, and that the electronic device may also include more or fewer components than shown in fig. 4, or have a different configuration than shown in fig. 4. The components shown in fig. 4 may be implemented in hardware, software, or a combination thereof.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an intelligent disinfection cabinet according to some embodiments of the present disclosure. The embodiment of the application provides an intelligent disinfection cabinet, which comprises a cabinet body 2 and a side cover plate 3 which are connected with each other, and the intelligent disinfection cabinet also comprises the electronic equipment.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, of the flowcharts and block diagrams in the figures that illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application 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 application. 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.
Finally, it should be noted that: the embodiment of the application is disclosed only as a preferred embodiment of the application, and is only used for illustrating the technical scheme of the application, but not limiting the technical scheme; although the application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims (10)

1. A plasma sterilization and disinfection system, comprising:
the multiple modeling module is used for performing multiple modeling by utilizing a PLS algorithm based on the screened and classified plasma sterilization and disinfection data to obtain modeling parameters;
the modeling parameter substitution module is used for substituting the modeling parameter into a prediction model, wherein the prediction model comprises a BP neural network model and an LSTM neural network model;
the model training module is used for respectively training the BP neural network model and the LSTM neural network model by taking the preprocessed plasma sterilization and disinfection data as training samples, and determining an optimal prediction model from the trained BP neural network model and the trained LSTM neural network model based on a preset model evaluation index;
the space matching module is used for acquiring volume data and space types of a target disinfection space, inputting the volume data and the space types into a preset database for matching, and determining the installation position of each first plasma generator;
the bacteria prediction module is used for sampling air in the target disinfection space in real time, detecting the air sampled in real time according to a preset time interval to obtain a detection result, and inputting the detection result into the optimal prediction model to obtain a bacteria prediction result;
a control command generation module for determining the second plasma generator based on the bacteria prediction result and the installation position of each first plasma generator, and generating a control command at the same time;
and the control command execution module is used for converting direct current high voltage generated by the high-voltage power supply based on the control command and transmitting the converted direct current high voltage to the second plasma generator so as to enable the second plasma generator to generate plasma.
2. The plasma sterilization system as recited in claim 1, further comprising:
the pretreatment module is used for acquiring a plurality of plasma sterilization and disinfection data and carrying out pretreatment on the plurality of plasma sterilization and disinfection data;
and the screening and classifying module is used for screening and classifying the pretreated plasma sterilization and disinfection data through correlation analysis.
3. The plasma sterilization system of claim 2, wherein the pretreatment module comprises:
the missing value screening unit is used for screening the missing value of the plasma sterilization and disinfection data and determining the missing value;
the abnormal value eliminating unit is used for determining abnormal values according to preset plasma sterilization and disinfection indexes after filling the missing values by adopting a random forest method, and eliminating the abnormal values;
and the abnormal value filling unit is used for filling the removed abnormal values by using a random forest method to obtain the preprocessed plasma sterilization and disinfection data.
4. The plasma sterilization system of claim 2, wherein the screening classification module comprises:
the normal analysis unit is used for carrying out normal analysis on the pretreated plasma sterilization and disinfection data, wherein if the pretreated plasma sterilization and disinfection data accords with normal distribution, the correlation analysis is Pelson correlation analysis, and if the pretreated plasma sterilization and disinfection data does not accord with normal distribution, the correlation analysis is Szerland correlation analysis.
5. The plasma sterilization decontamination system of claim 1, wherein the multiple modeling module comprises:
the first modeling fitting data obtaining unit is used for modeling the screened and classified plasma sterilization and disinfection data by utilizing a PLS algorithm to obtain first modeling fitting data;
the comparison unit is used for comparing the first modeling fitting data with corresponding plasma sterilization and disinfection data to obtain a comparison result;
the second modeling fit data obtaining unit is used for screening the first modeling fit data based on the comparison result to obtain second modeling fit data;
and the modeling parameter obtaining unit is used for modeling the second modeling fitting data by utilizing a PLS algorithm to obtain modeling parameters.
6. The plasma sterilization system as recited in claim 1, further comprising:
the virtual space model construction module is used for constructing a corresponding virtual space model according to the volume data and the space types of each test disinfection space;
the virtual generator construction module is used for constructing a virtual generator according to the disinfection and sterilization range data of the preset plasma generator;
the virtual generator layout module is used for laying at least one virtual generator in a corresponding virtual space model aiming at any test disinfection space, and adjusting the layout number of the virtual generators and the positions of each virtual generator according to the disinfection and sterilization range data so as to obtain a plasma generator installation scheme corresponding to the test disinfection space;
and the scheme binding module is used for binding the volume data, the space types and the corresponding plasma generator installation schemes of each test disinfection space and then storing the volume data, the space types and the corresponding plasma generator installation schemes into a preset database.
7. The plasma sterilization system of claim 1, wherein the control command execution module comprises:
and the direct current high voltage conversion unit is used for converting direct current high voltage generated by the high voltage power supply into high voltage pulses through the pulse generator and conducting the high voltage pulses to the second plasma generator through the pulse generator.
8. The plasma sterilization and disinfection system according to claim 1, wherein the calculation formula of the hidden layer node number of the BP neural network model is as followsWherein h is the number of hidden layer nodes, m is the number of input layer nodes, n is the number of output layer nodes, a is an adjustment constant, and a is more than or equal to 1 and less than or equal to 10.
9. The plasma sterilization system of claim 8, wherein the output value of the BP neural network modelThe calculation formula of (2) is +.>Wherein->Represents the activation value of layer i neurons, < ->Representing the neurons of layer l-1 connected to layer i neurons,/>Representing each +.>Corresponding weights, ++>Is the offset, where n=1, 2,3.
10. An intelligent disinfection cabinet comprising a cabinet body and a side cover plate which are connected with each other, characterized in that the intelligent disinfection cabinet further comprises a plasma disinfection system as claimed in any one of claims 1 to 9.
CN202310855562.3A 2023-07-12 2023-07-12 Plasma sterilization and disinfection system and intelligent disinfection cabinet Active CN116870211B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310855562.3A CN116870211B (en) 2023-07-12 2023-07-12 Plasma sterilization and disinfection system and intelligent disinfection cabinet

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310855562.3A CN116870211B (en) 2023-07-12 2023-07-12 Plasma sterilization and disinfection system and intelligent disinfection cabinet

Publications (2)

Publication Number Publication Date
CN116870211A true CN116870211A (en) 2023-10-13
CN116870211B CN116870211B (en) 2024-05-24

Family

ID=88254348

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310855562.3A Active CN116870211B (en) 2023-07-12 2023-07-12 Plasma sterilization and disinfection system and intelligent disinfection cabinet

Country Status (1)

Country Link
CN (1) CN116870211B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117760143A (en) * 2023-12-26 2024-03-26 广东玖尚电子科技有限公司 Plasma fresh-keeping cabinet and fresh-keeping cabinet control system
CN118059285A (en) * 2024-04-22 2024-05-24 四川省畜牧科学研究院 Negative ion disinfection and purification system for livestock colony house
CN118446124A (en) * 2024-04-12 2024-08-06 深圳市富临厨房设备有限公司 Disinfection cabinet model integrated design method based on three-dimensional modeling

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20100124511A (en) * 2009-05-19 2010-11-29 한국건설기술연구원 Apparatus and method for predicting the production of disinfection by-product using a artificial neural network
WO2012053083A1 (en) * 2010-10-21 2012-04-26 株式会社日立製作所 Plasma sterilization appartus, plasma sterilization system and plasma sterilization method
CN103492064A (en) * 2010-11-09 2014-01-01 三星电子株式会社 Plasma generator, and plasma generating method
CN108983642A (en) * 2018-09-10 2018-12-11 深圳市宇墨科技有限公司 A kind of toilet disinfection control and toilet management system
CN111414995A (en) * 2020-03-16 2020-07-14 北京君立康生物科技有限公司 Small target colony detection processing method and device, electronic equipment and medium
CN111514349A (en) * 2020-04-22 2020-08-11 四川智眼天下网络科技有限公司 Working method of intelligent disinfection system
CN111544634A (en) * 2020-05-20 2020-08-18 李潮云 Closed environment disinfection and sterilization system based on data analysis
DE202020004425U1 (en) * 2020-11-13 2021-02-17 Robert Färber Room air disinfection device using plasma technology
US20210299296A1 (en) * 2020-03-31 2021-09-30 Beijing Xiaomi Mobile Software Co., Ltd. Disinfection and sterilization apparatus and method, and disinfection and sterilization control apparatus
CN114124460A (en) * 2021-10-09 2022-03-01 广东技术师范大学 Industrial control system intrusion detection method and device, computer equipment and storage medium
US20230008646A1 (en) * 2021-07-12 2023-01-12 Toyota Motor Engineering & Manufacturing North America, Inc. Detection, classification, and prediction of bacteria colony growth in vehicle passenger cabin

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20100124511A (en) * 2009-05-19 2010-11-29 한국건설기술연구원 Apparatus and method for predicting the production of disinfection by-product using a artificial neural network
WO2012053083A1 (en) * 2010-10-21 2012-04-26 株式会社日立製作所 Plasma sterilization appartus, plasma sterilization system and plasma sterilization method
CN103492064A (en) * 2010-11-09 2014-01-01 三星电子株式会社 Plasma generator, and plasma generating method
CN108983642A (en) * 2018-09-10 2018-12-11 深圳市宇墨科技有限公司 A kind of toilet disinfection control and toilet management system
CN111414995A (en) * 2020-03-16 2020-07-14 北京君立康生物科技有限公司 Small target colony detection processing method and device, electronic equipment and medium
US20210299296A1 (en) * 2020-03-31 2021-09-30 Beijing Xiaomi Mobile Software Co., Ltd. Disinfection and sterilization apparatus and method, and disinfection and sterilization control apparatus
CN111514349A (en) * 2020-04-22 2020-08-11 四川智眼天下网络科技有限公司 Working method of intelligent disinfection system
CN111544634A (en) * 2020-05-20 2020-08-18 李潮云 Closed environment disinfection and sterilization system based on data analysis
DE202020004425U1 (en) * 2020-11-13 2021-02-17 Robert Färber Room air disinfection device using plasma technology
US20230008646A1 (en) * 2021-07-12 2023-01-12 Toyota Motor Engineering & Manufacturing North America, Inc. Detection, classification, and prediction of bacteria colony growth in vehicle passenger cabin
CN114124460A (en) * 2021-10-09 2022-03-01 广东技术师范大学 Industrial control system intrusion detection method and device, computer equipment and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117760143A (en) * 2023-12-26 2024-03-26 广东玖尚电子科技有限公司 Plasma fresh-keeping cabinet and fresh-keeping cabinet control system
CN118446124A (en) * 2024-04-12 2024-08-06 深圳市富临厨房设备有限公司 Disinfection cabinet model integrated design method based on three-dimensional modeling
CN118059285A (en) * 2024-04-22 2024-05-24 四川省畜牧科学研究院 Negative ion disinfection and purification system for livestock colony house

Also Published As

Publication number Publication date
CN116870211B (en) 2024-05-24

Similar Documents

Publication Publication Date Title
CN116870211B (en) Plasma sterilization and disinfection system and intelligent disinfection cabinet
Xu et al. Digital twin-based anomaly detection in cyber-physical systems
CN110136731B (en) Cavity causal convolution generation confrontation network end-to-end bone conduction voice blind enhancement method
Lin et al. Graph-evolving meta-learning for low-resource medical dialogue generation
CN109948117A (en) A kind of satellite method for detecting abnormality fighting network self-encoding encoder
CN113569243A (en) Deep semi-supervised learning network intrusion detection method based on self-supervised variation LSTM
Gai et al. A Parameter‐Optimized DBN Using GOA and Its Application in Fault Diagnosis of Gearbox
CN108090686B (en) Medical event risk assessment analysis method and system
Tian et al. Joint learning model for underwater acoustic target recognition
CN114661905A (en) Power grid fault diagnosis method based on BERT
WO2023064397A1 (en) Anomaly detection based on normal behavior modeling
CN117494037A (en) Transformer fault diagnosis method based on variable-weight VAE and dual-channel feature fusion
Xu et al. Loop optimization noise-reduced LSTM based classifier for PD detection
CN118155662A (en) Transformer voiceprint fault identification method based on artificial intelligence
KR20090027921A (en) Automatic gis partial discharge identification method
Li et al. A lstm-based method for comprehension and evaluation of network security situation
Wen et al. An unsupervised subdomain adversarial network for remaining useful life estimation under various conditions
CN118013191A (en) Denoising method based on LSM filtering and CEEMDAN combined wavelet detection insulator
Xu et al. DTST: A Dual-aspect Time Series Transformer Model for Fault Diagnosis of Space Power System
Sun et al. Adversarial representation learning for intelligent condition monitoring of complex machinery
CN108538301A (en) A kind of intelligent digital musical instrument based on neural network Audiotechnica
Ghasvarian Jahromi et al. Wind power prediction based on wind speed forecast using hidden Markov model
US20230029400A1 (en) Method of Hierarchical Machine Learning for an Industrial Plant Machine Learning System
CN116089894A (en) Unknown fault diagnosis method for water chilling unit based on semi-supervised countermeasure variation automatic coding
CN115963788A (en) Multi-sampling-rate industrial process key quality index online prediction method

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