AI Flexible Control System and Method for Hydrogen Peroxide Low-Temperature Plasma Sterilizer

Abstract

The present invention provides an AI flexible control system and method for a hydrogen peroxide low-temperature plasma sterilizer, which relates to the technical field of medical devices. It includes a constant value module, and the constant value module includes a full-cycle parameter block and a half-cycle parameter block. It also includes a flexible module, and the flexible module includes a device ID subsystem for obtaining the appearance information and barcode information of the device; a device AI analysis subsystem for obtaining device attribute information; and a sterilization process PID dynamic control subsystem for adjusting the sterilization effect of the flexible hydrogen peroxide low-temperature plasma sterilizer control system to the optimal value. The beneficial effect of the present invention is that it can automatically read and judge the basic information of the device. After the AI analysis system pulls the corresponding device ID data and obtains the basic sterilization parameters of the device, the process PID dynamic control subsystem can dynamically adjust the sterilization parameters in real time according to the feedback data during sterilization. Under the comprehensive and accurate SQL database and dynamic control system, intelligent unmanned sterilization can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and more particularly, to an AI flexible control system and method for a hydrogen peroxide low-temperature plasma sterilizer. Background Art

[0002] With the development of modern medical technology, medical devices have gradually become more diverse, sophisticated, and specialized. Now, the requirements for the disinfection and sterilization of medical devices and the medical environment are also gradually increasing, and new requirements have been put forward for efficient, temperature-controlled, and safe sterilization methods. The traditional high-temperature and high-pressure sterilization method and chemical disinfectant method can no longer meet the sterilization requirements of some special items.

[0003] Currently, in the low-temperature sterilization industry, the sterilization modes of hydrogen peroxide low-temperature plasma sterilizers are all similar to the standard mode and detection mode specified in GB27955. The control system loads corresponding fixed built-in parameters for sterilization according to the sterilization mode manually selected by the operator. However, there are the following problems with this current method: it cannot remind of abnormal instruments, high-risk instruments, and fatigued instruments, and cannot perform protective adjustments during the sterilization process, resulting in instrument damage; it cannot meet the sterilization requirements of all medical devices on the market currently, resulting in restricted usage scenarios; before sterilization, it cannot completely avoid human misjudgment and misoperation, resulting in the use of the wrong sterilization mode to sterilize the instrument, causing equipment damage; it cannot adjust and update the dynamic parameters of new medical devices on the market, resulting in the inability to perform sterilization.

[0004] In summary, under the fixed sterilization mode and fixed sterilization parameters, the standard mode and detection mode often cannot meet the special requirements of different medical devices currently, and even risks such as decreased sterilization stability, decreased efficiency, decreased accuracy, decreased safety, and decreased durability may occur. Summary of the Invention

[0005] The purpose of the present invention is to provide an AI flexible control system and method for a hydrogen peroxide low-temperature plasma sterilizer to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0006] In a first aspect, the present application provides an AI flexible control system for a hydrogen peroxide low-temperature plasma sterilizer, including a constant value module. The constant value module includes a full-cycle parameter block and a half-cycle parameter block. The full-cycle parameter block is the standard mode for instrument sterilization in the AI flexible control system of the hydrogen peroxide low-temperature plasma sterilizer, and the half-cycle parameter block is the detection mode for sterilization performance verification in the AI flexible control system of the hydrogen peroxide low-temperature plasma sterilizer. It further includes a flexible module. The flexible module includes an instrument ID subsystem for obtaining the appearance information and barcode information of the instrument; an instrument AI analysis subsystem for obtaining instrument attribute information; and a PID dynamic control subsystem for the sterilization process, which is used to adjust the sterilization effect of the flexible hydrogen peroxide low-temperature plasma sterilizer control system to an optimal value.

[0007] Preferably, the instrument ID subsystem is used to obtain the appearance information and barcode information of the instrument through a visual port scanner and store the obtained information in the ID data register.

[0008] Preferably, the instrument AI analysis subsystem is used to read and judge the data stream stored in the ID data register, and obtain the current instrument data group corresponding to the instrument in the instrument information SQL database through the AI analysis system.

[0009] Preferably, the PID dynamic control subsystem for the sterilization process is used to import the current instrument data group, and during sterilization, adjust the sterilization parameters in real time and dynamically according to the feedback data on the device, optimize the performance of the PID dynamic control subsystem for the sterilization process, and thus make the sterilization effect reach the optimal value.

[0010] In a second aspect, the present application also provides an AI flexible control method for a hydrogen peroxide low-temperature plasma sterilizer, including:

[0011] Using an image acquisition device to obtain the basic information of the instrument and store it as the first data. Among them, the basic information includes the SN barcode data of the instrument and the appearance state data of the instrument, and the first data includes the aging condition data, discoloration condition data, and damage condition data of the instrument.

[0012] Reading the first data and extracting the second data corresponding to the first data. Among them, the second data includes the production date, material type, historical sterilization data, model, and manufacturer information of the instrument corresponding to the first data.

[0013] Based on a preset algorithm, generating a basic parameter group of the instrument from the second data.

[0014] Inputting the basic parameter group into a preset optimization model, adjusting the parameter size to control the parameters during sterilization, and obtaining an ideal curve of the optimal sterilization parameters.

[0015] The beneficial effects of the present invention are:

[0016] The low-temperature plasma sterilizer of the present invention can perform low-temperature sterilization on both metal medical devices and non-metal medical devices; hydrogen peroxide diffuses in the chamber and is then "excited" into a plasma state to sterilize the medical devices. The hydrogen peroxide vapor can combine with the plasma to safely and quickly sterilize medical devices and materials without leaving any toxic residues. Each stage of the sterilization process operates in a dry and low-temperature environment, so it will not damage heat- or moisture-sensitive devices, is applicable to both metal and non-metal devices, and can sterilize difficult-to-reach (poorly diffusible) device parts such as hemostat hinges.

[0017] In the flexible mode of the present invention, there is no need for manual verification of the device model and material, nor for manual judgment of the device status. The device ID subsystem will automatically read and judge the basic information of the device. After the AI analysis system retrieves the corresponding device ID data and obtains the basic sterilization parameters of the device, during the sterilization period, the process PID dynamic control subsystem will dynamically adjust the sterilization parameters in real time according to the feedback data. Under the comprehensive and accurate SQL database and dynamic control system, intelligent unmanned sterilization can be achieved.

[0018] In the present invention, in the PID dynamic control subsystem, the parameters in the basic parameter group are used as the target parameters, the actual value feedback by the sensor is calculated to obtain the e(t) deviation value, and the u(t) value is obtained through the PID algorithm as the control quantity of the actuator, so that the data curve of the entire sterilization process always follows the optimal sterilization curve. This method can better achieve the followability of system dynamic control, eliminate the deviation in dynamic control, and thus greatly optimize the control of the system.

[0019] The present invention can generate different basic parameter groups for different devices, different manufacturers of the same device, different batches of the same device and manufacturer, different production dates of the same device, manufacturer and batch, and different sterilization times of the same device, manufacturer, batch and production date, so that the sterilization process has adaptability, specificity, efficiency, safety and stability.

[0020] The present invention adopts an AI flexible system that can adapt to all medical devices within the sterilizable range of the device, automatically identify the devices, calculate parameters and perform dynamic control, achieving full-process intelligence.

[0021] Other features and advantages of the present invention will be described in the subsequent specification, and part of them will be obvious from the specification or understood by implementing the embodiments of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the structures specifically pointed out in the written specification, claims, and drawings. Brief Description of the Drawings

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0023] Figure 1 It is a schematic flow chart of the AI flexible control method for the hydrogen peroxide low-temperature plasma sterilizer described in the embodiments of the present invention. Detailed implementation manners

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and illustrated in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents the selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0025] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present invention, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0026] Embodiment 1:

[0027] This embodiment provides an AI flexible control system for a hydrogen peroxide low-temperature plasma sterilizer. The system includes a constant value module, and the constant value module includes a full-cycle parameter block and a half-cycle parameter block. Among them, the full-cycle parameter block is the standard mode for instrument sterilization in the AI flexible control system of the hydrogen peroxide low-temperature plasma sterilizer, and the half-cycle parameter block is the detection mode for sterilization performance verification in the AI flexible control system of the hydrogen peroxide low-temperature plasma sterilizer. It also includes a flexible module, and the flexible module includes an instrument ID subsystem for obtaining the appearance information and barcode information of the instrument; an instrument AI analysis subsystem for obtaining instrument attribute information; and a sterilization process PID dynamic control subsystem for adjusting the sterilization effect of the flexible hydrogen peroxide low-temperature plasma sterilizer control system to the optimal value.

[0028] It should be noted that the AI flexible control system for realizing flexible mode sterilization mainly relies on the cooperation and linkage of the following three subsystems: the instrument ID subsystem, the instrument AI analysis subsystem, and the PID dynamic control subsystem for the sterilization process.

[0029] It should be noted that the AI flexible control system of the hydrogen peroxide low-temperature plasma sterilizer is used to control each component of the AI hydrogen peroxide low-temperature plasma sterilizer so that the hydrogen peroxide low-temperature plasma sterilizer performs the sterilization work according to the set program.

[0030] Preferably, the instrument ID subsystem is used to obtain the appearance information and barcode information of the instrument through a visual port scanner, and store the obtained information in the ID data register.

[0031] Preferably, the instrument AI analysis subsystem is used to read and judge the data stream stored in the ID data register, and obtain the current instrument data group of the corresponding instrument in the instrument information SQL database through the AI analysis system.

[0032] Preferably, the PID dynamic control subsystem for the sterilization process is used to import the current instrument data group, and during sterilization, adjust the sterilization parameters in real time according to the feedback data on the equipment, optimize the performance of the PID dynamic control subsystem for the sterilization process, so as to make the sterilization effect reach the optimal value.

[0033] Embodiment 2:

[0034] This embodiment provides an AI flexible control method for a hydrogen peroxide low-temperature plasma sterilizer.

[0035] See Figure 1 , the figure shows that this method includes step S100, step S200, step S300, and step S400.

[0036] S100. Use an image acquisition device to obtain the basic information of the instrument and store it as the first data. Among them, the basic information includes the SN barcode data of the instrument and the appearance state data of the instrument, and the first data includes the aging condition data, discoloration condition data, and damage condition data of the instrument.

[0037] It can be understood that in this step S100 includes S101, S102, and S103, where:

[0038] S101. Use a camera to collect the first image information and the second image information of the instrument. The first image information is an image containing SN barcode data, and the second image information is the appearance image information of the instrument;

[0039] It should be noted that the camera includes but is not limited to a camera, a video camera, a camera, a scanner, and other devices with a photographing function (such as mobile phones, tablets, etc.).

[0040] S102. Perform image processing on the second image information. The image processing includes a pixel matrix, and the pixel matrix processing includes image filtering, image color space conversion, image compression, and feature extraction. Collect the status data of the appearance of the instrument in the processed second image information to generate a status data set;

[0041] S103. Use the barcode data and status data in the first image information as the current instrument data group, and store the instrument data group set in the ID data register.

[0042] It should be noted that after step S103, it includes S1031 and S1032, where:

[0043] Perform data cleaning on all parameters in the instrument data group to obtain the cleaned data;

[0044] Perform data exploration on the cleaned data to obtain the data after exploratory analysis.

[0045] S200. Read the first data and extract the second data corresponding to the first data. Among them, the second data includes the production date, material type, historical sterilization data, model, and manufacturer information of the instrument corresponding to the first data.

[0046] It can be understood that in this step, the production date, material type, historical sterilization data, model, and manufacturer information of the corresponding instrument are retrieved from the instrument information SQL database to generate the current instrument data group.

[0047] S300. Based on a preset algorithm, generate a basic parameter group of the instrument. The preset algorithm in this step is the AI module algorithm.

[0048] It can be understood that in this S300 step, it includes S301, S302, and S303, where:

[0049] S301. Obtain historical sterilization parameter data;

[0050] It should be noted that through the data of the historical sterilization parameters, a linear regression algorithm is used to calculate the parameters.

[0051] S302. Calculate the historical sterilization parameter data based on the linear regression algorithm. For example, let the number of sterilizations be x, and the sterilization pressure parameter in the basic parameter group be y. The calculation formula for the preset linear relationship between x and y is as follows:

[0052] y = bx + a

[0053] Where x is the number of sterilization times, y is the sterilization pressure parameter in the basic parameter group, b is the linear parameter, and a is the intercept;

[0054] S303. Using the least squares method, assuming a normal distribution, find the partial derivatives of a and b respectively and set them equal to zero, and solve for the second data to obtain the basic parameter group of the instrument. The solution calculation formulas for b and a are as follows:

[0055]

[0056] Where i is the data subscript number, i = 1, 2,..., n; n is the total number of samples; is the average of x1, x2... x n in the sample, is the average of y1, y2... y n in the sample, is the product of the average value of x, the average value of y, and the total number of samples n in the sample; is the sum of the products of x i , y i for each data set; is the product of the total number of samples n and the square of the average value of x in the sample; is the sum of the squares of x i for each data set; is the product of b in the solution of the function equation and the average value of x in the sample.

[0057] It should be noted that all parameters in the basic parameter group of the instrument need to be within the fixed safety range. If the basic parameter group of the instrument obtained through the AI module algorithm exceeds the safety range, then the instrument is determined to have reached the sterilization limit. After the instrument is returned to the factory for necessary maintenance and then can be sterilized again. That is to say, it is necessary to judge whether the basic parameter group is within the safety range. If it exceeds, it needs to be returned to the factory for further processing before proceeding to the next step.

[0058] S400. Input the basic parameter group into the preset optimization model, adjust the parameter size to control the parameters during the sterilization process, and obtain the ideal curve of the optimal sterilization parameters.

[0059] It can be understood that in this S400 step, S401 is included, where:

[0060] S401. After starting the sterilization program, input the basic parameter group into the preset PID dynamic control system model for processing to obtain an ideal curve with the smallest deviation from the optimal sterilization curve. The processing process includes: calculating the deviation based on the real-time data displayed by the device, where the real-time data includes feedback data and the feedback data corresponding to the optimal sterilization curve, and the feedback data includes pressure, temperature, hydrogen peroxide concentration, and plasma intensity data; taking the basic parameters as a reference, adjusting the corresponding basic parameter group according to the deviation value, so that when the feedback data of the current sterilization reaches the threshold requirement, the deviation from the optimal sterilization curve is minimized.

[0061] It should be noted that after starting the sterilization, taking the basic parameters as a reference, during sterilization, the basic parameter group of the current instrument is automatically imported into the PID dynamic control system model (preset model). According to the feedback data in the system, such as pressure, temperature, hydrogen peroxide concentration, plasma intensity data, and the corresponding pressure, temperature, hydrogen peroxide concentration, and plasma intensity in the optimal sterilization curve, the deviation value is calculated, and then the corresponding basic parameter group is adjusted according to the deviation value. The real-time data continuously adjusts the sterilization parameters, so that the current sterilization feedback data can always meet the qualified requirements while maintaining the smallest deviation from the optimal sterilization curve, continuously optimizing the performance of the system to achieve the optimal sterilization effect.

[0062] It can be understood that in this step S401, it includes S4011 and S4012, where:

[0063] S4011. Taking the basic parameters as the target parameters, calculate the actual value feedback by the sensor to obtain the deviation value e(t), and use the PID algorithm to obtain the value u(t) as the control quantity of the actuator, so that the data curve of the entire sterilization process is the optimal sterilization curve. The differential calculation formula of the PID controller is:

[0064]

[0065] In the formula, e(t) is the deviation curve between the given value and the controlled variable, u(t) is the control quantity of the actuator, K P is the proportionality coefficient, T I is the integral time constant, T D is the differential time constant, t is the time interval elapsed from the start of adjustment to the output of the current control quantity, is the area obtained by integrating the deviation curve e(t) with the X-axis from 0 to time t, is the slope of the deviation curve e(t);

[0066] S4012. Discretize the continuous signal. Let the sampling period be T, then the above formula can be converted to:

[0067]

[0068] In the formula, K I is the integral gain, K D is the differential gain, K P is the proportional coefficient, k is the sampling sequence number, k = 0, 1, 2...; is the accumulated value of the deviation values of the inputs from the first to the k-th sampling, u(k) is the computer output value at the k-th sampling moment, e(k) is the deviation value of the input at the k-th sampling moment; e(k - 1) is the deviation value of the input at the (k - 1)-th sampling moment;

[0069] Simplify the above formula:

[0070]

[0071] In the formula, K I is the integral gain; K D is the differential gain; k is the sampling sequence number, k = 0, 1, 2...; u(k) is the computer output value at the k-th sampling moment; e(k) is the deviation value of the input at the k-th sampling moment; e(k - 1) is the deviation value of the input at the (k - 1)-th sampling moment.

[0072] In this embodiment, the implementation schemes for configuring the hardware system and the software system are as follows:

[0073] 1. Configure the hardware system: Connect the image acquisition / barcode scanning device and the online SQL server to the on / off port of the control system / sterilization chamber, configure the unoccupied IP address, and the hardware port can be activated to complete the configuration of the entire hardware system network.

[0074] 2. Configure the software system: After the hardware system configuration is completed, connect the RJ45 port on the main controller of the control system / sterilization chamber to the PC, and configure the IP and DNS parameters;

[0075] Load the system program onto the main controller of the control system / sterilization chamber through the program software on the PC side, and restart the device;

[0076] After restarting, the program on the main controller of the control system / sterilization chamber automatically searches for the SQL server and the image acquisition / barcode scanning device through self-checking, and automatically assigns the corresponding communication addresses; after the self-checking is successful, the software system configuration is completed.

[0077] In the flexible mode, there is no need for manual verification of the instrument model and material, nor for manual judgment of the instrument status. The instrument ID subsystem will automatically read and judge the basic information of the instrument. After the AI analysis system retrieves the corresponding instrument ID data and obtains the basic sterilization parameters of the instrument, during sterilization, the process PID dynamic control subsystem will dynamically adjust the sterilization parameters in real time according to the feedback data. Under the comprehensive and accurate SQL database and dynamic control system, intelligent unmanned sterilization can be achieved.

[0078] In summary, this control method can better achieve the followability of system dynamic control, eliminate the deviation in dynamic control, and thus greatly optimize the control of the system.

[0079] It should be noted that the present invention adopts an instrument ID subsystem. By scanning technology and obtaining the SN code information of the instrument itself, the device ID data is determined. By visual inspection technology, the appearance status of the instrument is judged and obtained. This can not only timely provide the instrument status information to the operator before sterilization, but also prevent the operator from misjudging the instrument model and material type, and avoid damage to the instrument caused by incorrect information entry during the sterilization process; an instrument AI analysis subsystem is adopted. The basic parameter group obtained by comparing and calculating the data in the ID data register with the instrument information SQL database, with the support of the online SQL server, enables the basic parameter group to be applicable to all data instruments on the current market, thus avoiding the risk of the operator misjudging the sterilization mode; different basic parameter groups will be generated for different instruments, different manufacturers of the same instrument, different batches of the same instrument from the same manufacturer, different production dates of the same instrument from the same manufacturer and the same batch, and different sterilization times of the same instrument from the same manufacturer and the same batch and the same production date, which can make the sterilization process have adaptability, specificity, high efficiency, safety and stability; and during the flexible mode sterilization process, the dynamic model in the sterilization process PID dynamic control subsystem synchronously adjusts the sterilization parameters according to the real-time data of the device to correct the dynamic deviation of the basic parameter group. Even for new medical devices, the sterilization effect can be optimized every time sterilization is performed.

[0080] It should be noted that regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment related to the method, and will not be elaborated here.

[0081] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0082] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. The AI flexible control method of a hydrogen peroxide low-temperature plasma sterilizer is realized through the AI flexible control system of the hydrogen peroxide low-temperature plasma sterilizer. The AI flexible control system of the hydrogen peroxide low-temperature plasma sterilizer includes a constant value module. The constant value module includes a full-cycle parameter block and a half-cycle parameter block. Among them, the full-cycle parameter block is the standard mode for instrument sterilization in the AI flexible control system of the hydrogen peroxide low-temperature plasma sterilizer, and the half-cycle parameter block is the detection mode for sterilization performance verification in the AI flexible control system of the hydrogen peroxide low-temperature plasma sterilizer. It also includes a flexible module. The flexible module includes an instrument ID subsystem for obtaining the appearance information and barcode information of the instrument; an instrument AI analysis subsystem for obtaining instrument attribute information; a sterilization process PID dynamic control subsystem for adjusting the sterilization effect of the flexible hydrogen peroxide low-temperature plasma sterilizer control system to the optimal value. The instrument ID subsystem is used to obtain the appearance information and barcode information of the instrument through a vision port scanner and store the obtained information in the ID data register. The instrument AI analysis subsystem is used to read and judge the data stream stored in the ID data register and obtain the current instrument data group of the corresponding instrument in the instrument information SQL database through the AI analysis system. The sterilization process PID dynamic control subsystem is used to import the current instrument data group and, during sterilization, perform real-time dynamic adjustment of the sterilization parameters according to the feedback data on the device, optimize the performance of the sterilization process PID dynamic control subsystem, and thus make the sterilization effect reach the optimal value. It is characterized in that The AI flexible control method of the hydrogen peroxide low-temperature plasma sterilizer includes: Using an image acquisition device to obtain the basic information of the instrument and store it as the first data. Among them, the basic information includes the SN barcode data of the instrument and the appearance state data of the instrument, and the first data includes the aging condition data, discoloration condition data, and damage condition data of the instrument. Reading the first data and extracting the second data corresponding to the first data. Among them, the second data includes the production date, material type, historical sterilization data, model, and manufacturer information of the instrument corresponding to the first data. Based on a preset algorithm, generating a basic parameter group of the instrument. Inputting the basic parameter group into a preset optimization model, adjusting the parameter size to control the parameters during sterilization, and obtaining an ideal curve of the optimal sterilization parameters. Among them, using an image acquisition device to obtain the basic information of the instrument and store it as the first data includes using a camera to collect the first image information and the second image information of the instrument. The first image information is an image containing SN barcode data, and the second image information is the appearance image information of the instrument. Performing image processing on the second image information. The image processing includes a pixel matrix. Among them, the pixel matrix processing includes image filtering, image color space conversion, image compression, and feature extraction. Collecting the state data of the appearance of the instrument in the processed second image information and generating a state data set. Take the barcode data and status data in the first image information as the current device data group, and store the device data group set in the ID data register; based on a preset algorithm, generate a basic parameter group for the device, including: Obtain historical sterilization parameter data; Based on the linear regression algorithm, calculate the historical sterilization parameter data. The preset linear regression function can be as follows: y = bx + a In the formula, x is the number of sterilizations, y is the sterilization pressure parameter in the basic parameter group, b is the linear slope, and a is the intercept; Using the least squares method, solve the second data. The function equation solution of the preset linear regression function can be obtained by the following solution set, as follows: Where i is the data subscript number, i = 1, 2, …… n; n is the total number of samples; is the average of x1, x2 …… x n in the sample, is the average of y1, y2 …… y n in the sample, is the product of the average value of x, the average value of y, and the total number of samples n in the sample; is the sum of the products of each data set x i , y i in the sample; is the product of the total number n and the square of the average value of x in the sample; is the sum of the squares of each data set x i in the sample; is the product of b in the solution of the function equation and the average value of x in the sample.

2. The AI flexible control method of the hydrogen peroxide low-temperature plasma sterilizer according to claim 1, wherein The step of taking the barcode data and status data in the first image information as the current device data group is followed by: Perform data cleaning on all parameters in the device data group to obtain the cleaned data; Perform data exploration on the cleaned data to obtain the data after exploratory analysis.

3. The AI flexible control method of the hydrogen peroxide low-temperature plasma sterilizer according to claim 1, characterized in that The step of inputting the basic parameter group into a preset optimization model, adjusting the parameter size to control the parameters during sterilization, and obtaining the ideal curve of the optimal sterilization parameters includes: After starting the sterilization program, input the basic parameter group into a preset PID dynamic control system model for processing to obtain an ideal curve with the smallest deviation from the optimal sterilization curve; the processing process includes: calculating the deviation based on the real-time data displayed by the device, where the real-time data includes feedback data and the feedback data corresponding to the optimal sterilization curve, and the feedback data includes pressure, temperature, hydrogen peroxide concentration, and plasma intensity data; taking the basic parameters as the benchmark, adjusting the corresponding basic parameter group according to the deviation value so that when the feedback data of the current sterilization reaches the threshold requirement, the deviation from the optimal sterilization curve is kept the smallest.

4. The AI flexible control method of the hydrogen peroxide low-temperature plasma sterilizer according to claim 3, wherein The step of inputting the basic parameter group into a preset PID dynamic control system model for processing to obtain an ideal curve with the smallest deviation from the optimal sterilization curve, and the calculation formula is as follows: Taking the basic parameters as the target parameters, calculating the actual value feedback by the sensor to obtain the e(t) deviation value, and using the PID algorithm to obtain the u(t) value as the control quantity of the actuator, so that the data curve of the entire sterilization process is the optimal sterilization curve. The differential calculation formula of the PID controller is: where e(t) is the deviation curve between the given value and the controlled variable, u(t) is the control quantity of the actuator, K P is the proportionality coefficient, T I is the integral time constant, T D is the derivative time constant, t is the time interval elapsed from the start of regulation to the output of the current control quantity, is the area obtained by integrating the deviation curve e(t) with the X-axis from 0 to time t, is the slope of the deviation curve e(t); Discretize the continuous signal. Let the sampling period be T and the sampling sequence number be k, then the above formula can be converted to: where K I is the integral gain, K D is the derivative gain, K P is the proportionality coefficient, k is the sampling sequence number, k = 0, 1, 2...; is the cumulative value of the deviation values of the inputs from the first to the k-th sampling, u(k) is the computer output value at the k-th sampling moment; e(k) is the deviation value of the input at the k-th sampling moment; e(k - 1) is the deviation value of the input at the (k - 1)-th sampling moment.

Images