Oxygen supply control method and system based on gas flow signal

Abstract

The invention discloses an oxygen supply control method and system based on a gas flow signal, and relates to the technical field of gas control. A gas flow signal is denoised through a wavelet transform algorithm, so that the judgment precision of the main control unit on the gas flow state is improved, and the gas supply adjustment precision is ensured; a neural network and a fuzzy control algorithm are combined, the gas flow is dynamically adjusted, real-time monitoring and recalculation are carried out, the gas flow requirements of users at different stages are met, and the supply stability and accuracy are guaranteed; meanwhile, a dynamic model is established according to the valve control response time, the control signal output time sequence is optimized, the gas supply pressure and flow adjustment are smoother and more stable, the dynamic response and reliability of the system are improved, and the use comfort of a user is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of gas control, and in particular to an oxygen supply control method and system based on a gas flow signal. Background Art

[0002] In the gas supply system, it is necessary to dynamically adjust the gas supply according to the real-time gas flow state, which requires the system to accurately collect gas flow signals and respond in time. However, due to the irregularity of gas flow signals and external environmental interference, the data collected by the pressure sensor may have large noise, making it difficult for the control system to accurately judge the gas flow state; at the same time, the fluctuation of gas flow frequency and flow change trend will also affect the stability and accuracy of gas supply; in addition, the regulation of gas supply pressure and flow needs to be achieved by controlling the opening and closing time of the solenoid valve and the opening of the pressure regulating valve, which puts high demands on the signal processing capability and response speed of the control system; and the mechanical characteristics and response time limitations of the solenoid valve and pressure regulating valve will also affect the dynamic performance of gas supply. How to achieve accurate collection and judgment of gas flow signals in a noisy environment, how to achieve fast and accurate adjustment of gas supply pressure and flow according to gas flow state and preset parameters, and how to optimize the control strategy of the solenoid valve and pressure regulating valve to improve dynamic response characteristics are the main challenges faced by the gas supply system in technical implementation. Summary of the invention

[0003] The object of the present invention is to provide an oxygen supply control method and system based on a gas flow signal; The purpose of the present invention can be achieved through the following technical solutions: The present application provides an oxygen supply control method based on a gas flow signal, comprising the following steps: S1. Obtain the original gas flow signal from the pressure sensor, decompose the signal using the wavelet transform algorithm, extract and filter out the high-frequency noise component, and obtain the denoised gas flow signal; S2. Calculate the time-frequency characteristics of the signal based on the denoised gas flow signal, extract the period and change trend of the gas flow signal, and determine whether the gas flow signal is in the flow increase or decrease state stage through the state judgment algorithm. When the gas flow state is in the flow increase stage, calculate the current required gas flow value based on the preset gas supply parameters, and dynamically adjust the gas supply target value in combination with the flow frequency change trend; S3, using PID control algorithm, according to the deviation between the gas flow target value and the current actual flow value, calculate the opening and closing time of the solenoid valve, generate a PWM control signal and output it to the solenoid valve actuator; S4. Obtain the current gas supply pressure value through the opening feedback signal of the pressure regulating valve, and determine whether the opening of the pressure regulating valve needs to be adjusted in combination with the preset pressure range. If the current pressure value exceeds the preset range, the opening adjustment amount of the pressure regulating valve is calculated based on the pressure deviation value using a fuzzy control algorithm, and a control signal is generated and output to the pressure regulating valve actuator; S5. According to the control response time of the solenoid valve and the pressure regulating valve, the output timing of the control signal is optimized to make the dynamic adjustment process of the pressure and flow of the gas supply smooth and stable. Then, by real-time monitoring of the changing trends of the gas flow signal and the gas supply parameters, the preset parameters are dynamically updated to match the changes in the user's gas demand status and accurately adjust the gas supply.

[0004] Furthermore, the wavelet transform algorithm is used to decompose the signal, extract and filter out the high-frequency noise components, and obtain the denoised gas flow signal, which specifically includes: S11, obtaining gas flow signal data collected by the pressure sensor, inputting the gas flow signal data into a wavelet transform algorithm model, and then using the wavelet transform algorithm to perform multi-scale decomposition on the gas flow signal, decomposing the gas flow signal into sub-signals of different frequency scales; S12, extracting high-frequency noise component features from each sub-signal obtained by decomposition, inputting the extracted high-frequency noise component features into a noise filtering model, adaptively adjusting filter parameters according to the input high-frequency noise component features, and performing adaptive filtering on the sub-signal to remove the high-frequency noise components therein; S13, performing wavelet reconstruction on each sub-signal after filtering out the high-frequency noise to obtain a denoised gas flow signal, and performing smoothing on the denoised gas flow signal to eliminate the residual spike noise in the signal to obtain a smoothed gas flow signal; S14. Output the smoothed gas flow signal as the final gas flow signal detection result for frequency and amplitude analysis of the gas flow signal.

[0005] Furthermore, according to the denoised gas flow signal, the time-frequency characteristics of the signal are calculated, the period and change trend of the gas flow signal are extracted, and the gas flow signal is judged to be in the flow increase or decrease state stage through the state judgment algorithm, which specifically includes: Performing short-time Fourier transform on the denoised gas flow signal to obtain the time-frequency representation of the gas flow signal, and then extracting the time-frequency characteristics of the gas flow signal, including flow frequency and flow amplitude characteristics; According to the extracted flow frequency characteristics, the gas flow cycle is calculated to obtain the start time and end time of each gas flow cycle. Then, according to the extracted flow amplitude characteristics, the gas flow change trend is calculated to obtain the flow increase flow change curve over time. According to the gas flow cycle and change trend, determine whether the current gas flow state is a flow increase stage or a flow decrease stage. When the gas flow is on an upward trend and is in the first half of the gas flow cycle, it is determined to be a flow increase stage. When the gas flow is on a downward trend and is in the second half of the gas flow cycle, it is determined to be a flow decrease stage. According to the determined gas flow state, the current gas flow state is output, and the gas flow state is associated with the corresponding time point to obtain a complete gas flow state sequence.

[0006] Furthermore, after the state judgment algorithm determines that the gas flow signal is in the flow increase or decrease state stage, the method further includes: According to the preset gas supply parameters and the real-time detected flow frequency data, it is used as the input of the neural network model, and the gas flow target value required for the current flow increase stage is calculated through the trained neural network model; According to the calculated gas flow target value and combined with the flow frequency change trend data, the fuzzy control algorithm is used to dynamically adjust the output flow of the gas supply device so that it gradually approaches the target value; During the adjustment process, the flow frequency changes and gas flow changes are detected in real time. When the flow frequency changes significantly or the gas flow deviates greatly from the target value, the neural network model is triggered to recalculate the gas flow target value. The new gas flow target value calculated by the neural network model is input into the fuzzy control algorithm, and the output flow of the gas supply device is dynamically adjusted again until the gas flow is stabilized near the new target value.

[0007] Furthermore, a PID control algorithm is used to calculate the opening and closing time of the solenoid valve according to the deviation between the gas flow target value and the current actual flow value, generate a PWM control signal and output it to the solenoid valve actuator, specifically including: Obtain the target value and actual flow value of gas supply, calculate the deviation between the two, input the deviation into the PID control algorithm, and calculate the opening and closing time of the solenoid valve according to the proportional, integral and differential coefficients of the PID algorithm; Generate a corresponding control signal according to the calculated opening and closing time of the solenoid valve, and output the generated control signal to the solenoid valve actuator to control the opening and closing of the solenoid valve; The solenoid valve adjusts the valve opening according to the control signal received, thereby changing the actual flow of the gas. By continuously obtaining the real-time gas flow value, comparing it with the target value, and calculating the deviation value, a closed-loop control is formed.

[0008] Furthermore, the current gas supply pressure value is obtained through the opening feedback signal of the pressure regulating valve, and combined with the preset pressure range, it is determined whether the opening of the pressure regulating valve needs to be adjusted, specifically including: The pressure value data is transmitted to the control system, and it is compared with the preset pressure threshold range to determine whether the current pressure is within a reasonable range. When the pressure value is lower than the lower limit threshold of the preset range, the control system issues a command to increase the opening of the pressure regulating valve through the actuator; When the pressure value is higher than the upper threshold of the preset range, the control system issues a command to reduce the opening of the pressure regulating valve through the actuator to reduce the gas supply pressure. After the opening of the pressure regulating valve is adjusted, its outlet pressure value is obtained again until the pressure value stabilizes within the preset range.

[0009] During the pressure regulation process, historical pressure data is analyzed through machine learning algorithms such as support vector machines or neural networks, and a mapping model between pressure value and valve opening is established. The established mapping model is used to predict the optimal valve opening at the next moment based on the current pressure value, and feedforward control of the pressure regulating valve is performed.

[0010] Furthermore, a fuzzy control algorithm is used to calculate the opening adjustment amount of the pressure regulating valve, generate a control signal and output it to the pressure regulating valve actuator, specifically including: The current system pressure value is obtained in real time through the pressure sensor, and the pressure value is compared with the preset pressure range to determine whether the pressure value exceeds the preset range.

[0011] When the pressure value exceeds the preset range, the deviation between the current pressure value and the midpoint of the preset pressure range is calculated, and the deviation is used as the input of the fuzzy control algorithm. Then, according to the pressure deviation value, the pre-established fuzzy control rule library is used to calculate the opening adjustment amount of the pressure regulating valve through fuzzy reasoning; The calculated pressure regulating valve opening adjustment amount is converted into a corresponding control signal, the digital signal is converted into an analog signal through a digital-to-analog converter, and the generated analog control signal is output to an actuator of the pressure regulating valve to drive the actuator to adjust the opening of the pressure regulating valve; The pressure regulating valve changes the valve opening according to the adjustment action of the actuator, thereby adjusting the system pressure and returning the pressure value to the preset range.

[0012] Furthermore, according to the control response time of the solenoid valve and the pressure regulating valve, the output timing of the control signal is optimized to make the dynamic regulation process of the pressure and flow of the gas supply smooth and stable, specifically including: Obtain the control response time parameters of the solenoid valve and the pressure regulating valve, establish a valve dynamic model, obtain the relationship curve between the valve opening and the pressure and flow rate, and calculate the target valve opening and the control signal output timing through the valve dynamic model according to the target values ​​of the gas supply pressure and flow rate; Then, the valve opening deviation and pressure flow deviation are used as inputs, and the optimal adjustment amount of the control signal is obtained through fuzzy reasoning. The optimized control signal is sent to the solenoid valve and the pressure regulating valve in sequence according to the calculated output timing to dynamically adjust the valve opening; During the dynamic adjustment of the valve, the pressure and flow data of the gas supply pipeline are collected in real time and compared with the target value to obtain the deviation of pressure and flow. When the pressure deviation or flow deviation exceeds the preset threshold, the deviation is used as a feedback signal and input into the fuzzy control algorithm for further optimization and adjustment of the control signal.

[0013] Furthermore, by real-time monitoring of the changing trends of gas flow and gas supply parameters, the preset parameters are dynamically updated to match the changes in the user's gas demand status and accurately adjust the gas supply, including: Obtain the user's real-time gas flow signal and current gas supply parameters, compare them with the preset normal range threshold, and determine whether they exceed the normal range; when the real-time gas flow signal or gas supply parameter exceeds the normal range, an early warning is triggered, and the amplitude of the gas supply parameter that needs to be adjusted is determined according to the degree of deviation from the normal range; Through machine learning algorithms, based on the user's historical gas flow signals and the changing trends of gas supply parameters, the user's gas flow state changing trends in the future are predicted; then, based on the user's real-time gas flow signals, current gas supply parameters and the predicted future gas flow state changing trends, the gas supply parameters are dynamically adjusted to generate new gas supply parameter settings; The dynamically adjusted gas supply parameter settings are sent to the gas supply device, and the control device adjusts the gas supply in real time according to the new parameter settings to match the user's real-time gas flow status; After adjusting the gas supply parameters, continuously monitor the changes in the user's gas flow signal to determine whether the user's gas flow status has returned to normal. If not, return to continue adjusting; The user's real-time gas flow signal, gas supply parameters, and adjusted effect data are stored in the database for optimizing the machine learning model.

[0014] The present invention also provides an oxygen supply control system based on a gas flow signal, which is used to implement an oxygen supply control method based on a gas flow signal, comprising: The gas flow processing module obtains the gas flow signal from the pressure sensor, uses the wavelet transform algorithm to perform multi-scale decomposition, extracts and filters out high-frequency noise components, and then performs wavelet reconstruction and smoothing processing to finally output a smooth gas flow signal; The gas flow calculation module calculates the time-frequency characteristics of the denoised gas flow signal, extracts the gas flow cycle and change trend, and determines the current gas flow state. When the flow is in the rising stage, it combines the preset parameters and real-time flow frequency data to calculate the gas flow target value through the neural network model, and uses the fuzzy control algorithm to dynamically adjust the output flow of the gas supply device to meet the gas flow needs of users at different stages; The solenoid valve control module uses the PID control algorithm to calculate the opening and closing time of the solenoid valve according to the deviation between the gas supply target value and the actual flow value, generate a control signal and output it to the solenoid valve actuator to control the opening and closing of the solenoid valve, adjust the valve opening to change the actual gas flow, stabilize the gas flow at the target value through closed-loop control, and perform precise gas supply control; The pressure regulating module obtains the current gas supply pressure value through the opening feedback signal of the pressure regulating valve, and makes a judgment based on the preset pressure range. When the pressure value exceeds the preset range, the fuzzy control algorithm is used to calculate the opening adjustment amount of the pressure regulating valve according to the pressure deviation value, and a control signal is generated and output to the actuator to drive it to adjust the valve opening and adjust the system pressure so that the gas supply pressure is stable within the preset range; The dynamic adjustment optimization module integrates the control response time of the solenoid valve and the pressure regulating valve, optimizes the control signal output timing, and makes the dynamic adjustment process of the gas supply pressure and flow smooth and stable. By real-time monitoring of the gas flow signal and the changing trend of the gas supply parameters, it dynamically updates the preset parameters, matches the user's gas flow status changes, and realizes precise adjustment of the gas supply. The relevant data is stored in the database for optimizing the machine learning model.

[0015] The beneficial effects of the present invention are: The present invention uses a wavelet transform algorithm to perform multi-scale decomposition on the gas flow signal, extracts and filters out high-frequency noise components, and then performs wavelet reconstruction and smoothing processing, thereby effectively solving the problem of large noise in the gas flow signal collected by the pressure sensor, thereby improving the accuracy of the main control unit's judgment on the user's gas flow state and ensuring the accuracy of subsequent gas supply adjustment; The gas flow target value is calculated by combining the neural network model, and the fuzzy control algorithm is used to dynamically adjust the output flow of the gas supply device. At the same time, the flow frequency and gas flow changes are monitored in real time to trigger the model to recalculate, which solves the problem that the user's flow frequency and flow increase flow changes affect the stability and accuracy of gas supply. The gas supply flow is adjusted quickly and accurately according to the user's real-time gas flow status, ensuring the stability and accuracy of gas supply and meeting the user's gas flow needs at different stages. By obtaining the control response time parameters of the solenoid valve and pressure regulating valve, establishing a valve dynamic model, optimizing the control signal output timing, and using fuzzy reasoning for dynamic adjustment, the problem of the mechanical characteristics and response time limitations of the solenoid valve and pressure regulating valve affecting the dynamic performance of gas supply is effectively solved. This makes the dynamic adjustment process of gas supply pressure and flow smoother and more stable, improves the dynamic response characteristics of the system, and improves the reliability and comfort of gas supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0017] Figure 1 A flow chart of an oxygen supply control method based on a gas flow signal provided in Example 1 of the present application; Figure 2 A schematic flow chart of obtaining a denoised gas flow signal according to the oxygen supply control method based on a gas flow signal provided in Example 1 of the present application; Figure 3 This is a schematic diagram of the structure of an oxygen supply control system based on a gas flow signal provided in Example 2 of the present application. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0019] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0020] The specific implementation methods, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0021] Example 1: Please refer to Figure 1-Figure 2 This embodiment provides an oxygen supply control method based on a gas flow signal, comprising the following steps: S1. Obtain the original gas flow signal from the pressure sensor, decompose the signal using the wavelet transform algorithm, extract and filter out the high-frequency noise component, and obtain the denoised gas flow signal; Furthermore, the wavelet transform algorithm is used to decompose the signal, extract and filter out the high-frequency noise components, and obtain the denoised gas flow signal, which specifically includes: S11, obtaining gas flow signal data collected by the pressure sensor, inputting the gas flow signal data into a wavelet transform algorithm model, and then using the wavelet transform algorithm to perform multi-scale decomposition on the gas flow signal, decomposing the gas flow signal into sub-signals of different frequency scales; S12, extracting high-frequency noise component features from each sub-signal obtained by decomposition, inputting the extracted high-frequency noise component features into a noise filtering model, adaptively adjusting filter parameters according to the input high-frequency noise component features, and performing adaptive filtering on the sub-signal to remove the high-frequency noise components therein; S13, performing wavelet reconstruction on each sub-signal after filtering out the high-frequency noise to obtain a denoised gas flow signal, and performing smoothing on the denoised gas flow signal to eliminate the residual spike noise in the signal to obtain a smoothed gas flow signal; S14. Output the smoothed gas flow signal as the final gas flow signal detection result for subsequent frequency and amplitude analysis of the gas flow signal.

[0022] Specifically, the gas flow signal is decomposed at multiple scales through the wavelet transform algorithm, high-frequency noise components are extracted and filtered out, and then wavelet reconstruction and smoothing are performed to finally obtain a smooth gas flow signal. The noise in the gas flow signal is effectively removed, and the main features of the signal are retained. The quality and clarity of the gas flow signal are significantly improved, providing an accurate and reliable signal basis for the subsequent frequency and amplitude analysis of the gas flow signal, thereby ensuring that the portable oxygen generator can more accurately judge the user's gas flow status, and thus achieve more accurate gas supply adjustment.

[0023] Among them, gas flow refers to the flow signal of oxygen, and gas supply refers to the supply of oxygen; S2. Calculate the time-frequency characteristics of the signal based on the denoised gas flow signal, extract the period and change trend of the gas flow signal, and determine whether the gas flow signal is in the flow increase or decrease state stage through the state judgment algorithm. When the gas flow state is in the flow increase stage, calculate the current required gas flow value based on the preset gas supply parameters, and dynamically adjust the gas supply target value in combination with the flow frequency change trend; Furthermore, according to the denoised gas flow signal, the time-frequency characteristics of the signal are calculated, the period and change trend of the gas flow signal are extracted, and the gas flow signal is judged to be in the flow increase or decrease state stage through the state judgment algorithm, which specifically includes: Performing short-time Fourier transform on the denoised gas flow signal to obtain the time-frequency representation of the gas flow signal, and then extracting the time-frequency characteristics of the gas flow signal, including flow frequency and flow amplitude characteristics; According to the extracted flow frequency characteristics, the gas flow cycle is calculated to obtain the start time and end time of each gas flow cycle. Then, according to the extracted flow amplitude characteristics, the gas flow change trend is calculated to obtain the flow increase flow change curve over time. According to the gas flow cycle and change trend, determine whether the current gas flow state is a flow increase stage or a flow decrease stage. When the gas flow is on an upward trend and is in the first half of the gas flow cycle, it is determined to be a flow increase stage. When the gas flow is on a downward trend and is in the second half of the gas flow cycle, it is determined to be a flow decrease stage. According to the determined gas flow state, the current gas flow state is output, and the gas flow state is associated with the corresponding time point to obtain a complete gas flow state sequence.

[0024] Specifically, by calculating the time-frequency characteristics of the denoised gas flow signal, the gas flow period and change trend are accurately extracted, and then the current gas flow state is accurately judged as the flow rising or falling stage, and the gas supply target value is dynamically adjusted according to the preset parameters in the flow rising stage, thereby realizing real-time and accurate monitoring and response to the user's gas flow state, so that the gas supply can be dynamically adjusted according to the user's actual gas flow demand, improving the accuracy and adaptability of the gas supply, and better meeting the user's gas flow demand.

[0025] Furthermore, after the state judgment algorithm determines that the gas flow signal is in the flow increase or decrease state stage, the method further includes: According to the preset gas supply parameters and the real-time detected flow frequency data, it is used as the input of the neural network model, and the gas flow target value required for the current flow increase stage is calculated through the trained neural network model; According to the calculated gas flow target value and combined with the flow frequency change trend data, the fuzzy control algorithm is used to dynamically adjust the output flow of the gas supply device so that it gradually approaches the target value; During the adjustment process, the flow frequency changes and gas flow changes are detected in real time. When the flow frequency changes significantly or the gas flow deviates greatly from the target value, the neural network model is triggered to recalculate the gas flow target value. The new gas flow target value calculated by the neural network model is input into the fuzzy control algorithm, and the output flow of the gas supply device is dynamically adjusted again until the gas flow is stabilized near the new target value.

[0026] Continuously monitor the changes in gas flow rate in multiple gas flow cycles, calculate the average value and standard deviation of the gas flow, and determine whether the gas flow rate is stable within the target value range. When the gas flow rate is stable within the target value range in multiple consecutive gas flow cycles, the current gas supply strategy is maintained unchanged; When the gas flow rate deviates significantly from the target value, the adjustment strategy is triggered, and the flow frequency, gas flow target value, actual output flow and other parameters are written into the log file for subsequent analysis and optimization of the gas supply strategy.

[0027] Through the synergy of neural networks and fuzzy control algorithms, real-time dynamic adjustment of gas flow is achieved to ensure that it accurately and stably meets the gas flow needs of users. At the same time, key parameters are recorded to optimize the supply strategy, thereby improving the intelligence and adaptability of the equipment.

[0028] S3, using PID control algorithm, according to the deviation between the gas flow target value and the current actual flow value, calculate the opening and closing time of the solenoid valve, generate a PWM control signal and output it to the solenoid valve actuator; Furthermore, a PID control algorithm is used to calculate the opening and closing time of the solenoid valve according to the deviation between the gas flow target value and the current actual flow value, generate a PWM control signal and output it to the solenoid valve actuator, specifically including: Obtain the target value and actual flow value of gas supply, calculate the deviation between the two, input the deviation into the PID control algorithm, and calculate the opening and closing time of the solenoid valve according to the proportional, integral and differential coefficients of the PID algorithm; Generate a corresponding control signal according to the calculated opening and closing time of the solenoid valve, and output the generated control signal to the solenoid valve actuator to control the opening and closing of the solenoid valve; The solenoid valve adjusts the valve opening according to the control signal received, thereby changing the actual flow of the gas. By continuously obtaining the real-time gas flow value, comparing it with the target value, and calculating the deviation value, a closed-loop control is formed.

[0029] By continuously iterating the above process, the actual flow value of the gas gradually approaches and stabilizes at the target value, thereby achieving precise control of the gas supply.

[0030] Specifically, a PID control algorithm is used to accurately calculate the opening and closing time of the solenoid valve according to the deviation between the gas supply target value and the actual flow value, and generate a control signal to output to the actuator. Through continuous closed-loop control and deviation value feedback, the solenoid valve opening is continuously adjusted so that the actual gas flow value gradually approaches and stabilizes at the target value, thereby achieving high-precision and stable control of the gas supply, ensuring that users can obtain accurate and stable gas supply.

[0031] S4. Obtain the current gas supply pressure value through the opening feedback signal of the pressure regulating valve, and determine whether the opening of the pressure regulating valve needs to be adjusted in combination with the preset pressure range. If the current pressure value exceeds the preset range, the opening adjustment amount of the pressure regulating valve is calculated based on the pressure deviation value using a fuzzy control algorithm, and a control signal is generated and output to the pressure regulating valve actuator; wherein, this method is applicable to pressure control of gas or liquid.

[0032] Furthermore, the current gas supply pressure value is obtained through the opening feedback signal of the pressure regulating valve, and combined with the preset pressure range, it is determined whether the opening of the pressure regulating valve needs to be adjusted, specifically including: The pressure value data is transmitted to the control system, and it is compared with the preset pressure threshold range to determine whether the current pressure is within a reasonable range. When the pressure value is lower than the lower limit threshold of the preset range, the control system issues a command to increase the opening of the pressure regulating valve through the actuator to increase the gas supply pressure; When the pressure value is higher than the upper threshold of the preset range, the control system issues a command to reduce the opening of the pressure regulating valve through the actuator to reduce the gas supply pressure. After the opening of the pressure regulating valve is adjusted, its outlet pressure value is obtained again until the pressure value stabilizes within the preset range.

[0033] During the pressure regulation process, historical pressure data is analyzed through machine learning algorithms such as support vector machines or neural networks, and a mapping model between pressure value and valve opening is established. The established mapping model is used to predict the optimal valve opening at the next moment based on the current pressure value, thereby realizing feedforward control of the pressure regulating valve and improving the dynamic response performance of the system.

[0034] Furthermore, a fuzzy control algorithm is used to calculate the opening adjustment amount of the pressure regulating valve, generate a control signal and output it to the pressure regulating valve actuator, specifically including: The current system pressure value is obtained in real time through the pressure sensor, and the pressure value is compared with the preset pressure range to determine whether the pressure value exceeds the preset range.

[0035] When the pressure value exceeds the preset range, the deviation between the current pressure value and the midpoint of the preset pressure range is calculated, and the deviation is used as the input of the fuzzy control algorithm. Then, according to the pressure deviation value, the pre-established fuzzy control rule library is used to calculate the opening adjustment amount of the pressure regulating valve through fuzzy reasoning; The calculated pressure regulating valve opening adjustment amount is converted into a corresponding control signal, the digital signal is converted into an analog signal through a digital-to-analog converter, and the generated analog control signal is output to an actuator of the pressure regulating valve to drive the actuator to adjust the opening of the pressure regulating valve; The pressure regulating valve changes the valve opening according to the adjustment action of the actuator, thereby adjusting the system pressure and returning the pressure value to the preset range.

[0036] Specifically, through the opening feedback of the pressure regulating valve and the fuzzy control algorithm, the gas supply pressure can be accurately adjusted to stabilize it within the preset range. Combined with the mapping model established by the machine learning algorithm, feedforward control is achieved, which improves the dynamic response performance of the system, ensures the stability and reliability of the gas supply pressure, and provides users with a safe and stable gas flow environment.

[0037] S5. According to the control response time of the solenoid valve and the pressure regulating valve, the output timing of the control signal is optimized to make the dynamic adjustment process of the pressure and flow of the gas supply smooth and stable. Then, by real-time monitoring of the changing trends of the gas flow and gas supply parameters, the preset parameters are dynamically updated to match the changes in the user's gas demand status and accurately adjust the gas supply.

[0038] Furthermore, according to the control response time of the solenoid valve and the pressure regulating valve, the output timing of the control signal is optimized to make the dynamic regulation process of the pressure and flow of the gas supply smooth and stable, specifically including: Obtain the control response time parameters of the solenoid valve and the pressure regulating valve, establish a valve dynamic model, obtain the relationship curve between the valve opening and the pressure and flow rate, and calculate the target valve opening and the control signal output timing through the valve dynamic model according to the target values ​​of the gas supply pressure and flow rate; Then, the valve opening deviation and pressure flow deviation are used as inputs, and the optimal adjustment amount of the control signal is obtained through fuzzy reasoning. The optimized control signal is sent to the solenoid valve and the pressure regulating valve in sequence according to the calculated output timing to achieve dynamic adjustment of the valve opening; During the dynamic adjustment of the valve, the pressure and flow data of the gas supply pipeline are collected in real time, compared with the target value, and the deviation of pressure and flow is obtained; when the pressure deviation or flow deviation exceeds the preset threshold, the deviation is used as a feedback signal and input into the fuzzy control algorithm to further optimize and adjust the control signal; By continuously repeating the above process of pressure and flow acquisition, deviation calculation, and control optimization until the gas supply pressure and flow are stabilized at the target value, smooth dynamic regulation can be achieved.

[0039] Furthermore, by real-time monitoring of the changing trends of gas flow and gas supply parameters, the preset parameters are dynamically updated to match the changes in the user's gas demand status and accurately adjust the gas supply, including: Obtain the user's real-time gas flow signal and current gas supply parameters, compare them with the preset normal range threshold, and determine whether they exceed the normal range; when the real-time gas flow signal or gas supply parameter exceeds the normal range, an early warning is triggered, and the amplitude of the gas supply parameter that needs to be adjusted is determined according to the degree of deviation from the normal range; Through machine learning algorithms, based on the user's historical gas flow signals and the changing trends of gas supply parameters, the user's gas flow state changing trends in the future are predicted; then, based on the user's real-time gas flow signals, current gas supply parameters and the predicted future gas flow state changing trends, the gas supply parameters are dynamically adjusted to generate new gas supply parameter settings; The dynamically adjusted gas supply parameter settings are sent to the gas supply device, and the control device adjusts the gas supply in real time according to the new parameter settings to match the user's real-time gas flow status; After adjusting the gas supply parameters, continuously monitor the changes in the user's gas flow signal to determine whether the user's gas flow status has returned to normal. If not, return to continue adjusting; The user's real-time gas flow signal, gas supply parameters, and adjusted effect data are stored in the database to optimize the machine learning model and improve the accuracy of future predictions and adjustments.

[0040] Specifically, by optimizing the control signal output timing and real-time monitoring and updating of preset parameters, smooth and stable regulation of gas supply pressure and flow is achieved, as well as precise matching of changes in user gas flow status, thereby improving the comfort and adaptability of gas supply and ensuring that users can obtain continuous and stable gas flow support.

[0041] Example 2: Please refer to Figure 3 This embodiment provides an oxygen supply control system based on a gas flow signal, which is used to implement an oxygen supply control method based on a gas flow signal, including: The gas flow processing module obtains the gas flow signal from the pressure sensor, uses the wavelet transform algorithm to perform multi-scale decomposition, extracts and filters out high-frequency noise components, and then performs wavelet reconstruction and smoothing processing to finally output a smooth gas flow signal; The gas flow calculation module calculates the time-frequency characteristics of the denoised gas flow signal, extracts the gas flow cycle and change trend, and determines the current gas flow state. When the flow is in the rising stage, it combines the preset parameters and real-time flow frequency data to calculate the gas flow target value through the neural network model, and uses the fuzzy control algorithm to dynamically adjust the output flow of the gas supply device to meet the gas flow needs of users at different stages; The solenoid valve control module uses the PID control algorithm to calculate the opening and closing time of the solenoid valve according to the deviation between the gas supply target value and the actual flow value, generate a control signal and output it to the solenoid valve actuator to control the opening and closing of the solenoid valve, adjust the valve opening to change the actual gas flow, stabilize the gas flow at the target value through closed-loop control, and perform precise gas supply control; The pressure regulating module obtains the current gas supply pressure value through the opening feedback signal of the pressure regulating valve, and makes a judgment based on the preset pressure range. When the pressure value exceeds the preset range, the fuzzy control algorithm is used to calculate the opening adjustment amount of the pressure regulating valve according to the pressure deviation value, and a control signal is generated and output to the actuator to drive it to adjust the valve opening and adjust the system pressure to ensure that the gas supply pressure is stable within the preset range; The dynamic adjustment optimization module integrates the control response time of the solenoid valve and the pressure regulating valve, optimizes the control signal output timing, and makes the dynamic adjustment process of the gas supply pressure and flow smooth and stable. By real-time monitoring of the gas flow signal and the changing trend of the gas supply parameters, it dynamically updates the preset parameters, matches the user's gas flow status changes, and realizes precise adjustment of the gas supply. The relevant data is stored in the database for optimizing the machine learning model and improving the prediction and adjustment accuracy.

[0042] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An oxygen supply control method based on a gas flow signal, characterized in that: The steps include: The original gas flow signal is obtained from the pressure sensor, and the signal is decomposed at multiple scales using the wavelet transform algorithm to extract and filter out the high-frequency noise component to obtain the denoised gas flow signal; According to the denoised gas flow signal, the time-frequency characteristics of the signal are calculated, the period and change trend of the gas flow signal are extracted, and the gas flow signal is judged to be in the flow rising or falling state stage through the state judgment algorithm. When it is in the flow rising state stage, the current required gas flow value is calculated according to the preset gas supply parameters, and the gas supply target value is dynamically adjusted in combination with the frequency change trend of the gas flow signal; Adopt PID control algorithm, calculate the opening and closing time of the solenoid valve according to the deviation between the gas flow target value and the current actual flow value, generate PWM control signal and output it to the solenoid valve actuator; The current gas supply pressure value is obtained through the opening feedback signal of the pressure regulating valve, and combined with the preset pressure range, it is determined whether the opening of the pressure regulating valve needs to be adjusted. If the current pressure value exceeds the preset range, the fuzzy control algorithm is used to calculate the opening adjustment amount of the pressure regulating valve according to the pressure deviation value, and a control signal is generated and output to the pressure regulating valve actuator; According to the control response time of the solenoid valve and the pressure regulating valve, the output timing of the control signal is optimized to make the dynamic adjustment process of the pressure and flow of the gas supply smooth and stable. Then, by real-time monitoring of the changing trends of the gas flow and gas supply parameters, the preset parameters are dynamically updated to match the changes in the user's gas demand status and accurately adjust the gas supply.

2. The oxygen supply control method based on the gas flow signal according to claim 1, characterized in that: The wavelet transform algorithm is used to perform multi-scale decomposition of the signal, extract and filter out the high-frequency noise components, and obtain the denoised gas flow signal, which includes: The gas flow signal data is input into the wavelet transform algorithm model, and then the wavelet transform algorithm is used to perform multi-scale decomposition on the gas flow signal, decomposing the gas flow signal into sub-signals of different frequency scales; According to each sub-signal obtained by decomposition, the high-frequency noise component characteristics are extracted, and the extracted high-frequency noise component characteristics are input into the noise filtering model. According to the input high-frequency noise component characteristics, the filter parameters are adaptively adjusted, and the sub-signal is adaptively filtered to remove the high-frequency noise components. After filtering out the high-frequency noise, each sub-signal is subjected to wavelet reconstruction to obtain a denoised gas flow signal, and the denoised gas flow signal is smoothed to eliminate the residual spike noise in the signal to obtain a smooth gas flow signal; The smoothed gas flow signal is output as the final gas flow signal detection result and used for frequency and amplitude analysis of the gas flow signal.

3. The oxygen supply control method based on the gas flow signal according to claim 1, characterized in that: According to the denoised gas flow signal, the time-frequency characteristics of the signal are calculated, the period and change trend of the gas flow signal are extracted, and the gas flow signal is judged to be in the flow increase or decrease state stage through the state judgment algorithm, which specifically includes: Performing short-time Fourier transform on the denoised gas flow signal to obtain the time-frequency representation of the gas flow signal, and then extracting the time-frequency characteristics of the gas flow signal, including flow frequency and flow amplitude characteristics; According to the extracted flow frequency characteristics, the gas flow cycle is calculated to obtain the start time and end time of each gas flow cycle. Then, according to the extracted flow amplitude characteristics, the gas flow change trend is calculated to obtain the flow increase flow change curve over time. According to the gas flow cycle and change trend, determine whether the current gas flow state is a flow increase stage or a flow decrease stage. When the gas flow is on an upward trend and is in the first half of the gas flow cycle, it is determined to be a flow increase stage. When the gas flow is on a downward trend and is in the second half of the gas flow cycle, it is determined to be a flow decrease stage. According to the determined gas flow state, the current gas flow state is output, and the gas flow state is associated with the corresponding time point to obtain a complete gas flow state sequence.

4. The oxygen supply control method based on the gas flow signal according to claim 3, characterized in that: After the state judgment algorithm determines that the gas flow signal is in the flow increase or decrease state, it also includes: According to the preset gas supply parameters and the real-time detected flow frequency data, it is used as the input of the neural network model, and the gas flow target value required for the current flow increase stage is calculated through the trained neural network model; According to the calculated gas flow target value and combined with the flow frequency change trend data, the fuzzy control algorithm is used to dynamically adjust the output flow of the gas supply device so that it gradually approaches the target value; During the adjustment process, the flow frequency changes and gas flow changes are detected in real time. When the flow frequency changes significantly or the gas flow deviates greatly from the target value, the neural network model is triggered to recalculate the gas flow target value. The new gas flow target value calculated by the neural network model is input into the fuzzy control algorithm, and the output flow of the gas supply device is dynamically adjusted again until the gas flow is stabilized near the new target value.

5. The oxygen supply control method based on the gas flow signal according to claim 1, characterized in that: The PID control algorithm is used to calculate the opening and closing time of the solenoid valve according to the deviation between the gas flow target value and the current actual flow value, generate a PWM control signal and output it to the solenoid valve actuator, including: Obtain the target value and actual flow value of gas supply, calculate the deviation between the two, input the deviation into the PID control algorithm, and calculate the opening and closing time of the solenoid valve according to the proportional, integral and differential coefficients of the PID algorithm; Generate a corresponding control signal according to the calculated opening and closing time of the solenoid valve, and output the generated control signal to the solenoid valve actuator to control the opening and closing of the solenoid valve; The solenoid valve adjusts the valve opening according to the control signal received, thereby changing the actual flow of the gas. By continuously obtaining the real-time gas flow value, comparing it with the target value, and calculating the deviation value, a closed-loop control is formed.

6. The oxygen supply control method based on the gas flow signal according to claim 1, characterized in that: The current gas supply pressure value is obtained through the opening feedback signal of the pressure regulating valve, and combined with the preset pressure range, it is determined whether the opening of the pressure regulating valve needs to be adjusted, including: The pressure value data is transmitted to the control system, and it is compared with the preset pressure threshold range to determine whether the current pressure is within a reasonable range. When the pressure value is lower than the lower limit threshold of the preset range, the control system issues a command to increase the opening of the pressure regulating valve through the actuator; When the pressure value is higher than the upper threshold of the preset range, the control system issues a command to reduce the opening of the pressure regulating valve through the actuator to reduce the gas supply pressure. After the opening of the pressure regulating valve is adjusted, its outlet pressure value is obtained again until the pressure value stabilizes within the preset range. During the pressure regulation process, historical pressure data is analyzed through machine learning algorithms such as support vector machines or neural networks, and a mapping model between pressure value and valve opening is established. The established mapping model is used to predict the optimal valve opening at the next moment based on the current pressure value, and feedforward control of the pressure regulating valve is performed.

7. The oxygen supply control method based on the gas flow signal according to claim 1, characterized in that: The fuzzy control algorithm is used to calculate the opening adjustment of the pressure regulating valve, generate a control signal and output it to the pressure regulating valve actuator, specifically including: The current system pressure value is obtained in real time through the pressure sensor, and the pressure value is compared with the preset pressure range to determine whether the pressure value exceeds the preset range; When the pressure value exceeds the preset range, the deviation between the current pressure value and the midpoint of the preset pressure range is calculated, and the deviation is used as the input of the fuzzy control algorithm. Then, according to the pressure deviation value, the pre-established fuzzy control rule library is used to calculate the opening adjustment amount of the pressure regulating valve through fuzzy reasoning; The calculated pressure regulating valve opening adjustment amount is converted into a corresponding control signal, the digital signal is converted into an analog signal through a digital-to-analog converter, and the generated analog control signal is output to an actuator of the pressure regulating valve to drive the actuator to adjust the opening of the pressure regulating valve; The pressure regulating valve changes the valve opening according to the adjustment action of the actuator, thereby adjusting the system pressure and returning the pressure value to the preset range.

8. The oxygen supply control method based on the gas flow signal according to claim 1, characterized in that: According to the control response time of the solenoid valve and the pressure regulating valve, the output timing of the control signal is optimized to make the dynamic adjustment process of the pressure and flow of the gas supply smooth and stable, including: Obtain the control response time parameters of the solenoid valve and the pressure regulating valve, establish a valve dynamic model, obtain the relationship curve between the valve opening and the pressure and flow rate, and calculate the target valve opening and the control signal output timing through the valve dynamic model according to the target values ​​of the gas supply pressure and flow rate; Then, the valve opening deviation and pressure flow deviation are used as inputs, and the optimal adjustment amount of the control signal is obtained through fuzzy reasoning. The optimized control signal is sent to the solenoid valve and the pressure regulating valve in sequence according to the calculated output timing to dynamically adjust the valve opening; During the dynamic adjustment of the valve, the pressure and flow data of the gas supply pipeline are collected in real time and compared with the target value to obtain the deviation of pressure and flow. When the pressure deviation or flow deviation exceeds the preset threshold, the deviation is used as a feedback signal and input into the fuzzy control algorithm for further optimization and adjustment of the control signal.

9. The oxygen supply control method based on the gas flow signal according to claim 1, characterized in that: By real-time monitoring of the changing trends of gas flow and gas supply parameters, dynamically updating preset parameters, matching the changes in user gas demand status, and accurately adjusting gas supply, specifically including: Obtain the user's real-time gas flow signal and current gas supply parameters, compare them with the preset normal range threshold, and determine whether they exceed the normal range; when the real-time gas flow signal or gas supply parameter exceeds the normal range, an early warning is triggered, and the amplitude of the gas supply parameter that needs to be adjusted is determined according to the degree of deviation from the normal range; Through machine learning algorithms, based on the user's historical gas flow signals and the changing trends of gas supply parameters, the user's gas flow state changing trends in the future are predicted; then, based on the user's real-time gas flow signals, current gas supply parameters and the predicted future gas flow state changing trends, the gas supply parameters are dynamically adjusted to generate new gas supply parameter settings; The dynamically adjusted gas supply parameter settings are sent to the gas supply device, and the control device adjusts the gas supply in real time according to the new parameter settings to match the user's real-time gas flow status; After adjusting the gas supply parameters, continuously monitor the changes in the user's gas flow signal to determine whether the user's gas flow status has returned to normal. If not, return to continue adjusting; The user's real-time gas flow signal, gas supply parameters and data on the adjusted effects are stored in the database for optimizing the machine learning model.

10. An oxygen supply control system based on a gas flow signal, used to implement the oxygen supply control method based on a gas flow signal as claimed in any one of claims 1 to 9, characterized in that: include: The gas flow processing module obtains the gas flow signal from the pressure sensor, uses the wavelet transform algorithm to perform multi-scale decomposition, extracts and filters out high-frequency noise components, and then performs wavelet reconstruction and smoothing processing to finally output a smooth gas flow signal; The gas flow calculation module calculates the time-frequency characteristics of the denoised gas flow signal, extracts the gas flow cycle and change trend, and determines the current gas flow state. When the flow is in the rising stage, it combines the preset parameters and real-time flow frequency data to calculate the gas flow target value through the neural network model, and uses the fuzzy control algorithm to dynamically adjust the output flow of the gas supply device to meet the gas flow needs of users at different stages; The solenoid valve control module uses the PID control algorithm to calculate the opening and closing time of the solenoid valve according to the deviation between the gas supply target value and the actual flow value, generate a control signal and output it to the solenoid valve actuator to control the opening and closing of the solenoid valve, adjust the valve opening to change the actual gas flow, stabilize the gas flow at the target value through closed-loop control, and perform precise gas supply control; The pressure regulating module obtains the current gas supply pressure value through the opening feedback signal of the pressure regulating valve, and makes a judgment based on the preset pressure range. When the pressure value exceeds the preset range, the fuzzy control algorithm is used to calculate the opening adjustment amount of the pressure regulating valve according to the pressure deviation value, and a control signal is generated and output to the actuator to drive it to adjust the valve opening and adjust the system pressure so that the gas supply pressure is stable within the preset range; The dynamic adjustment optimization module integrates the control response time of the solenoid valve and the pressure regulating valve, optimizes the control signal output timing, and makes the dynamic adjustment process of the gas supply pressure and flow smooth and stable. It monitors the gas flow signal and the changing trend of the gas supply parameters in real time, dynamically updates the preset parameters, matches the user's gas flow status changes, and accurately adjusts the gas supply. The relevant data is stored in the database for optimizing the machine learning model.

Images