Oxygen supply control method and system based on gas flow signal

Abstract

The present invention discloses an oxygen supply control method and system based on gas flow signals, which relates to the technical field of gas control. The present invention performs noise reduction processing on the gas flow signal through a wavelet transform algorithm to improve the judgment accuracy of the main control unit on the gas flow state and ensure accurate adjustment of gas supply; combines neural network and fuzzy control algorithms to dynamically adjust the gas flow, monitors and recalculates in real time to meet the gas flow requirements of users in different stages, and ensures the stability and accuracy of supply; at the same time, establishes a dynamic model based on the valve control response time to optimize the output timing of the control signal, making the adjustment of gas supply pressure and flow smoother and more stable, improving the dynamic response and reliability of the system, and enhancing the user's comfort in use.

Description

Technical Field

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

[0002] In a 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 a timely manner. However, due to the irregularity of gas flow signals and external environmental interference, the data collected by pressure sensors may have significant noise, making it difficult for the control system to accurately judge the gas flow state; at the same time, the fluctuations in gas flow frequency and flow change trend will also affect the stability and accuracy of gas supply; in addition, the adjustment of gas supply pressure and flow needs to be achieved by controlling the opening and closing time of solenoid valves and the opening degree of pressure regulating valves, which poses high requirements on the signal processing ability and response speed of the control system; moreover, the mechanical characteristics and response time limitations of solenoid valves and pressure regulating valves will also affect the dynamic performance of gas supply. How to accurately collect and judge gas flow signals in a noisy environment, how to quickly and accurately adjust gas supply pressure and flow according to gas flow state and preset parameters, and how to optimize the control strategies of solenoid valves and pressure regulating valves to improve dynamic response characteristics are the main challenges faced by gas supply systems in technical implementation. Summary of the Invention

[0003] The purpose of the present invention is to provide an oxygen supply control method and system based on gas flow signals;

[0004] The purpose of the present invention can be achieved by the following technical solutions:

[0005] The present application provides an oxygen supply control method based on gas flow signals, including the following steps:

[0006] S1. Obtain the original gas flow signal from a pressure sensor, decompose the signal using the wavelet transform algorithm, extract and filter out the high-frequency noise components to obtain the denoised gas flow signal;

[0007] S2. According to the denoised gas flow signal, calculate the time-frequency characteristics of the signal, extract the period and change trend of the gas flow signal, and judge whether the gas flow signal is in the rising or falling state stage through a state judgment algorithm. When the gas flow state is in the rising stage, calculate the current required gas flow value according to the preset gas supply parameters, and dynamically adjust the gas supply target value in combination with the flow frequency change trend;

[0008] S3. Adopt the 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 a PWM control signal and output it to the solenoid valve actuator;

[0009] S4. Obtain the current gas supply pressure value through the opening feedback signal of the pressure regulating valve. Combine it with the preset pressure range to judge whether it is necessary to adjust the opening of the pressure regulating valve. If the current pressure value exceeds the preset range, calculate the opening adjustment amount of the pressure regulating valve using the fuzzy control algorithm according to the pressure deviation value, generate a control signal and output it to the pressure regulating valve actuator;

[0010] S5. Optimize the output timing of the control signal according to the control response times of the solenoid valve and the pressure regulating valve, so that the dynamic adjustment process of the gas supply pressure and flow rate is smooth and stable. Then, dynamically update the preset parameters by real-time monitoring the change trends of the gas flow signal and the gas supply parameters, match the changes in the user's gas demand state, and perform precise adjustment of the gas supply.

[0011] Furthermore, use the wavelet transform algorithm to decompose the signal, extract the high-frequency noise components and filter them to obtain the denoised gas flow signal, specifically including:

[0012] S11. Obtain the gas flow signal data collected by the pressure sensor, input the gas flow signal data into the wavelet transform algorithm model, and then use 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;

[0013] S12. According to each decomposed sub-signal, extract the characteristics of the high-frequency noise components therein, input the extracted high-frequency noise component characteristics into the noise filtering model, adaptively adjust the filter parameters according to the input high-frequency noise component characteristics, and perform adaptive filtering processing on the sub-signals to remove the high-frequency noise components therein;

[0014] S13. Perform wavelet reconstruction on each sub-signal after filtering out the high-frequency noise to obtain the denoised gas flow signal, perform smoothing processing on the denoised gas flow signal to eliminate the residual spike noise in the signal, and obtain a smooth gas flow signal;

[0015] S14. Output the smoothed gas flow signal as the final gas flow signal detection result for the frequency and amplitude analysis of the gas flow signal.

[0016] Furthermore, according to the denoised gas flow signal, calculate the time-frequency characteristics of the signal, extract the period and change trend of the gas flow signal, and judge whether the gas flow signal is in the rising or falling state stage through the state judgment algorithm, specifically including:

[0017] Perform short-time Fourier transform on the denoised gas flow signal to obtain the time-frequency representation of the gas flow signal, and then extract the time-frequency characteristics of the gas flow signal, including the flow frequency and flow amplitude characteristics;

[0018] According to the extracted flow rate frequency characteristics, calculate the gas flow cycle, obtain the start time and end time of each gas flow cycle, and then according to the extracted flow rate amplitude characteristics, calculate the gas flow change trend to obtain the curve of the rising flow rate changing with time;

[0019] According to the gas flow cycle and change trend, judge whether the current gas flow state is in the rising flow stage or the falling flow stage. When the gas flow shows an upward trend and is in the first half of the gas flow cycle, it is judged as the rising flow stage. When the gas flow shows a downward trend and is in the second half of the gas flow cycle, it is judged as the falling flow stage;

[0020] According to the judged gas flow state, output the current gas flow state and associate the gas flow state with the corresponding time point to obtain a complete gas flow state sequence.

[0021] Furthermore, after judging the gas flow signal as the rising or falling flow state stage through the state judgment algorithm, it further includes:

[0022] According to the preset gas supply parameters and the real-time detected flow rate frequency data, use them as the input of the neural network model, and through the trained neural network model, calculate the target value of the gas flow required in the current rising flow stage;

[0023] According to the calculated target value of the gas flow, combined with the flow rate frequency change trend data, adopt the fuzzy control algorithm to dynamically adjust the output flow rate of the gas supply device to gradually approach the target value;

[0024] During the adjustment process, real-time detect the flow rate frequency change and gas flow change. When the flow rate frequency changes significantly or the deviation between the gas flow and the target value is large, trigger the neural network model to recalculate the target value of the gas flow;

[0025] Input the new target value of the gas flow calculated by the neural network model into the fuzzy control algorithm to perform another dynamic adjustment on the output flow rate of the gas supply device until the gas flow stabilizes near the new target value.

[0026] Furthermore, adopt the PID control algorithm. According to the deviation between the target value of the gas flow and the current actual flow rate value, calculate the opening and closing time of the solenoid valve, generate a PWM control signal and output it to the solenoid valve actuator, specifically including:

[0027] Obtain the target value and actual flow rate value of the gas supply, calculate the deviation value between the two, input the deviation value 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;

[0028] Generate corresponding control signals according to the calculated opening and closing times of the solenoid valve, output the generated control signals to the solenoid valve actuator, and control the opening and closing of the solenoid valve;

[0029] The solenoid valve adjusts the opening of the valve according to the received control signal, thereby changing the actual gas flow rate. By continuously obtaining real-time gas flow rate values, comparing them with the target value, calculating the deviation value, a closed-loop control is formed.

[0030] Furthermore, obtain the current gas supply pressure value through the opening feedback signal of the pressure regulating valve, and combine it with the preset pressure range to determine whether the opening of the pressure regulating valve needs to be adjusted. Specifically, it includes:

[0031] Transmit the pressure value data to the control system, compare it with the preset pressure threshold range, and determine whether the current pressure is within a reasonable range. When the pressure value is lower than the lower threshold of the preset range, the control system issues an instruction to increase the opening of the pressure regulating valve through the actuator;

[0032] When the pressure value is higher than the upper threshold of the preset range, the control system issues an instruction 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, obtain its outlet pressure value again until the pressure value stabilizes within the preset range.

[0033] During the pressure regulation process, analyze the historical pressure data through machine learning algorithms such as support vector machines or neural networks, establish a mapping model between the pressure value and the valve opening, and use the established mapping model to predict the optimal valve opening at the next moment according to the current pressure value for feedforward control of the pressure regulating valve.

[0034] Furthermore, use the fuzzy control algorithm 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, it includes:

[0035] Obtain the current system pressure value in real time through the pressure sensor, compare the pressure value with the preset pressure range, and determine whether the pressure value exceeds the preset range.

[0036] When the pressure value exceeds the preset range, calculate the deviation value between the current pressure value and the median of the preset pressure range, use the deviation value as the input of the fuzzy control algorithm, and then according to the pressure deviation value, adopt the pre-established fuzzy control rule base to calculate the opening adjustment amount of the pressure regulating valve through fuzzy inference;

[0037] Convert the calculated opening adjustment amount of the pressure regulating valve into the corresponding control signal, convert the digital signal into an analog signal through the digital-to-analog converter, and output the generated analog control signal to the actuator of the pressure regulating valve to drive the actuator to adjust the opening of the pressure regulating valve;

[0038] The pressure regulating valve changes the valve opening according to the adjustment action of the actuator, thereby regulating the system pressure and bringing the pressure value back within the preset range.

[0039] Furthermore, according to the control response times 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 rate of the gas supply smooth and stable. Specifically, it includes:

[0040] 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 output timing of the control signal through the valve dynamic model according to the target values of the gas supply pressure and flow rate;

[0041] Then, using the valve opening deviation and the pressure and flow rate deviation as inputs, through fuzzy inference, obtain the optimized adjustment amount of the control signal, and send the optimized control signal to the solenoid valve and the pressure regulating valve in sequence according to the calculated output timing for dynamic adjustment of the valve opening;

[0042] During the dynamic adjustment of the valve, the pressure and flow rate data of the gas supply pipeline are collected in real time, compared with the target values to obtain the pressure and flow rate deviations; when the pressure deviation or the flow rate 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.

[0043] Furthermore, by real-time monitoring the change trends of the gas flow rate and the gas supply parameters, the preset parameters are dynamically updated to match the change of the user's gas demand state for precise adjustment of the gas supply. Specifically, it includes:

[0044] Obtain the user's real-time gas flow rate signal and the current gas supply parameters, compare them with the preset normal range threshold to determine whether they exceed the normal range; when the real-time gas flow rate signal or the gas supply parameters exceed the normal range, trigger an alarm, and determine the amplitude of the gas supply parameters to be adjusted according to the degree of deviation from the normal range;

[0045] Through a machine learning algorithm, based on the change trends of the user's historical gas flow rate signals and gas supply parameters, predict the change trend of the user's gas flow rate state in the next period of time; then, according to the user's real-time gas flow rate signal, the current gas supply parameters, and the predicted future gas flow rate state change trend, dynamically adjust the gas supply parameters to generate a new gas supply parameter setting;

[0046] Send the dynamically adjusted gas supply parameter setting to the gas supply equipment, and the control equipment adjusts the gas supply in real time according to the new parameter setting to match the user's real-time gas flow rate state;

[0047] After adjusting the gas supply parameters, continuously monitor the change of the user's gas flow signal, and judge whether the user's gas flow state returns to normal. If it does not return to normal, return to continue the adjustment;

[0048] Store data such as the user's real-time gas flow signal, gas supply parameters, and the effect after adjustment into the database for optimizing the machine learning model.

[0049] The present invention also provides an oxygen supply control system based on the gas flow signal for implementing the oxygen supply control method based on the gas flow signal, including:

[0050] A gas flow processing module, which obtains the gas flow signal from the pressure sensor, performs multi-scale decomposition on it using the wavelet transform algorithm, extracts and filters out the high-frequency noise components, then performs wavelet reconstruction and smoothing processing, and finally outputs a smoothed gas flow signal;

[0051] A gas flow calculation module, based on the denoised gas flow signal, calculates its time-frequency characteristics, extracts the gas flow period and change trend, judges the current gas flow state. When in the flow rising stage, combined with the preset parameters and real-time flow frequency data, calculates 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 requirements of users in different stages;

[0052] A solenoid valve control module, which uses the PID control algorithm, calculates the opening and closing time of the solenoid valve according to the deviation between the gas supply target value and the actual flow value, generates a control signal and outputs it to the solenoid valve actuator, controls the opening and closing of the solenoid valve, adjusts the valve opening to change the actual gas flow, and makes the gas flow stable at the target value through closed-loop control to perform precise gas supply control;

[0053] A pressure regulation module, obtains the current gas supply pressure value through the opening feedback signal of the pressure regulating valve, makes a judgment in combination with the preset pressure range. When the pressure value exceeds the preset range, calculates the opening adjustment amount of the pressure regulating valve according to the pressure deviation value using the fuzzy control algorithm, generates a control signal and outputs it to the actuator to drive it to adjust the valve opening and regulate the system pressure to make the gas supply pressure stable within the preset range;

[0054] A dynamic regulation and optimization module, comprehensively considering the control response time of the solenoid valve and the pressure regulating valve, optimizes the output timing of the control signal to make the dynamic regulation process of the gas supply pressure and flow smooth and stable. By real-time monitoring the change trend of the gas flow signal and gas supply parameters, dynamically updates the preset parameters to match the change of the user's gas flow state, realizes the precise regulation of gas supply, and stores the relevant data into the database for optimizing the machine learning model.

[0055] The beneficial effects of the present invention are:

[0056] The present invention performs multi-scale decomposition on the gas flow signal by using the wavelet transform algorithm, extracts and filters out the high-frequency noise components, and then performs wavelet reconstruction and smoothing processing, effectively solving the problem of large noise in the gas flow signal collected by the pressure sensor, thereby improving the judgment accuracy of the main control unit on the user's gas flow state and ensuring the accuracy of subsequent gas supply regulation;

[0057] Combined with the neural network model to calculate the gas flow target value, and uses the fuzzy control algorithm to dynamically adjust the output flow of the gas supply device. At the same time, it monitors the flow frequency and gas flow change in real time and triggers the model to recalculate, solving the problem that the user's flow frequency and rising flow change affect the stability and accuracy of gas supply, and realizing the rapid and accurate adjustment of the gas supply flow according to the user's real-time gas flow state, ensuring the stability and accuracy of gas supply, and meeting the gas flow requirements of users at different stages;

[0058] By obtaining the control response time parameters of the solenoid valve and the pressure regulating valve, establishing a valve dynamic model, optimizing the output timing of the control signal, and using fuzzy inference for dynamic adjustment, it effectively solves the problem that the mechanical characteristics and response time limitations of the solenoid valve and the pressure regulating valve affect the dynamic performance of gas supply, making the dynamic adjustment process of gas supply pressure and flow smoother and more stable, improving the dynamic response characteristics of the system, and enhancing the reliability and comfort of gas supply. Description of the Drawings

[0059] For better understanding and implementation, the technical solutions of this application will be described in detail below with reference to the drawings.

[0060] Figure 1 It is a schematic flow chart of the oxygen supply control method based on the gas flow signal provided in Embodiment 1 of this application;

[0061] Figure 2 It is a schematic flow chart of obtaining the denoised gas flow signal by the oxygen supply control method based on the gas flow signal provided in Embodiment 1 of this application;

[0062] Figure 3 It is a schematic structural diagram of the oxygen supply control system based on the gas flow signal provided in Embodiment 2 of this application. Detailed Embodiments

[0063] To further illustrate the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail herein, and the examples are shown in the 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 embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of methods and systems consistent with some aspects of the present application as detailed in the appended claims.

[0064] The terms used in the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0065] The following will, in conjunction with the accompanying drawings and preferred embodiments, elaborate in detail on the specific embodiments, features, and their effects according to the present invention.

[0066] Embodiment 1: Please refer to Figure 1 - Figure 2 , this embodiment provides an oxygen supply control method based on a gas flow signal, including the following steps:

[0067] S1. Obtain the original gas flow signal from a pressure sensor, decompose the signal using a wavelet transform algorithm, extract the high-frequency noise components and filter them to obtain a denoised gas flow signal;

[0068] Further, decomposing the signal using a wavelet transform algorithm, extracting the high-frequency noise components and filtering them to obtain a denoised gas flow signal specifically includes:

[0069] S11. Obtain the gas flow signal data collected by the pressure sensor, input the gas flow signal data into a wavelet transform algorithm model, and then use 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;

[0070] S12. According to each sub-signal obtained by the decomposition, extract the high-frequency noise component features therein, input the extracted high-frequency noise component features into a noise filtering model, adaptively adjust the filter parameters according to the input high-frequency noise component features, and perform adaptive filtering processing on the sub-signals to remove the high-frequency noise components therein;

[0071] S13. Perform wavelet reconstruction on each sub-signal after filtering out high-frequency noise to obtain the denoised gas flow signal. Smooth the denoised gas flow signal to eliminate the residual spike noise in the signal and obtain a smooth gas flow signal.

[0072] 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.

[0073] Specifically, the gas flow signal is decomposed at multiple scales by the wavelet transform algorithm, the high-frequency noise components are extracted and filtered out, then wavelet reconstruction and smoothing processing are performed. Finally, a smooth gas flow signal is obtained, effectively removing the noise in the gas flow signal, retaining the main features of the signal, significantly improving the quality and clarity of the gas flow signal, providing an accurate and reliable signal basis for 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 state and further achieve more accurate gas supply adjustment.

[0074] Among them, the gas flow refers to the flow signal of oxygen, and the gas supply is represented as the supply of oxygen.

[0075] S2. According to the denoised gas flow signal, calculate the time-frequency characteristics of the signal, extract the period and change trend of the gas flow signal, and judge whether the gas flow signal is in the rising or falling state stage through the state judgment algorithm. When the gas flow state is in the rising stage, calculate the current required gas flow value according to the preset gas supply parameters, and dynamically adjust the gas supply target value in combination with the flow frequency change trend.

[0076] Furthermore, according to the denoised gas flow signal, calculate the time-frequency characteristics of the signal, extract the period and change trend of the gas flow signal, and judge whether the gas flow signal is in the rising or falling state stage through the state judgment algorithm, specifically including:

[0077] Perform short-time Fourier transform on the denoised gas flow signal to obtain the time-frequency representation of the gas flow signal, and then extract the time-frequency characteristics of the gas flow signal, including flow frequency and flow amplitude characteristics.

[0078] According to the extracted flow frequency characteristics, calculate the gas flow period to obtain the start time and end time of each gas flow period, and then according to the extracted flow amplitude characteristics, calculate the gas flow change trend to obtain the change curve of the rising flow with time.

[0079] Based on the gas flow period and its changing trend, determine whether the current gas flow state is in the rising stage or the falling stage. When the gas flow shows an upward trend and is in the first half of the gas flow period, it is judged as the rising stage. When the gas flow shows a downward trend and is in the second half of the gas flow period, it is judged as the falling stage;

[0080] According to the judged gas flow state, output the current gas flow state and associate the gas flow state with the corresponding time points to obtain a complete gas flow state sequence.

[0081] Specifically, by calculating the time-frequency characteristics of the denoised gas flow signal, accurately extract the gas flow period and its changing trend, and then accurately judge whether the current gas flow state is in the rising or falling stage. And in the rising stage of gas flow, dynamically adjust the gas supply target value according to the preset parameters, realizing real-time and accurate monitoring and response to the user's gas flow state, enabling the gas supply to be dynamically adjusted according to the actual gas flow demand of the user, improving the accuracy and adaptability of the gas supply, and better meeting the user's gas flow demand.

[0082] Furthermore, after judging whether the gas flow signal is in the rising or falling state stage through the state judgment algorithm, it also includes:

[0083] According to the preset gas supply parameters and the real-time detected flow frequency data, use them as the input of the neural network model, and through the trained neural network model, calculate the gas flow target value required in the current rising stage of gas flow;

[0084] According to the calculated gas flow target value, combined with the flow frequency change trend data, adopt the fuzzy control algorithm to dynamically adjust the output flow of the gas supply device to make it gradually approach the target value;

[0085] During the adjustment process, real-time detect the flow frequency change and the gas flow change. When the flow frequency changes significantly or the deviation between the gas flow and the target value is large, trigger the neural network model to recalculate the gas flow target value;

[0086] Input the new gas flow target value calculated by the neural network model into the fuzzy control algorithm to perform another dynamic adjustment on the output flow of the gas supply device until the gas flow stabilizes near the new target value.

[0087] Continuously monitor the gas flow changes within multiple gas flow periods, calculate the average value and standard deviation of the gas flow, and judge whether the gas flow is stable within the target value range. When the gas flow is stable within the target value range for multiple consecutive gas flow periods, maintain the current gas supply strategy unchanged;

[0088] When the gas flow significantly deviates from the target value, the adjustment strategy is triggered, and parameters such as the flow frequency, gas flow target value, and actual output flow are written into the log file for subsequent analysis and optimization of the gas supply strategy.

[0089] Through the synergistic effect of the neural network and the fuzzy control algorithm, the real-time dynamic adjustment of the gas flow is achieved, ensuring that it accurately and stably meets the user's gas flow requirements. At the same time, key parameters are recorded to optimize the supply strategy, improving the intelligence and adaptability of the equipment.

[0090] S3. Adopt the 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;

[0091] Furthermore, adopt the 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, specifically including:

[0092] Obtain the target value and the actual flow value of the gas supply, calculate the deviation value between the two, input the deviation value 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;

[0093] According to the calculated opening and closing time of the solenoid valve, generate the corresponding control signal, output the generated control signal to the solenoid valve actuator, and control the opening and closing of the solenoid valve;

[0094] The solenoid valve adjusts the opening of the valve according to the received control signal, thereby changing the actual gas flow. By continuously obtaining the real-time gas flow value, comparing it with the target value, calculating the deviation value, a closed-loop control is formed.

[0095] By continuously iterating the above process, the actual gas flow value gradually approaches and stabilizes at the target value, achieving precise control of the gas supply.

[0096] Specifically, adopt the PID control algorithm. According to the deviation between the gas supply target value and the actual flow value, accurately calculate the opening and closing time of the solenoid valve and generate a control signal to output to the actuator. Through continuous closed-loop control and deviation value feedback, continuously adjust the opening of the solenoid valve, 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.

[0097] S4. Obtain the current gas supply pressure value through the opening feedback signal of the pressure regulating valve. Combine it with the preset pressure range to determine whether the opening of the pressure regulating valve needs to be adjusted. If the current pressure value exceeds the preset range, calculate the opening adjustment amount of the pressure regulating valve using the fuzzy control algorithm according to the pressure deviation value, generate a control signal and output it to the actuator of the pressure regulating valve; among them, this method is applicable to the pressure control of gases or liquids.

[0098] Further, obtain the current gas supply pressure value through the opening feedback signal of the pressure regulating valve. Combine it with the preset pressure range to determine whether the opening of the pressure regulating valve needs to be adjusted, specifically including:

[0099] Transmit the pressure value data to the control system, compare it with the preset pressure threshold range, and judge whether the current pressure is within a reasonable range. When the pressure value is lower than the lower threshold of the preset range, the control system issues an instruction to increase the opening of the pressure regulating valve through the actuator to increase the gas supply pressure;

[0100] When the pressure value is higher than the upper threshold of the preset range, the control system issues an instruction to decrease 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, obtain its outlet pressure value again until the pressure value is stable within the preset range.

[0101] During the pressure regulation process, analyze the historical pressure data through machine learning algorithms such as support vector machines or neural networks, establish a mapping model between the pressure value and the valve opening, and use the established mapping model to predict the optimal valve opening at the next moment according to the current pressure value to achieve the feedforward control of the pressure regulating valve and improve the dynamic response performance of the system.

[0102] Further, calculate the opening adjustment amount of the pressure regulating valve using the fuzzy control algorithm, generate a control signal and output it to the actuator of the pressure regulating valve, specifically including:

[0103] Obtain the current system pressure value in real time through the pressure sensor, compare the pressure value with the preset pressure range, and judge whether the pressure value exceeds the preset range.

[0104] When the pressure value exceeds the preset range, calculate the deviation value between the current pressure value and the median of the preset pressure range, use the deviation value as the input of the fuzzy control algorithm, and then calculate the opening adjustment amount of the pressure regulating valve through fuzzy inference according to the pressure deviation value using the pre-established fuzzy control rule base;

[0105] Convert the calculated opening adjustment amount of the pressure regulating valve into a corresponding control signal, convert the digital signal into an analog signal through the digital-to-analog converter, and output the generated analog control signal to the actuator of the pressure regulating valve to drive the actuator to adjust the opening of the pressure regulating valve;

[0106] The pressure regulating valve changes the valve opening according to the adjustment action of the actuator, thereby regulating the system pressure and bringing the pressure value back within the preset range.

[0107] Specifically, through the opening feedback of the pressure regulating valve and the fuzzy control algorithm, the gas supply pressure is accurately regulated and stabilized within the preset range. Combining with the mapping model established by the machine learning algorithm, feedforward control is realized, improving the dynamic response performance of the system, ensuring the stability and reliability of the gas supply pressure, and providing a safe and stable gas flow environment for users.

[0108] S5. According to the control response times of the solenoid valve and the pressure regulating valve, optimize the output timing of the control signal to make the dynamic adjustment process of the gas supply pressure and flow smooth and stable. Then, by real-time monitoring the change trends of the gas flow and gas supply parameters, dynamically update the preset parameters to match the change of the user's gas demand state and perform precise adjustment of the gas supply.

[0109] Furthermore, according to the control response times of the solenoid valve and the pressure regulating valve, optimize the output timing of the control signal to make the dynamic adjustment process of the gas supply pressure and flow smooth and stable, which specifically includes:

[0110] Obtain the control response time parameters of the solenoid valve and the pressure regulating valve, establish a valve dynamic model, obtain the relationship curves between the valve opening and the pressure and flow, and calculate the target opening of the valve and the output timing of the control signal through the valve dynamic model according to the target values of the gas supply pressure and flow;

[0111] Then, take the valve opening deviation and the pressure-flow deviation as inputs, and through fuzzy inference, obtain the optimized adjustment amount of the control signal. Send the optimized control signal to the solenoid valve and the pressure regulating valve in sequence according to the calculated output timing to realize the dynamic adjustment of the valve opening;

[0112] During the dynamic adjustment of the valve, real-time collect the pressure and flow data of the gas supply pipeline, compare them with the target values to obtain the pressure and flow deviations; when the pressure deviation or the flow deviation exceeds the preset threshold, take the deviation as a feedback signal and input it into the fuzzy control algorithm for further optimization adjustment of the control signal;

[0113] By continuously repeating the above processes of pressure-flow data collection, deviation calculation, and control optimization until the gas supply pressure and flow are stable at the target values, smooth dynamic adjustment is achieved.

[0114] Furthermore, by real-time monitoring the change trends of the gas flow and gas supply parameters, dynamically update the preset parameters to match the change of the user's gas demand state and perform precise adjustment of the gas supply, which specifically includes:

[0115] 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, trigger an alarm, and determine the amplitude of the gas supply parameter to be adjusted according to the degree of deviation from the normal range;

[0116] Through machine learning algorithms, based on the change trends of the user's historical gas flow signals and gas supply parameters, predict the change trend of the user's gas flow state in the next period of time; then, according to the user's real-time gas flow signal, current gas supply parameters, and the predicted future gas flow state change trend, dynamically adjust the gas supply parameters to generate a new gas supply parameter setting;

[0117] Send the dynamically adjusted gas supply parameter setting to the gas supply device, and the control device adjusts the gas supply in real time according to the new parameter setting to match the user's real-time gas flow state;

[0118] After adjusting the gas supply parameters, continuously monitor the change of the user's gas flow signal to determine whether the user's gas flow state returns to normal. If it does not return to normal, return to continue the adjustment;

[0119] Store data such as the user's real-time gas flow signal, gas supply parameters, and the effect after adjustment in the database to optimize the machine learning model and improve the accuracy of future prediction and adjustment.

[0120] Specifically, by optimizing the control signal output timing and real-time monitoring to update the preset parameters, smooth and stable adjustment of the gas supply pressure and flow is achieved, as well as precise matching of the change of the user's gas flow state, improving the comfort and adaptability of the gas supply, and ensuring that the user can obtain continuous and stable gas flow support.

[0121] Example 2: Please refer to Figure 3 , this example provides an oxygen supply control system based on the gas flow signal for implementing the oxygen supply control method based on the gas flow signal, including:

[0122] A gas flow processing module, which obtains the gas flow signal from a pressure sensor, performs multi-scale decomposition on it using the wavelet transform algorithm, extracts and filters out the high-frequency noise components, and then performs wavelet reconstruction and smoothing processing, and finally outputs a smooth gas flow signal;

[0123] The gas flow calculation module calculates the time-frequency characteristics based on the denoised gas flow signal, extracts the gas flow period and change trend, and judges the current gas flow state. When in the flow rising stage, it combines the preset parameters and real-time flow frequency data, calculates the gas flow target value through a neural network model, and uses a fuzzy control algorithm to dynamically adjust the output flow of the gas supply device to meet the gas flow requirements of users in different stages;

[0124] The solenoid valve control module uses a 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, generates a control signal and outputs it to the solenoid valve actuator to control the opening and closing of the solenoid valve, adjusts the valve opening to change the actual gas flow, and stabilizes the gas flow at the target value through closed-loop control to perform precise gas supply control;

[0125] The pressure regulation module obtains the current gas supply pressure value through the opening feedback signal of the pressure regulating valve, combines it with the preset pressure range for judgment. When the pressure value exceeds the preset range, it calculates the opening adjustment amount of the pressure regulating valve based on the pressure deviation value using a fuzzy control algorithm, generates a control signal and outputs it to the actuator to drive it to adjust the valve opening and regulate the system pressure to ensure that the gas supply pressure is stable within the preset range;

[0126] The dynamic adjustment and optimization module comprehensively considers the control response times of the solenoid valve and the pressure regulating valve, optimizes the output timing of the control signal to make the dynamic adjustment process of the gas supply pressure and flow smooth and stable. By real-time monitoring the gas flow signal and the change trend of the gas supply parameters, it dynamically updates the preset parameters to match the change of the user's gas flow state, realizes the precise adjustment of the gas supply, and stores the relevant data in the database for optimizing the machine learning model to improve the prediction and adjustment accuracy.

[0127] The above is only a preferred embodiment of the present invention and does not impose any form of limitation on the present invention. Although the present invention has been disclosed above with a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the above-disclosed technical content to form an equivalent embodiment within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention still fall 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 trend 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. Among them, 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, 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.

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: 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.

9. 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 8, 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. By real-time monitoring of the gas flow signal and the change trend of the gas supply parameters, it dynamically updates the preset parameters, matches the user's gas flow state changes, and accurately adjusts the gas supply. The relevant data is stored in the database for optimizing the machine learning model. Among them, the control response time of the solenoid valve and the pressure regulating valve is integrated to optimize the control signal output timing, so that the dynamic adjustment process of the gas supply pressure and flow is 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.

Images