An oxygen concentration continuous monitoring device and method

Abstract

The present invention relates to the technical field of analysis and processing of physical properties of materials, and particularly relates to an oxygen concentration continuous monitoring device and method. The method includes: acquiring oxygen concentration data and corresponding multi-dimensional environmental factor data; determining the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data; performing empirical mode decomposition on the oxygen concentration data and the single-dimensional environmental factor data to obtain multiple pairs of nodes of IMF components; determining the influence weights between the oxygen concentration IMF components and the single-dimensional environmental factor IMF components in each pair of nodes; using the influence weights to determine the influence stability of each single-dimensional environmental factor IMF component on the oxygen concentration data; using the influence stability to determine the target environmental compensation model, and using the target environmental compensation model to correct the oxygen concentration measurement value. Through the oxygen concentration continuous monitoring method of the present invention, the accuracy and timeliness of the oxygen concentration monitoring data are ensured, and the accuracy and reliability of the oxygen concentration monitoring system are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of analysis and processing of physical properties of materials, and particularly relates to an oxygen concentration continuous monitoring device and method. Background Art

[0002] Medical molecular sieve oxygen generation devices separate nitrogen and oxygen in the air through molecular sieve materials (such as zeolites). After the air is pretreated, the molecular sieve adsorbs nitrogen under low pressure and releases oxygen with a higher concentration. In medical molecular sieve oxygen generation devices, it is crucial to accurately monitor the concentration of the produced oxygen. In order to maintain the oxygen-using state of the medical device, an oxygen monitor is used to continuously monitor the oxygen concentration at the tail of the oxygen storage tank when the oxygen generation device is working. The instrument sends the data to the control device through a sensor to ensure that the oxygen concentration always remains within the medical standard range and to ensure that the provided oxygen meets the clinical requirements.

[0003] During the process of continuously monitoring the oxygen concentration using an electrochemical oxygen sensor, the changes in temperature, humidity, and pressure in different environments will affect the detection results of the oxygen detector. Moreover, the influence of environmental factors on the oxygen concentration detection is not completely real-time, that is, it has a certain time delay. The existence of these errors will affect the accuracy and timeliness of the oxygen concentration monitoring data, resulting in instability in the oxygen supply quality of the oxygen generation device. Summary of the Invention

[0004] In order to solve the technical problem of low accuracy and timeliness of the detection results of oxygen concentration under different environmental factors, the purpose of the present invention is to provide an oxygen concentration continuous monitoring device and method, and the specific technical solutions adopted are as follows:

[0005] The present invention provides an oxygen concentration continuous monitoring method, and the method includes:

[0006] Obtain oxygen concentration data and corresponding multi-dimensional environmental factor data;

[0007] Determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data;

[0008] Perform empirical mode decomposition on the oxygen concentration data and the single-dimensional environmental factor data to obtain multiple pairs of nodes of IMF components;

[0009] Use the comprehensive time delay to determine the influence weight between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component in each pair of nodes;

[0010] Use the influence weight to determine the influence stability of each single-dimensional environmental factor IMF component on the oxygen concentration data;

[0011] Use the influence stability to determine the target environmental compensation model, and use the target environmental compensation model to correct the oxygen concentration measurement value;

[0012] Among them, each pair of nodes includes an oxygen concentration IMF component and a one-dimensional environmental factor IMF component.

[0013] Further, the steps of determining the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data include:

[0014] Determine the response time delay of the oxygen concentration data relative to the one-dimensional environmental factor data;

[0015] Using the response time delay, determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0016] Further, the steps of determining the response time delay of the oxygen concentration data relative to the one-dimensional environmental factor data include:

[0017] Determine the Pearson coefficient between the oxygen concentration data and the one-dimensional environmental factor data;

[0018] When the Pearson coefficient is the largest, obtain the response time delay of the oxygen concentration data relative to the one-dimensional environmental factor data.

[0019] Further, the steps of using the response time delay to determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data include:

[0020] Determine the DTW distance between the oxygen concentration data and the one-dimensional environmental factor data;

[0021] Using the response time delay and the DTW distance, calculate the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0022] Further, the steps of using the comprehensive time delay to determine the influence weight between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component in each pair of nodes include:

[0023] Set a sliding window on each pair of nodes, and use the comprehensive time delay and the data information within the sliding window to determine the correlation between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component;

[0024] Using the correlation and the number of sliding windows in each pair of nodes, determine the influence weight between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component.

[0025] Further, the steps of using the comprehensive time delay and the data information within the sliding window to determine the correlation between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component include:

[0026] Determine the number of data within the sliding window;

[0027] Determine the data values of the same serial numbers between the IMF components of the oxygen concentration and the IMF components of the single-dimensional environmental factors within the sliding window;

[0028] Using the comprehensive time delay, the number of the data, and the data values, calculate the correlation between the IMF components of the oxygen concentration and the IMF components of the single-dimensional environmental factors.

[0029] Further, the steps of determining the influence stability of each single-dimensional environmental factor IMF component on the oxygen concentration data by using the influence weight include:

[0030] Determine the average value of the influence weights between the IMF components of the single-dimensional environmental factors and all the IMF components of the oxygen concentration;

[0031] Using the influence weight, the average value of the influence weights, and the number of the IMF components of the oxygen concentration, calculate the influence stability of each single-dimensional environmental factor IMF component on the oxygen concentration data.

[0032] Further, the steps of determining the target environmental compensation model by using the influence stability include:

[0033] Assign corresponding weights to each single-dimensional environmental factor IMF component by using the influence stability;

[0034] Perform weighted reconstruction on the IMF components of the oxygen concentration by using the weights to obtain the target environmental compensation model.

[0035] Further, the steps of correcting the oxygen concentration measurement value by using the target environmental compensation model include:

[0036] Input the real-time environmental factor data and the real-time oxygen concentration measurement data into the target environmental compensation model to obtain the expected value of the oxygen concentration;

[0037] Determine the deviation between the oxygen concentration measurement value and the expected value of the oxygen concentration, and correct the oxygen concentration measurement value by using the deviation.

[0038] The present invention also provides an oxygen concentration continuous monitoring device, which is used to implement the oxygen concentration continuous monitoring method described in any one of the above; the device includes:

[0039] A signal monitoring module, which is used to acquire the oxygen concentration data and the corresponding multi-dimensional environmental factor data;

[0040] A time delay analysis module, which is used to determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data;

[0041] The component processing module is used to perform empirical mode decomposition on the oxygen concentration data and the one-dimensional environmental factor data to obtain multiple pairs of nodes of the IMF components; use the comprehensive time delay to determine the influence weights between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component in each pair of nodes; use the influence weights to determine the influence stability of each one-dimensional environmental factor IMF component on the oxygen concentration data;

[0042] The measurement compensation module is used to determine the target environmental compensation model by using the influence stability and correct the oxygen concentration measurement value by using the target environmental compensation model.

[0043] The present invention has the following beneficial effects:

[0044] The present invention determines the influence weights of environmental factors according to various environmental factors such as temperature, humidity, and pressure, and combines the time delay of the influence to construct a prediction model to predict the future change of the oxygen concentration and correct the error of the oxygen concentration data detection result caused by the external environment in real time. Specifically:

[0045] First, by considering the interference of various environmental factors on the oxygen concentration monitoring signal (data) and combining the time delay factor for adjustment, it can more accurately reflect the change of the oxygen concentration and avoid errors caused by external factors;

[0046] Second, through EMD decomposition and stability analysis of the influence weights, it can dynamically adapt to environmental changes, construct a highly adaptable prediction model, which can not only handle complex non-linear relationships, but also cope with multiple interferences of different environmental factors on the monitoring signal, and improve the intelligent level of the oxygen monitoring system;

[0047] Third, calculate and correct the deviation of the oxygen monitoring data in real time, so that the monitoring system can adapt to changes under different environmental conditions, ensure the accuracy and timeliness of the monitoring data, and effectively improve the accuracy and reliability of the oxygen concentration monitoring system. Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 It is a step flow chart of a method for continuous monitoring of oxygen concentration provided by an embodiment of the present invention;

[0050] Figure 2The detailed flowchart of step S2 in a method for continuous oxygen concentration monitoring provided by an embodiment of the present invention;

[0051] Figure 3 The detailed flowchart of step S4 in a method for continuous oxygen concentration monitoring provided by an embodiment of the present invention;

[0052] Figure 4 The detailed flowchart of step S5 in a method for continuous oxygen concentration monitoring provided by an embodiment of the present invention;

[0053] Figure 5 The structural schematic diagram of the hardware operating environment of the continuous oxygen concentration monitoring device involved in the embodiment solution of the present invention;

[0054] Figure 6 The framework structural schematic diagram of the continuous oxygen concentration monitoring device involved in the embodiment solution of the present invention. Detailed implementation manners

[0055] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following combines the drawings and preferred embodiments to specifically describe a method for continuous oxygen concentration monitoring proposed by the present invention, including its specific implementation manners, structures, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0057] The following specifically describes the specific solutions of a continuous oxygen concentration monitoring device and method provided by the present invention with reference to the drawings.

[0058] Embodiment 1:

[0059] For a method for continuous oxygen concentration monitoring provided by the present invention. Please refer to Figure 1 , which shows the step flowchart of the continuous oxygen concentration monitoring method provided by an embodiment of the present invention.

[0060] The method includes:

[0061] Step S1, obtaining oxygen concentration data and corresponding multi-dimensional environmental factor data;

[0062] This embodiment can be applied to a medical molecular sieve oxygen generation system, and the specific scenario can be:

[0063] Electrochemical oxygen sensors have advantages such as low cost and fast response, but their measurement accuracy is easily affected by environmental temperature and humidity. When the environmental humidity is high, water molecules may interfere with the electrochemical reaction of the sensor, resulting in deviation in the measurement of oxygen concentration; temperature changes will also affect the chemical reaction rate inside the sensor, thus affecting the accuracy of the readings. In addition, pressure will also affect the monitoring of oxygen concentration by the sensor. These problems may lead to unstable monitoring results of oxygen concentration in practical applications, especially in the case of long-term operation or large fluctuations in environmental conditions, causing trouble for the precise control of oxygen output.

[0064] An electrochemical oxygen sensor can be selected to detect oxygen concentration data, and at the same time, temperature, humidity, and air pressure sensors are set to collect real-time multi-dimensional environmental factor data when the gas passes through the electrochemical oxygen sensor. A number of sensors perform synchronous collection to obtain oxygen concentration data (i.e., oxygen concentration signal) and corresponding multi-dimensional environmental factor data (i.e., multi-dimensional environmental factor signal). Among them, temperature, humidity, and air pressure each correspond to one dimension, that is, they correspond to their respective single-dimensional environmental factor data.

[0065] Step S2, determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data;

[0066] Please refer to Figure 2 , the said step S2 specifically includes:

[0067] Step S21, determine the response time delay of the oxygen concentration data relative to the single-dimensional environmental factor data;

[0068] Step S22, use the said response time delay to determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0069] More specifically, in one embodiment, step S21 includes:

[0070] Determine the Pearson coefficient between the oxygen concentration data and the single-dimensional environmental factor data;

[0071] When the Pearson coefficient is the largest, obtain the response time delay of the oxygen concentration data relative to the single-dimensional environmental factor data.

[0072] More specifically, in one embodiment, step S22 includes:

[0073] Determine the DTW distance between the oxygen concentration data and the single-dimensional environmental factor data;

[0074] Use the said response time delay and DTW distance to calculate the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0075] During the use of a medical molecular sieve oxygen generation system, due to various reasons such as compressor aging, the environmental factors such as temperature, humidity, and pressure during the oxygen generator's output of gas may not be stable enough. These environmental factors affect the reaction rate of oxygen molecules with the electrolyte on the sensor surface, thereby changing the monitoring signal of the electrochemical oxygen sensor, resulting in an unstable situation for the actual oxygen concentration signal detected by using the electrochemical oxygen sensor. Therefore, it is necessary to calculate the delay of the influence of different environmental data on the detection of the oxygen concentration signal.

[0076] First, analyze the response delay of the influence degree of a single environmental index on the change of oxygen concentration:

[0077] The detection principle of the electrochemical oxygen sensor depends on the catalytic reaction. Temperature changes will affect the solubility, diffusion rate, and the speed of the electrochemical reaction of oxygen. Generally, an increase in temperature will accelerate the reaction rate, thereby affecting the response of the oxygen sensor; humidity changes affect the conductivity of the electrolyte of the sensor. Excessive humidity may cause liquid accumulation inside the sensor or change the properties of the electrolyte, resulting in signal deviation; the pressure change caused by the gas flow rate will directly affect the concentration distribution of oxygen molecules, and thus affect the reaction of oxygen molecules on the sensor. The influences of temperature, humidity, and pressure on the oxygen concentration signal, although achieved through different physical processes, their influence mechanisms essentially affect the reaction efficiency of oxygen on the sensor surface or the working environment of the oxygen sensor, so they will show consistency.

[0078] After the compressed gas passes through the oxygen generation main unit, the temperature, humidity, and gas flow rate will change. When these changes pass through the electrochemical oxygen sensor, it causes a certain delay in the monitoring result of the sensor for oxygen data. Determining the specific time delay can help determine the influence weight of different working environments on the detection data error of the final electrochemical oxygen sensor, and then ensure that the correction parameters for adjusting the electrochemical oxygen sensor are accurate and effective.

[0079] Based on the analysis of the above principle, calculate the response delay of the electrochemical oxygen sensor compared to the detection signal of the temperature sensor (i.e., the response delay of the oxygen concentration data relative to the single-dimensional environmental factor data of temperature) :

[0080] ;

[0081] Among them, represents the response delay of the electrochemical oxygen sensor compared to the detection signal of the temperature sensor, represents the function of finding the maximum point, that is, the corresponding when the correlation coefficient reaches the maximum; represents the Pearson correlation coefficient between two signal data sequences (i.e., oxygen concentration data and single-dimensional environmental factor data); represents the current moment; represents the length of the selected signal data sequence (the two sequences have the same length); represents the detection signal data of the electrochemical oxygen sensor at time (i.e., the corresponding oxygen concentration data, referring to the data points here); represents the detection signal of the temperature sensor at time (i.e., the corresponding one-dimensional environmental factor data, referring to the data points here). Δt represents the time delay between the data points of the two sequences.

[0082] The Pearson correlation coefficient reflects the linear relationship between these two signal sequences. The closer it is to 1, the stronger the correlation between the signals. Based on the two sequences, a window is set on the two sequences. The signal data sequence within the time window can be selected as needed. By calculating the Pearson correlation coefficient between the signal data points of the two sequences within the window, different time delays Δt between the data points can be obtained, and the time delay Δt that maximizes the correlation coefficient can be found. By finding an optimal time offset, the correlation between the two signal sequences can be made the strongest.

[0083] Similarly, the response time delay of the electrochemical oxygen sensor compared to the humidity sensor can be obtained ; the response time delay of the electrochemical oxygen sensor compared to the pressure sensor .

[0084] Secondly, based on each response time delay, the final time delay factor, i.e., the comprehensive time delay, is obtained:

[0085] By the response time delays of temperature, humidity, and pressure respectively, the final time lag is corrected to obtain the final time delay factor. The influence degrees of different environmental factors on the measurement of oxygen concentration are inconsistent. When the influence degree of an environmental factor in a certain dimension on the measurement of oxygen concentration is large, the DTW (Dynamic Time Warping) distance between the two data sequences is large. Then, the weight of the response time delay corresponding to this factor should be higher at this time. Calculate the DTW distances of temperature, humidity, and pressure on the detection result of oxygen concentration respectively, and use them as the weights of the response time delays for weighting to obtain the final time delay factor:

[0086] ;

[0087] ;

[0088] Among them, represents the comprehensive time delay, represents the response time delay of the electrochemical oxygen sensor compared to the detection signal of the temperature sensor, represents the DTW distance between the temperature detection signal and the oxygen concentration detection signal; Indicates the response delay of the electrochemical oxygen sensor compared to the humidity sensor, Indicates the DTW distance between the temperature detection signal and the oxygen concentration detection signal; Indicates the response delay of the electrochemical oxygen sensor compared to the pressure sensor, Indicates the DTW distance between the temperature detection signal and the oxygen concentration detection signal.

[0089] Step S3, perform empirical mode decomposition on the oxygen concentration data and the single-dimensional environmental factor data to obtain multiple pairs of nodes of the IMF components;

[0090] Use the EMD (Empirical Mode Decomposition) algorithm to decompose the collected oxygen concentration signal and the environmental factor signals of several dimensions. The decomposition process is a well-known prior art. After obtaining different groups of IMF (Intrinsic Mode Function) components, the analysis of these components can be started.

[0091] The EMD algorithm decomposes a complex signal into several intrinsic mode functions (IMFs), which helps to extract the local time-frequency characteristics of the signal data. These IMF components represent the vibration modes of different frequencies in the original signal. Higher IMF components represent high-frequency instantaneous fluctuations, and lower components represent the long-term trend of the signal. The oxygen concentration signal is affected by various environmental factors, resulting in different time-frequency changes. By analyzing the correlation between the IMF components of different components, the influence weights of different environmental factors can be determined, and the influence of different environmental factors on the oxygen concentration can be identified and quantified more accurately.

[0092] A pair of nodes can be formed by combining any oxygen concentration IMF component and any single-dimensional environmental factor IMF component. Among them, each pair of nodes includes an oxygen concentration IMF component and a single-dimensional environmental factor IMF component.

[0093] Step S4, use the comprehensive delay to determine the influence weight between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component in each pair of nodes;

[0094] Please refer to Figure 3 , the specific content of step S4 includes:

[0095] Step S41, set a sliding window on each pair of nodes, and use the comprehensive delay and the data information within the sliding window to determine the correlation between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component;

[0096] More specifically, the steps of determining the correlation between the IMF component of oxygen concentration and the IMF component of one-dimensional environmental factors by using the comprehensive time delay and the data information within the sliding window include:

[0097] Determine the number of data within the sliding window;

[0098] Determine the numerical values of the data with the same serial number between the IMF component of oxygen concentration and the IMF component of one-dimensional environmental factors within the sliding window;

[0099] Using the comprehensive time delay, the number of data, and the numerical values of the data, calculate the correlation between the IMF component of oxygen concentration and the IMF component of one-dimensional environmental factors.

[0100] Step S42: Determine the influence weight between the IMF component of oxygen concentration and the IMF component of one-dimensional environmental factors by using the correlation and the number of sliding windows in each pair of nodes.

[0101] Taking the oxygen concentration signal data as a reference, construct a bipartite graph, where one set of nodes represents the IMF components of oxygen concentration, and the other set of nodes represents the IMF components of different environmental factors. Set a sliding window (the window size is an integer multiple of the comprehensive time delay of the above signal data) on each pair of nodes, and calculate the influence weight of different environmental factors on different oxygen concentration components in the nodes.

[0102] The sliding window can capture the short-term fluctuations of the signal, which helps to identify and compensate for the short-term changes caused by environmental factors. In the sliding window corresponding to the same pair of nodes, when the signal change trends at the corresponding positions within the window are more similar, it indicates that the correlation within the corresponding window is closer.

[0103] For the sliding window within each pair of nodes (an IMF component of oxygen concentration and an IMF component of an environmental factor), calculate the correlation between the IMF component of oxygen concentration and the IMF component of the one-dimensional environmental factor signal:

[0104] ;

[0105] where represents the correlation between the i-th IMF component of oxygen concentration and the j-th IMF component of the environmental factor signal in the v-th sliding window; represents the numerical value (data value) of the r-th signal data within the v-th sliding window in the i-th IMF component of oxygen concentration; represents the numerical value (data value) of the r-th signal data within the v-th sliding window in the j-th IMF component of the environmental factor signal; It represents the comprehensive time delay; m represents the number of signal data within the sliding window (the number of data refers to the number of data of the oxygen concentration IMF component or the single-dimensional environmental factor IMF component within the sliding window, and the two are the same quantity); corr() represents the cross-correlation function.

[0106] It represents calculating the data correlation between the i-th IMF component of the oxygen concentration and the j-th IMF component of the environmental factor signal within the same sliding window using the cross-correlation function corr, and then dividing by the time delay factor to eliminate the influence of the response time delay on the data measured by the sensor; summing and averaging the corresponding several data correlations within the window to obtain the average correlation between the two signal components within the same window, which can represent the influence degree of the environmental factor signal on the oxygen concentration detected by the sensor within the sliding window.

[0107] According to several sliding windows corresponding to each pair of nodes, calculate the influence weights between the components:

[0108] ;

[0109] Among them, It represents the influence weight between the i-th IMF component of the oxygen concentration and the j-th IMF component of the environmental factor signal; It represents the correlation between the i-th IMF component of the oxygen concentration and the j-th IMF component of the environmental factor signal in the v-th sliding window; N represents the number of sliding windows corresponding to each pair of nodes.

[0110] Step S5, using the influence weights, determine the influence stability of each single-dimensional environmental factor IMF component on the oxygen concentration data;

[0111] Please refer to Figure 4 , the specific content of step S5 includes:

[0112] Step S51, determine the average value of the influence weights between the single-dimensional environmental factor IMF component and all oxygen concentration IMF components;

[0113] Step S52, using the influence weights, the average value of the influence weights, and the number of oxygen concentration IMF components, calculate the influence stability of each single-dimensional environmental factor IMF component on the oxygen concentration data.

[0114] Affecting the stability of the weight, that is, affecting the stability, refers to whether the influence of an environmental factor in a certain dimension on the oxygen concentration remains consistent under different environmental conditions. Under different temperature, humidity, and pressure states, the stability of the signal data is different. By calculating the stability of the weight, it is possible to identify which environmental factors have a relatively stable influence and which factors may be affected by other external interferences. If the influence weight of an environmental factor fluctuates greatly, it may mean that the influence of this factor is relatively unstable under different conditions.

[0115] Compare the stability of the influence weights of the signal nodes of the same environmental factor on the oxygen concentration signals with different oxygen concentrations to obtain the final influence relationship:

[0116] ;

[0117] wherein, represents the stability of the influence of the j-th IMF component of the single-dimensional environmental factor signal on the oxygen concentration signal, that is, the influence stability; represents the influence weight between the i-th IMF component of the oxygen concentration and the j-th IMF component of the environmental factor signal; represents the average value of the influence weights between the j-th IMF component of the environmental factor signal and all the IMF components of the oxygen concentration; represents the number of IMF components of the oxygen concentration.

[0118] Step S6, use the influence stability to determine the target environmental compensation model, and use the target environmental compensation model to correct the measured value of the oxygen concentration;

[0119] Specifically, the steps of using the influence stability to determine the target environmental compensation model include:

[0120] Use the influence stability to assign corresponding weights to each single-dimensional environmental factor IMF component;

[0121] Use the weights to perform weighted reconstruction on the oxygen concentration IMF components to obtain the target environmental compensation model.

[0122] After calculating the stability of the influence of each environmental factor component on the oxygen concentration signal, different weights are assigned to each environmental factor component with the influence stability as the weight, and the weighted reconstruction of the IMF components of the oxygen concentration is performed using these weights to establish the target environmental compensation model, and then the oxygen concentration corrected based on the environmental factors can be obtained.

[0123] Specifically, the steps of using the target environmental compensation model to correct the measured value of the oxygen concentration include:

[0124] Input the real-time environmental factor data and the real-time oxygen concentration measurement data into the target environmental compensation model to obtain the expected value of the oxygen concentration;

[0125] Determine the deviation between the measured oxygen concentration value and the expected oxygen concentration value, and correct the measured oxygen concentration value by using the deviation.

[0126] Continuously obtain real-time environmental factor signals and oxygen concentration measurement data , input them into the above environmental compensation model. Through this prediction model, the expected value of the oxygen concentration based on the changes in environmental factors within a certain future time period can be obtained. . Then, compare the expected value with the actual monitoring data and calculate the deviation between the two.

[0127] ;

[0128] Among them, represents the deviation between the expected value and the actual monitoring value (measured oxygen concentration value); represents the expected value of the oxygen concentration; represents the monitored value of the real-time oxygen concentration, that is, the measured oxygen concentration value.

[0129] A threshold A can also be set as needed. For example, A = 0.3. Compare the deviation between the expected value and the actual monitoring value. When the deviation occurs, it indicates that the electrochemical oxygen concentration sensor may have failed or there is an unexpected situation, resulting in too large a deviation between the predicted expected value and the actual monitoring value. A real-time warning needs to be issued, and the staff further analyzes and checks the prediction model, monitoring data, and environmental factors to determine the specific reason for the too large deviation and take corresponding measures for improvement.

[0130] When the deviation occurs, according to the influence of the deviation, output the obtained real-time correction value:

[0131] ;

[0132] Among them, represents the correction value of the oxygen concentration monitoring; represents the monitored value of the real-time oxygen concentration; represents the deviation between the expected value and the actual monitoring value.

[0133] The present invention determines the influence weight of environmental factors according to various environmental factors such as temperature, humidity, and pressure, and combines the delay of the influence to construct a prediction model to predict the future change of the oxygen concentration and correct the error of the oxygen concentration data detection result caused by the external environment in real time. Specifically:

[0134] In the first aspect, by considering the interference of various environmental factors on the oxygen concentration monitoring signal (data) and making adjustments in combination with the time delay factor, it is possible to more accurately reflect the change in oxygen concentration and avoid errors caused by external factors.

[0135] In the second aspect, through EMD decomposition and stability analysis of influence weights, it is possible to dynamically adapt to environmental changes, construct a highly adaptable prediction model, which can not only handle complex non-linear relationships but also cope with multiple interferences of different environmental factors on the monitoring signal, thus enhancing the intelligent level of the oxygen monitoring system.

[0136] In the third aspect, by calculating and correcting the real-time deviation of the oxygen monitoring data, the monitoring system can adapt to changes under different environmental conditions, ensuring the accuracy and timeliness of the monitoring data, and effectively enhancing the accuracy and reliability of the oxygen concentration monitoring system.

[0137] Embodiment 2:

[0138] The embodiment of the present invention also provides an oxygen concentration continuous monitoring device. The oxygen concentration continuous monitoring device can be a data processing device such as a computer, a server, an oxygen monitoring device, a signal detection and analysis device, or a combination of multiple devices.

[0139] As Figure 5 shown, Figure 5 it is a schematic structural diagram of the hardware operating environment of the oxygen concentration continuous monitoring device involved in the embodiment of the present invention.

[0140] As Figure 5 shown, the oxygen concentration continuous monitoring device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display (Display) and an input unit such as a control panel. Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WIFI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001. Those skilled in the art can understand that Figure 5 the hardware structure shown in

[0141] does not limit the device, and it may include more or fewer components than shown, or combine some components, or have a different component layout. Figure 5 Figure 5 ​The memory 1005 as a computer-readable storage medium may include an operating system, a user interface module, a network communication module, and an oxygen concentration continuous monitoring program.

[0142] In Figure 5 the network communication module is mainly used to connect to the server and can communicate with the server for data; while the processor 1001 can call the oxygen concentration continuous monitoring program stored in the memory 1005 and execute the steps in each of the above embodiments.

[0143] Based on the above hardware structure of the oxygen concentration continuous monitoring device, each embodiment for implementing the oxygen concentration continuous monitoring method of the present invention is realized.

[0144] In addition, the present invention further provides an oxygen concentration continuous monitoring device. Please refer to Figure 6 wherein the oxygen concentration continuous monitoring device includes:

[0145] a signal monitoring module A10 for acquiring oxygen concentration data and corresponding multi-dimensional environmental factor data;

[0146] a time delay analysis module A20 for determining the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data;

[0147] a component processing module A30 for performing empirical mode decomposition on the oxygen concentration data and the one-dimensional environmental factor data to obtain multiple pairs of nodes of IMF components; using the comprehensive time delay to determine the influence weight between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component in each pair of nodes; using the influence weight to determine the influence stability of each one-dimensional environmental factor IMF component on the oxygen concentration data;

[0148] a measurement compensation module A40 for determining a target environmental compensation model using the influence stability and correcting the oxygen concentration measurement value using the target environmental compensation model.

[0149] Further, the time delay analysis module A20 is further used for:

[0150] determining the response time delay of the oxygen concentration data relative to the one-dimensional environmental factor data;

[0151] using the response time delay to determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0152] Further, the time delay analysis module A20 is further used for:

[0153] determining the Pearson coefficient between the oxygen concentration data and the one-dimensional environmental factor data;

[0154] When the Pearson coefficient is at its maximum, the response delay of the oxygen concentration data with respect to the single-dimensional environmental factor data is obtained.

[0155] Furthermore, the delay analysis module A20 is further configured to:

[0156] Determine the DTW distance between the oxygen concentration data and the single-dimensional environmental factor data;

[0157] Using the response delay and the DTW distance, calculate the comprehensive delay of the oxygen concentration data with respect to the multi-dimensional environmental factor data.

[0158] Furthermore, the component processing module A30 is further configured to:

[0159] Set a sliding window on each pair of nodes, and determine the correlation between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component using the comprehensive delay and the data information within the sliding window;

[0160] Using the correlation and the number of sliding windows in each pair of nodes, determine the influence weight between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component.

[0161] Furthermore, the component processing module A30 is further configured to:

[0162] Determine the number of data within the sliding window;

[0163] Determine the data values of the same serial numbers between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component within the sliding window;

[0164] Using the comprehensive delay, the number of data, and the data values, calculate the correlation between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component.

[0165] Furthermore, the component processing module A30 is further configured to:

[0166] Determine the average value of the influence weights between the single-dimensional environmental factor IMF component and all oxygen concentration IMF components;

[0167] Using the influence weight, the average value of the influence weights, and the number of oxygen concentration IMF components, calculate the influence stability of each single-dimensional environmental factor IMF component on the oxygen concentration data.

[0168] Furthermore, the measurement compensation module A40 is further configured to:

[0169] Allocate corresponding weights to each single-dimensional environmental factor IMF component using the influence stability;

[0170] Reconstruct the IMF components of the oxygen concentration with weighted using the said weights to obtain the target environmental compensation model.

[0171] Furthermore, the measurement compensation module A40 is further configured to:

[0172] Input the real-time environmental factor data and the real-time oxygen concentration measurement data into the target environmental compensation model to obtain the expected value of the oxygen concentration;

[0173] Determine the deviation between the measured value of the oxygen concentration and the expected value of the oxygen concentration, and correct the measured value of the oxygen concentration using the said deviation.

[0174] The specific implementation manner of the oxygen concentration continuous monitoring device of the present invention is basically the same as that of each embodiment of the above oxygen concentration continuous monitoring method, and will not be described in detail here.

[0175] In addition, the present invention also provides a computer-readable storage medium. A oxygen concentration continuous monitoring program is stored on the computer-readable storage medium of the present invention. When the oxygen concentration continuous monitoring program is executed by a processor, the steps of the oxygen concentration continuous monitoring method as described above are implemented.

[0176] Among them, the method implemented when the oxygen concentration continuous monitoring program is executed can refer to each embodiment of the oxygen concentration continuous monitoring method of the present invention, and will not be described in detail here.

[0177] It should be noted that: the above sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0178] Each embodiment in this specification is described in a progressive manner, and the same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0179] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device, or a computer program product. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0180] The above are only the preferred embodiments of the present invention, and do not thereby limit the protection scope of the present invention. Any equivalent structure / method transformation made by using the content of the specification and drawings of the present invention under the inventive concept of the present invention, or any direct / indirect application in other related technical fields shall be included in the protection scope of the present invention.

Claims

1. A method for continuously monitoring the oxygen concentration of an electrochemical oxygen sensor, characterized in that, The method includes: Obtaining oxygen concentration data and corresponding multi-dimensional environmental factor data; Determining the comprehensive time delay of the oxygen concentration data with respect to the multi-dimensional environmental factor data; Performing empirical mode decomposition on the oxygen concentration data and the single-dimensional environmental factor data to obtain multiple pairs of nodes of IMF components; Using the comprehensive time delay to determine the influence weight between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component in each pair of nodes; Using the influence weight to determine the influence stability of each single-dimensional environmental factor IMF component on the oxygen concentration data; Using the influence stability to determine the target environmental compensation model, and using the target environmental compensation model to correct the oxygen concentration measurement value; Wherein, each pair of nodes includes an oxygen concentration IMF component and a single-dimensional environmental factor IMF component; The step of determining the comprehensive time delay of the oxygen concentration data with respect to the multi-dimensional environmental factor data includes: Determining the response time delay of the oxygen concentration data with respect to the single-dimensional environmental factor data; Using the response time delay to determine the comprehensive time delay of the oxygen concentration data with respect to the multi-dimensional environmental factor data; The step of determining the response time delay of the oxygen concentration data with respect to the single-dimensional environmental factor data includes: Determining the Pearson coefficient between the oxygen concentration data and the single-dimensional environmental factor data; When the Pearson coefficient is the largest, obtaining the response time delay of the oxygen concentration data with respect to the single-dimensional environmental factor data; The step of using the response time delay to determine the comprehensive time delay of the oxygen concentration data with respect to the multi-dimensional environmental factor data includes: Determining the DTW distance between the oxygen concentration data and the single-dimensional environmental factor data; Using the response time delay and the DTW distance to calculate the comprehensive time delay of the oxygen concentration data with respect to the multi-dimensional environmental factor data; The step of determining the influence weight between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component in each pair of nodes includes: Setting a sliding window on each pair of nodes, and using the comprehensive time delay and the data information within the sliding window to determine the correlation between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component; Using the correlation and the number of sliding windows in each pair of nodes to determine the influence weight between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component; The step of using the influence stability to determine the target environmental compensation model includes: Using the influence stability to assign corresponding weights to each single-dimensional environmental factor IMF component; Using the weights to perform weighted reconstruction on the oxygen concentration IMF component to obtain the target environmental compensation model; The calculation formula for the influence stability is: ； Among them, represents the stability of the influence of the j-th IMF component of the single-dimensional environmental factor signal on the oxygen concentration signal, that is, the influence stability; represents the influence weight between the i-th IMF component of the oxygen concentration and the j-th IMF component of the environmental factor signal; represents the average value of the influence weights between the j-th IMF component of the environmental factor signal and all IMF components of the oxygen concentration; represents the number of IMF components of the oxygen concentration.

2. The method for continuously monitoring the oxygen concentration for an electrochemical oxygen sensor according to claim 1, characterized in that, The step of using the comprehensive time delay and the data information within the sliding window to determine the correlation between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component includes: Determining the number of data within the sliding window; Determining the data values of the same serial numbers between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component within the sliding window; Using the comprehensive time delay, the number of data, and the data values to calculate the correlation between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component.

3. The method for continuously monitoring the oxygen concentration for an electrochemical oxygen sensor according to claim 1, characterized in that, The step of using the target environmental compensation model to correct the oxygen concentration measurement value includes: Input the real-time environmental factor data and the real-time oxygen concentration measurement data into the target environmental compensation model to obtain the expected value of the oxygen concentration; Determine the deviation between the oxygen concentration measurement value and the expected value of the oxygen concentration, and use the deviation to correct the oxygen concentration measurement value.

4. An oxygen concentration continuous monitoring device for an electrochemistry oxygen sensor, characterized in that, The device is used to implement the oxygen concentration continuous monitoring method for an electrochemical oxygen sensor according to any one of claims 1 to 3; the device includes: A signal monitoring module, configured to obtain oxygen concentration data and corresponding multi-dimensional environmental factor data; A time delay analysis module, configured to determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data; A component processing module, configured to perform empirical mode decomposition on the oxygen concentration data and the single-dimensional environmental factor data to obtain multiple pairs of nodes of IMF components; use the comprehensive time delay to determine the influence weight between the oxygen concentration IMF component and the single-dimensional environmental factor IMF component in each pair of nodes; use the influence weight to determine the influence stability of each single-dimensional environmental factor IMF component on the oxygen concentration data; A measurement compensation module, configured to determine the target environmental compensation model by using the influence stability, and use the target environmental compensation model to correct the oxygen concentration measurement value.

Images