Oxygen concentration continuous monitoring device and method

Abstract

The invention relates to the technical field of material physical property analysis and processing, in particular to an oxygen concentration continuous monitoring device and method.The method comprises the steps that oxygen concentration data and corresponding multi-dimensional environment factor data are obtained; 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 an IMF component; determining an influence weight between an oxygen concentration IMF component and a single-dimensional environmental factor IMF component in each pair of nodes; determining the influence stability of each one-dimensional environmental factor IMF component on the oxygen concentration data by using the influence weight; and determining a target environment compensation model by using the influence stability, and correcting the oxygen concentration measurement value by using the target environment compensation model. By means of the oxygen concentration continuous monitoring method, the accuracy and timeliness of oxygen concentration monitoring data are ensured, and the precision and reliability of an oxygen concentration monitoring system are effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of material physical property analysis and processing, and in particular to an oxygen concentration continuous monitoring device and method. Background Art

[0002] Medical molecular sieve oxygen generators separate nitrogen from oxygen in the air through molecular sieve materials (such as zeolite). After the air is pretreated, the molecular sieve adsorbs nitrogen at low pressure and releases a higher concentration of oxygen. In medical molecular sieve oxygen generators, it is crucial to accurately monitor the concentration of produced oxygen. In order to maintain the oxygen status 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 generator is working. The instrument sends data to the control device through a sensor to ensure that the oxygen concentration is always kept within the medical standard range and that the oxygen provided meets clinical requirements.

[0003] When using electrochemical oxygen sensors to continuously monitor oxygen concentration, changes in temperature, humidity and pressure in different environments will affect the detection results of the oxygen detector, and the impact of environmental factors on oxygen concentration detection is not completely real-time, that is, there is a certain delay. The existence of these errors will affect the accuracy and timeliness of oxygen concentration monitoring data, resulting in instability in the oxygen supply quality of the oxygen generator. Summary of the invention

[0004] In order to solve the technical problem of low accuracy and timeliness of oxygen concentration detection results under different environmental factors, the purpose of the present invention is to provide an oxygen concentration continuous monitoring device and method, and the technical solution adopted is as follows: The present invention provides a method for continuously monitoring oxygen concentration, the method comprising: Obtain oxygen concentration data and corresponding multi-dimensional environmental factor data; Determine the combined time delay of oxygen concentration data relative to multi-dimensional environmental factor data; Perform empirical mode decomposition on oxygen concentration data and one-dimensional environmental factor data to obtain multiple pairs of nodes of IMF components; The influence weight between the oxygen concentration IMF component and the unidimensional environmental factor IMF component in each pair of nodes is determined by using the comprehensive time delay; Using the influence weights, determining the stability of the influence of each single-dimensional environmental factor IMF component on the oxygen concentration data; Determine a target environment compensation model using the influence stability, and correct the oxygen concentration measurement value using the target environment compensation model; Each pair of nodes includes an oxygen concentration IMF component and a one-dimensional environmental factor IMF component.

[0005] Further, the step of determining the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data comprises: Determine the response delay of oxygen concentration data relative to single-dimensional environmental factor data; The response time delay is used to determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0006] Further, the step of determining the response delay of the oxygen concentration data relative to the single-dimensional environmental factor data includes: Determine the Pearson coefficient between oxygen concentration data and unidimensional environmental factor data; When the Pearson coefficient is maximum, the response delay of the oxygen concentration data relative to the single-dimensional environmental factor data is obtained.

[0007] Furthermore, the step 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 includes: Determine the DTW distance between oxygen concentration data and unidimensional environmental factor data; The response time delay and DTW distance are used to calculate the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0008] Further, the step of determining the influence weight between the oxygen concentration IMF component and the unidimensional environmental factor IMF component in each pair of nodes by using the comprehensive time delay includes: A sliding window is set on each pair of nodes, and the correlation between the IMF component of oxygen concentration and the IMF component of single-dimensional environmental factors is determined by using the comprehensive time delay and the data information in the sliding window; The influence weight between the oxygen concentration IMF component and the unidimensional environmental factor IMF component is determined by using the correlation and the number of sliding windows in each pair of nodes.

[0009] Further, the step of determining the correlation between the oxygen concentration IMF component and the unidimensional environmental factor IMF component by using the integrated time delay and the data information in the sliding window includes: Determine the amount of data within the sliding window; Determine the data values ​​with the same sequence number between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component in the sliding window; The correlation between the IMF component of oxygen concentration and the IMF component of unidimensional environmental factors is calculated using the comprehensive time delay, the data quantity and the data value.

[0010] Furthermore, the step of using the influence weight to determine the stability of the influence of each unidimensional environmental factor IMF component on the oxygen concentration data includes: Determine the average impact weight between the IMF component of the single-dimensional environmental factor and all the IMF components of oxygen concentration; The influence stability of each unidimensional environmental factor IMF component on the oxygen concentration data is calculated by using the influence weight, the influence weight mean and the number of oxygen concentration IMF components.

[0011] Furthermore, the step of determining the target environment compensation model by using the influence stability includes: Using the impact stability, a corresponding weight is assigned to each single-dimensional environmental factor IMF component; The oxygen concentration IMF component is weightedly reconstructed using the weights to obtain a target environment compensation model.

[0012] Further, the step of correcting the oxygen concentration measurement value using the target environment compensation model includes: Inputting the real-time environmental factor data and the real-time oxygen concentration measurement data into the target environment compensation model to obtain the expected value of oxygen concentration; A deviation between the measured oxygen concentration value and the expected oxygen concentration value is determined, and the measured oxygen concentration value is corrected using the deviation.

[0013] The present invention also provides an oxygen concentration continuous monitoring device, which is used to implement the oxygen concentration continuous monitoring method as described in any one of the above items; the device comprises: Signal monitoring module, used to obtain oxygen concentration data and corresponding multi-dimensional environmental factor data; A time delay analysis module for determining the combined time delay of oxygen concentration data relative to multi-dimensional environmental factor data; 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 component; using the comprehensive delay, 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, determine the influence stability of each one-dimensional environmental factor IMF component on the oxygen concentration data; The measurement compensation module is used to determine a target environment compensation model using the influence stability, and to correct the oxygen concentration measurement value using the target environment compensation model.

[0014] The present invention has the following beneficial effects: The present invention determines the weight of environmental factors according to temperature, humidity, pressure and other environmental factors, and builds a prediction model based on the time delay of the impact to predict future changes in oxygen concentration and correct the error in oxygen concentration data detection results caused by the external environment in real time. Specifically: First, by considering the interference of various environmental factors on the oxygen concentration monitoring signal (data) and adjusting it in combination with the delay factor, it can more accurately reflect the changes in oxygen concentration and avoid errors caused by external factors; Secondly, through the stability analysis of EMD decomposition and influence weights, it is possible to dynamically adapt to environmental changes and build a highly adaptable prediction model that can not only handle complex nonlinear relationships, but also cope with the multiple interferences of different environmental factors on monitoring signals, thus improving the intelligence level of the oxygen monitoring system. Thirdly, the deviation of oxygen monitoring data is calculated and corrected 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flowchart of a method for continuously monitoring oxygen concentration provided by an embodiment of the present invention; Figure 2 A detailed flow chart of step S2 in a method for continuous monitoring of oxygen concentration provided by one embodiment of the present invention; Figure 3 A detailed flow chart of step S4 in a method for continuous monitoring of oxygen concentration provided by one embodiment of the present invention; Figure 4 A detailed flow chart of step S5 in a method for continuous monitoring of oxygen concentration provided by one embodiment of the present invention; Figure 5 It is a structural diagram of the hardware operating environment of the oxygen concentration continuous monitoring device involved in the embodiment of the present invention; Figure 6 It is a schematic diagram of the framework structure of the oxygen concentration continuous monitoring device involved in the embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the oxygen concentration continuous monitoring method proposed by the present invention, its specific implementation method, structure, characteristics and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the oxygen concentration continuous monitoring device and method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] Embodiment 1: For the oxygen concentration continuous monitoring method provided by the present invention, please refer to Figure 1 , which shows a step flow chart of a method for continuous monitoring of oxygen concentration provided by an embodiment of the present invention.

[0021] The method comprises: Step S1, obtaining oxygen concentration data and corresponding multi-dimensional environmental factor data; This embodiment can be applied to a medical molecular sieve oxygen production system, and the specific scenarios for the embodiment can be: Electrochemical oxygen sensors have advantages such as low cost and fast response, but their measurement accuracy is easily affected by ambient temperature and humidity. When the ambient humidity is high, water molecules may interfere with the electrochemical reaction of the sensor, resulting in deviations in oxygen concentration measurement; temperature changes can also affect the chemical reaction rate inside the sensor, thereby affecting the accuracy of the readings. In addition, pressure can also affect the sensor's monitoring of oxygen concentration. These problems may lead to unstable oxygen concentration monitoring results in practical applications, especially in long-term operation or when environmental conditions fluctuate greatly, causing problems in the precise control of oxygen output.

[0022] You can choose an electrochemical oxygen sensor to detect oxygen concentration data, and set the temperature, humidity, and air pressure sensors to collect environmental factor data of multiple dimensions in real time when the gas passes through the electrochemical oxygen sensor. Several sensors collect data synchronously 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, to their own single-dimensional environmental factor data.

[0023] Step S2, determining the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data; Please refer to Figure 2 , the step S2 specifically comprises: Step S21, determining the response delay of the oxygen concentration data relative to the single-dimensional environmental factor data; Step S22, using the response delay, determining the comprehensive delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0024] More specifically, in one embodiment, step S21 includes: Determine the Pearson coefficient between oxygen concentration data and unidimensional environmental factor data; When the Pearson coefficient is maximum, the response delay of the oxygen concentration data relative to the single-dimensional environmental factor data is obtained.

[0025] More specifically, in one embodiment, step S22 includes: Determine the DTW distance between oxygen concentration data and unidimensional environmental factor data; The response time delay and DTW distance are used to calculate the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0026] During the use of the medical molecular sieve oxygen production system, the environmental factors such as temperature, humidity, and pressure of the oxygen generator may be unstable when outputting gas due to various reasons such as aging of the compressor. These environmental factors affect the reaction rate of oxygen molecules on the sensor surface with the electrolyte, thereby changing the monitoring signal of the electrochemical oxygen sensor, resulting in the actual oxygen concentration signal detected by the electrochemical oxygen sensor being unstable. Therefore, it is necessary to calculate the delay of the impact of different environmental data on the detection of oxygen concentration signals.

[0027] First, the response delay of a single environmental indicator to the change in oxygen concentration is analyzed: The detection principle of electrochemical oxygen sensors relies on catalytic reactions. Temperature changes affect the solubility and diffusion rate of oxygen and the speed of electrochemical reactions. Temperature increases usually accelerate the reaction rate, thus affecting the response of the oxygen sensor. Humidity changes affect the conductivity of the sensor's electrolyte. Excessive humidity may cause liquid accumulation or changes in the electrolyte properties inside the sensor, resulting in signal deviation. Pressure changes caused by gas flow rate directly affect the concentration distribution of oxygen molecules, which in turn affects the reaction of oxygen molecules on the sensor. Although the effects of temperature, humidity and pressure on oxygen concentration signals are achieved through different physical processes, their influence mechanisms are essentially to affect the reaction efficiency of oxygen on the sensor surface or the working environment of the oxygen sensor, so they will show consistency.

[0028] After the compressed gas passes through the oxygen generator, the temperature, humidity and gas flow rate will change. These changes will cause a certain delay in the sensor's monitoring results of oxygen data when passing through the electrochemical oxygen sensor. Determining the specific time delay can help determine the weight of the impact of different working environments on the final electrochemical oxygen sensor's detection data error, thereby ensuring that the correction parameters of the electrochemical oxygen sensor are adjusted accurately and effectively.

[0029] Based on the analysis of the above principles, the response delay of the electrochemical oxygen sensor compared to the temperature sensor detection signal is calculated (that is, the response delay of the oxygen concentration data relative to the single-dimensional environmental factor data of temperature) : ; in, It indicates the response delay of the electrochemical oxygen sensor compared to the temperature sensor detection signal. It means to find the maximum point function, that is, to get the corresponding value when the correlation coefficient reaches the maximum ; It means to find the Pearson correlation coefficient between two signal data series (i.e. oxygen concentration data and one-dimensional environmental factor data); Indicates the current moment; Indicates the length of the selected signal data sequence (the two sequences have the same length); Indicates the electrochemical oxygen sensor at time The detection signal data under (i.e. the corresponding oxygen concentration data, here refers to the data points); Indicates the temperature sensor at time The detection signal under (i.e., the corresponding single-dimensional environmental factor data, here refers to the data points). Δt represents the time delay between the data points of the two sequences.

[0030] The Pearson correlation coefficient reflects the linear relationship between the 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 in the time window can be selected as needed. By calculating the Pearson correlation coefficient between the signal data points of the two sequences in the window, different time delays Δt between the data points are obtained, and the time delay Δt that maximizes the correlation coefficient is found. By finding an optimal time offset, the correlation between the two signal sequences is maximized.

[0031] Similarly, the response delay of the electrochemical oxygen sensor compared to the humidity sensor can be obtained ; Response delay of electrochemical oxygen sensor compared to pressure sensor .

[0032] Secondly, based on the delays of each response, the final delay factor, i.e., the comprehensive delay, is obtained: The final time lag is corrected by the response delays of temperature, humidity, and pressure to obtain the final delay factor. Different environmental factors have different effects on the measurement of oxygen concentration. When the environmental factors of a certain dimension have a greater impact on the measurement of oxygen concentration, the DTW (Dynamic Time Warping) distance between the two data sequences is larger. At this time, the weight of the response delay corresponding to this factor should be higher. Calculate the DTW distance of the oxygen concentration detection results of temperature, humidity, and pressure respectively, and weight them as the weight of the response delay to obtain the final delay factor: ; ; in, represents the comprehensive delay, It indicates the response delay of the electrochemical oxygen sensor compared to the temperature sensor detection signal. Indicates the DTW distance between the temperature detection signal and the oxygen concentration detection signal; Represents 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; Represents 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.

[0033] Step S3, 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; The collected oxygen concentration signal and environmental factor signals of several dimensions are decomposed using the EMD (Empirical Mode Decomposition) algorithm. The decomposition process is a well-known technology. After obtaining different groups of IMF (Intrinsic Mode Function) components, these components can be analyzed.

[0034] The EMD algorithm decomposes complex signals into several intrinsic mode functions (IMFs), which helps to extract the local time-frequency characteristics of the signal data. These IMF components represent vibration modes of different frequencies in the original signal. Higher IMF components represent instantaneous fluctuations of high frequencies, while lower components represent the long-term trend of the signal. The oxygen concentration signal is affected by a variety of environmental factors, resulting in different time-frequency changes. By analyzing the correlation between the IMF components of different components and determining the influence weights of different environmental factors, the impact of different environmental factors on oxygen concentration can be more accurately identified and quantified.

[0035] Any oxygen concentration IMF component and any single-dimensional environmental factor IMF component can be combined to form a pair of nodes, wherein each pair of nodes includes an oxygen concentration IMF component and a single-dimensional environmental factor IMF component.

[0036] Step S4, using the comprehensive time delay, determining the influence weight between the oxygen concentration IMF component and the unidimensional environmental factor IMF component in each pair of nodes; Please refer to Figure 3 , the step S4 specifically comprises: Step S41, setting a sliding window on each pair of nodes, and determining the correlation between the IMF component of oxygen concentration and the IMF component of the unidimensional environmental factor by using the comprehensive time delay and the data information in the sliding window; More specifically, the step of determining the correlation between the oxygen concentration IMF component and the unidimensional environmental factor IMF component by using the integrated time delay and the data information in the sliding window includes: Determine the amount of data within the sliding window; Determine the data values ​​with the same sequence number between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component in the sliding window; The correlation between the IMF component of oxygen concentration and the IMF component of unidimensional environmental factors is calculated using the comprehensive time delay, the data quantity and the data value.

[0037] Step S42, 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 unidimensional environmental factor IMF component.

[0038] Taking the oxygen concentration signal data as a reference, a bipartite graph is constructed, in which one group of nodes represents the IMF components of oxygen concentration, and the other group of nodes represents the IMF components of different environmental factors. A sliding window is set on each pair of nodes (the window size is an integer multiple of the comprehensive delay of the above signal data), and the influence weights of different environmental factors in the nodes on different oxygen concentration components are calculated.

[0039] The sliding window can capture short-term fluctuations in the signal, which helps to identify and compensate for short-term changes caused by environmental factors. For the same pair of nodes in the sliding window, the more similar the signal change trends at the corresponding positions in the window are, the closer the correlation in the corresponding window is.

[0040] For each pair of nodes (an IMF component of oxygen concentration and an IMF component of environmental factors) in the sliding window, the correlation between the IMF component of oxygen concentration and the IMF component of the one-dimensional environmental factor signal is calculated: ; in, Represents the correlation between the i-th IMF component of oxygen concentration and the j-th IMF component of environmental factor signal in the v-th sliding window; The value of the rth signal data in the vth sliding window in the i-th IMF component representing the oxygen concentration (data value); Represents the value (data value) of the rth signal data in the vth sliding window in the jth IMF component of the environmental factor signal; represents the integrated time delay; m represents the number of signal data in the sliding window (the number of data refers to the number of data of the oxygen concentration IMF component or the one-dimensional environmental factor IMF component in the sliding window, which are the same); corr() represents the cross-correlation function.

[0041] It means that the data correlation between the i-th IMF component of the oxygen concentration and the j-th IMF component of the environmental factor signal in the same sliding window is calculated using the cross-correlation function corr, and then divided by the delay factor to eliminate the influence of the response delay on the data measured by the sensor; the corresponding several data correlations in the window are summed and averaged to obtain the average correlation between the two signal components in the same window, which can represent the influence of the environmental factor signal in the sliding window on the oxygen concentration detected by the sensor.

[0042] According to the several sliding windows corresponding to each pair of nodes, the influence weights between components are calculated: ; in, represents the influence weight between the i-th IMF component of oxygen concentration and the j-th IMF component of environmental factor signal; Represents the correlation between the i-th IMF component of oxygen concentration and the j-th IMF component of environmental factor signal in the v-th sliding window; N represents the number of corresponding sliding windows in each pair of nodes.

[0043] Step S5, using the influence weights, determining the stability of the influence of each single-dimensional environmental factor IMF component on the oxygen concentration data; Please refer to Figure 4 , the step S5 specifically comprises: Step S51, determining the influence weight mean between the single-dimensional environmental factor IMF component and all oxygen concentration IMF components; Step S52, using the influence weight, the influence weight mean 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.

[0044] The stability of the influence weight, or influence stability, refers to whether the influence of a certain dimension of environmental factors on oxygen concentration remains consistent under different environmental conditions. The stability of signal data is different under different temperature, humidity and pressure conditions. By calculating the stability of the influence weight, we can identify which environmental factors have a relatively stable influence and which factors may be affected by other external interference. If the influence weight of a certain environmental factor fluctuates greatly, it may mean that the influence of this factor is relatively unstable under different conditions.

[0045] Compare the stability of the influence weights of the same environmental factor signal node on different oxygen concentration signals to obtain the final influence relationship: ; in, It 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 oxygen concentration and the j-th IMF component of environmental factor signal; Represents the average of the impact weights between the j-th IMF component of the environmental factor signal and all oxygen concentration IMF components; The number of IMF components representing oxygen concentration.

[0046] Step S6, determining a target environment compensation model using the influence stability, and correcting the oxygen concentration measurement value using the target environment compensation model; Specifically, the step of determining the target environment compensation model by using the influence stability includes: Using the impact stability, a corresponding weight is assigned to each single-dimensional environmental factor IMF component; The oxygen concentration IMF component is weightedly reconstructed using the weights to obtain a target environment compensation model.

[0047] After calculating the stability of the impact of each environmental factor component on the oxygen concentration signal, different weights are assigned to each environmental factor component based on the impact stability. These weights are used to weighted reconstruct the IMF component of oxygen concentration, and the target environmental compensation model is established, thereby obtaining the oxygen concentration corrected based on environmental factors.

[0048] Specifically, the step of correcting the oxygen concentration measurement value using the target environment compensation model includes: Inputting the real-time environmental factor data and the real-time oxygen concentration measurement data into the target environment compensation model to obtain the expected value of oxygen concentration; A deviation between the measured oxygen concentration value and the expected oxygen concentration value is determined, and the measured oxygen concentration value is corrected using the deviation.

[0049] Continuously obtain real-time environmental factor signals and oxygen concentration measurement data , input into the above environmental compensation model, through this prediction model, we can get the expected value of oxygen concentration based on the change of environmental factors in a given future period of time Then, the expected value is compared with the actual monitoring data and the deviation between the two is calculated.

[0050] ; in, Indicates the deviation between the expected value and the actual monitored value (oxygen concentration measurement); Indicates the expected value of oxygen concentration; Indicates the real-time oxygen concentration monitoring value, that is, the oxygen concentration measurement value.

[0051] You can also set a threshold A as needed, such as A=0.3, to compare the deviation between the expected value and the actual monitoring value. When an error occurs, it indicates that the electrochemical oxygen concentration sensor may have failed or an emergency has occurred, resulting in a large deviation between the predicted expected value and the actual monitored value. A real-time warning is required, and the staff will conduct further analysis and inspection of the prediction model, monitoring data, and environmental factors to determine the specific reasons for the large deviation and take appropriate measures to improve it.

[0052] when deviation When , according to the deviation, the output obtains the real-time correction value: ; in, Indicates the correction value of oxygen concentration monitoring; Indicates the real-time oxygen concentration monitoring value; Indicates the deviation between the expected value and the actual monitored value.

[0053] The present invention determines the weight of environmental factors according to temperature, humidity, pressure and other environmental factors, and builds a prediction model based on the time delay of the impact to predict future changes in oxygen concentration and correct the error in oxygen concentration data detection results caused by the external environment in real time. Specifically: First, by considering the interference of various environmental factors on the oxygen concentration monitoring signal (data) and adjusting it in combination with the delay factor, it can more accurately reflect the changes in oxygen concentration and avoid errors caused by external factors; Secondly, through the stability analysis of EMD decomposition and influence weights, it is possible to dynamically adapt to environmental changes and build a highly adaptable prediction model that can not only handle complex nonlinear relationships, but also cope with the multiple interferences of different environmental factors on monitoring signals, thus improving the intelligence level of the oxygen monitoring system. Thirdly, the deviation of oxygen monitoring data is calculated and corrected 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.

[0054] Embodiment 2: The embodiment of the present invention also provides an oxygen concentration continuous monitoring device, which can be a computer, a server, an oxygen monitoring device or other data processing device, a signal detection and analysis device, or a combination of multiple devices.

[0055] like Figure 5 As shown, Figure 5 It is a structural diagram of the hardware operating environment of the oxygen concentration continuous monitoring device involved in the embodiment of the present invention.

[0056] like Figure 5 As 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), an input unit such as a control panel, and the user interface 1003 may optionally 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. The memory 1005 may optionally be a storage device independent of the aforementioned processor 1001. Those skilled in the art will understand that, Figure 5 The hardware structure shown in the figure does not constitute a limitation of the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0057] Continue to refer to 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.

[0058] exist Figure 5 In the embodiment, the network communication module is mainly used to connect to the server and can communicate data with the server; and the processor 1001 can call the oxygen concentration continuous monitoring program stored in the memory 1005 and execute the steps in the above embodiments.

[0059] The hardware structure of the above oxygen concentration continuous monitoring device is used to implement various embodiments of the oxygen concentration continuous monitoring method of the present invention.

[0060] In addition, the present invention also provides an oxygen concentration continuous monitoring device, please refer to Figure 6 , the oxygen concentration continuous monitoring device comprises: The signal monitoring module A10 is used to obtain oxygen concentration data and corresponding multi-dimensional environmental factor data; The time delay analysis module A20 is used to determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data; The component processing module A30 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 component; using the comprehensive delay, 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, determine the influence stability of each one-dimensional environmental factor IMF component on the oxygen concentration data; The measurement compensation module A40 is used to determine a target environment compensation model using the influencing stability, and to correct the oxygen concentration measurement value using the target environment compensation model.

[0061] Furthermore, the delay analysis module A20 is further used for: Determine the response delay of oxygen concentration data relative to single-dimensional environmental factor data; The response time delay is used to determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0062] Furthermore, the delay analysis module A20 is further used for: Determine the Pearson coefficient between oxygen concentration data and unidimensional environmental factor data; When the Pearson coefficient is maximum, the response delay of the oxygen concentration data relative to the single-dimensional environmental factor data is obtained.

[0063] Furthermore, the delay analysis module A20 is further used for: Determine the DTW distance between oxygen concentration data and unidimensional environmental factor data; The response time delay and DTW distance are used to calculate the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

[0064] Furthermore, the component processing module A30 is also used for: A sliding window is set on each pair of nodes, and the correlation between the IMF component of oxygen concentration and the IMF component of single-dimensional environmental factors is determined by using the comprehensive time delay and the data information in the sliding window; The influence weight between the oxygen concentration IMF component and the unidimensional environmental factor IMF component is determined by using the correlation and the number of sliding windows in each pair of nodes.

[0065] Furthermore, the component processing module A30 is also used for: Determine the amount of data within the sliding window; Determine the data values ​​with the same sequence number between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component in the sliding window; The correlation between the IMF component of oxygen concentration and the IMF component of unidimensional environmental factors is calculated using the comprehensive time delay, the data quantity and the data value.

[0066] Furthermore, the component processing module A30 is also used for: Determine the average impact weight between the IMF component of the single-dimensional environmental factor and the IMF component of all oxygen concentrations; The influence stability of each unidimensional environmental factor IMF component on the oxygen concentration data is calculated by using the influence weight, the influence weight mean and the number of oxygen concentration IMF components.

[0067] Furthermore, the measurement compensation module A40 is also used for: Using the impact stability, a corresponding weight is assigned to each single-dimensional environmental factor IMF component; The oxygen concentration IMF component is weightedly reconstructed using the weights to obtain a target environment compensation model.

[0068] Furthermore, the measurement compensation module A40 is also used for: Inputting the real-time environmental factor data and the real-time oxygen concentration measurement data into the target environment compensation model to obtain the expected value of oxygen concentration; A deviation between the measured oxygen concentration value and the expected oxygen concentration value is determined, and the measured oxygen concentration value is corrected using the deviation.

[0069] The specific implementation of the oxygen concentration continuous monitoring device of the present invention is basically the same as the above-mentioned embodiments of the oxygen concentration continuous monitoring method, and will not be repeated here.

[0070] In addition, the present invention also provides a computer-readable storage medium. The computer-readable storage medium of the present invention stores an oxygen concentration continuous monitoring program, wherein 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.

[0071] Among them, the method implemented when the oxygen concentration continuous monitoring program is executed can refer to the various embodiments of the oxygen concentration continuous monitoring method of the present invention, and will not be repeated here.

[0072] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying 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.

[0073] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0074] It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] The above description is only a preferred embodiment of the present invention, and does not limit the protection scope of the present invention. All equivalent structural / method transformations made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or direct / indirect application in other related technical fields are included in the protection scope of the present invention.

Claims

1. A method for continuous monitoring of oxygen concentration, characterized in that: The method comprises: Obtain oxygen concentration data and corresponding multi-dimensional environmental factor data; Determine the combined time delay of oxygen concentration data relative to multi-dimensional environmental factor data; Perform empirical mode decomposition on oxygen concentration data and one-dimensional environmental factor data to obtain multiple pairs of nodes of IMF components; The influence weight between the oxygen concentration IMF component and the unidimensional environmental factor IMF component in each pair of nodes is determined by using the comprehensive time delay; Using the influence weights, determining the stability of the influence of each single-dimensional environmental factor IMF component on the oxygen concentration data; Determine a target environment compensation model using the influence stability, and correct the oxygen concentration measurement value using the target environment compensation model; Each pair of nodes includes an oxygen concentration IMF component and a one-dimensional environmental factor IMF component.

2. The method for continuous monitoring of oxygen concentration according to claim 1, characterized in that: The steps of determining the integrated time delay of oxygen concentration data relative to multi-dimensional environmental factor data include: Determine the response delay of oxygen concentration data relative to single-dimensional environmental factor data; The response time delay is used to determine the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

3. The method for continuous monitoring of oxygen concentration according to claim 2, characterized in that: The step of determining the response delay of oxygen concentration data relative to the single-dimensional environmental factor data comprises: Determine the Pearson coefficient between oxygen concentration data and unidimensional environmental factor data; When the Pearson coefficient is maximum, the response delay of the oxygen concentration data relative to the single-dimensional environmental factor data is obtained.

4. The method for continuous monitoring of oxygen concentration according to claim 2, characterized in that: The step of determining the comprehensive time delay of oxygen concentration data relative to multi-dimensional environmental factor data by using the response time delay comprises: Determine the DTW distance between oxygen concentration data and unidimensional environmental factor data; The response time delay and DTW distance are used to calculate the comprehensive time delay of the oxygen concentration data relative to the multi-dimensional environmental factor data.

5. The method for continuous monitoring of oxygen concentration according to claim 1, characterized in that: The steps of determining the influence weight between the oxygen concentration IMF component and the unidimensional environmental factor IMF component in each pair of nodes by using the comprehensive time delay include: A sliding window is set on each pair of nodes, and the correlation between the IMF component of oxygen concentration and the IMF component of single-dimensional environmental factors is determined by using the comprehensive time delay and the data information in the sliding window; The influence weight between the oxygen concentration IMF component and the unidimensional environmental factor IMF component is determined by using the correlation and the number of sliding windows in each pair of nodes.

6. The method for continuous monitoring of oxygen concentration according to claim 5, characterized in that: The step of determining the correlation between the oxygen concentration IMF component and the unidimensional environmental factor IMF component by using the integrated time delay and the data information in the sliding window comprises: Determine the amount of data within the sliding window; Determine the data values ​​with the same sequence number between the oxygen concentration IMF component and the one-dimensional environmental factor IMF component in the sliding window; The correlation between the IMF component of oxygen concentration and the IMF component of unidimensional environmental factors is calculated using the comprehensive time delay, the data quantity and the data value.

7. The method for continuous monitoring of oxygen concentration according to claim 1, characterized in that: The step of determining the stability of the influence of each unidimensional environmental factor IMF component on the oxygen concentration data by using the influence weights includes: Determine the average impact weight between the IMF component of the single-dimensional environmental factor and the IMF component of all oxygen concentrations; The influence stability of each unidimensional environmental factor IMF component on the oxygen concentration data is calculated by using the influence weight, the influence weight mean and the number of oxygen concentration IMF components.

8. The method for continuous monitoring of oxygen concentration according to claim 1, characterized in that: The step of determining a target environment compensation model using the impact stability comprises: Using the impact stability, a corresponding weight is assigned to each single-dimensional environmental factor IMF component; The weights are used to perform weighted reconstruction on the oxygen concentration IMF component to obtain a target environment compensation model.

9. The method for continuous monitoring of oxygen concentration according to claim 1, characterized in that: The steps for correcting the oxygen concentration measurement using the target environment compensation model include: Inputting the real-time environmental factor data and the real-time oxygen concentration measurement data into the target environment compensation model to obtain the expected value of oxygen concentration; A deviation between the measured oxygen concentration value and the expected oxygen concentration value is determined, and the measured oxygen concentration value is corrected using the deviation.

10. A continuous oxygen concentration monitoring device, characterized in that: The device is used to implement the method for continuous monitoring of oxygen concentration according to any one of claims 1 to 9; the device comprises: Signal monitoring module, used to obtain oxygen concentration data and corresponding multi-dimensional environmental factor data; A time delay analysis module for determining the combined time delay of oxygen concentration data relative to multi-dimensional environmental factor data; 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 component; using the comprehensive delay, 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, determine the influence stability of each one-dimensional environmental factor IMF component on the oxygen concentration data; The measurement compensation module is used to determine a target environment compensation model using the influence stability, and to correct the oxygen concentration measurement value using the target environment compensation model.

Images