A humidity compensation method and system based on adaptive filtering algorithm

Abstract

The present invention discloses a humidity compensation method and system based on an adaptive filtering algorithm. The method comprises: obtaining a working scenario of an online VOCs monitoring device, obtaining a corresponding filter coefficient and step-size threshold based on the working scenario; using the filter coefficient and step-size threshold as the initial filter coefficient and initial step-size threshold of the adaptive filter; obtaining a monitoring signal from the online VOCs monitoring device, inputting the monitoring signal into the adaptive filter, and obtaining signal interference data output by the adaptive filter, the signal interference data including a humidity interference signal and additional noise; and generating a VOCs signal monitored by the online VOC monitoring device based on the monitoring signal and signal interference data. The present invention collects a large amount of data from different scenarios, establishes samples for automatic training, and performs adaptive filtering modeling. The monitoring device's working environment meets the scenario of relative humidity of 0-100%, and continuous sampling is also possible, thereby improving the accuracy of VOCs data measurement.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial enterprise waste gas pollution monitoring, and in particular to a humidity compensation method and system based on an adaptive filtering algorithm. Background Art

[0002] Volatile organic compounds (VOCs) are important precursors to the formation of secondary pollutants such as fine particulate matter (PM2.5) and ozone (O3). Relevant laws and regulations require environmental protection departments to conduct monitoring and prevention and control.

[0003] VOCs online monitoring instruments are generally installed outdoors in an operating environment with a relative humidity range of 0-100%. The data accuracy of online monitoring instruments is greatly affected by the ambient humidity. When the relative humidity exceeds a certain level, the data of the online monitoring instrument will drift, making the data unusable.

[0004] The only monitoring devices on the market that can maintain accurate data in high-humidity environments use physical dehumidification to address humidity issues. However, these devices are expensive, making them unaffordable for many pollutant-discharging companies. Cheaper devices also suffer from inaccurate data due to humidity fluctuations, making them difficult to meet online monitoring requirements.

[0005] Therefore existing technology also needs further development. Summary of the Invention

[0006] In response to the above technical problems, the embodiments of the present invention provide a humidity compensation method and system based on an adaptive filtering algorithm, which can solve the technical problems of high cost and inaccurate humidity compensation data in the dehumidification method of VOCs online monitoring instruments in high humidity environments in the prior art.

[0007] A first aspect of an embodiment of the present invention provides a humidity compensation method based on an adaptive filtering algorithm, which is applied to a VOCs online monitoring device. The method includes:

[0008] Obtain a working scenario of a VOCs online monitoring device, and obtain a corresponding filter coefficient and step threshold according to the working scenario;

[0009] Using the filter coefficients and step-size thresholds as initial filter coefficients and initial step-size thresholds of an adaptive filter;

[0010] Obtaining a monitoring signal from a VOCs online monitoring device, inputting the monitoring signal into an adaptive filter, and obtaining signal interference data output by the adaptive filter, wherein the signal interference data includes a humidity interference signal and additional noise;

[0011] A VOCs signal monitored by the VOC online monitoring device is generated based on the monitoring signal and the signal interference data.

[0012] Optionally, before obtaining a working scenario of the VOCs online monitoring device and obtaining a corresponding filter coefficient and step threshold according to the working scenario, the method further includes:

[0013] The working scene of the VOCs online monitoring device is set in advance, and the device ID of the VOCs online monitoring device is bound to the working scene.

[0014] Optionally, obtaining a working scenario of the VOCs online monitoring device and obtaining a corresponding filter coefficient and step threshold according to the working scenario include:

[0015] Obtaining a device ID of a VOCs online monitoring device, and obtaining a working scenario of the VOCs online monitoring device according to the device ID;

[0016] The preset filter coefficients and step thresholds are obtained according to the working scenario.

[0017] Optionally, before obtaining the working scenario of the VOCs online monitoring device and obtaining the corresponding filter coefficient and step threshold according to the working scenario, the method further includes:

[0018] Obtain a large amount of test data corresponding to different work scenarios, and generate training samples based on the large amount of test data;

[0019] The adaptive filter is trained according to the training samples to generate filter coefficients and step thresholds corresponding to different working scenarios.

[0020] Optionally, the training of the adaptive filter according to the training samples to generate filter coefficients and step thresholds corresponding to different working scenarios includes:

[0021] Obtaining filter coefficients of an adaptive filter according to the training samples;

[0022] Calculate the error after filtering, update the step size and filter coefficient according to the error, and obtain the filtering result;

[0023] Determine whether the error of the filtering result meets the preset error standard;

[0024] If the error of the filtering result meets the preset error standard, the current filtering coefficient and step size are obtained as the filtering coefficient and step size threshold corresponding to the current working scene.

[0025] A second aspect of an embodiment of the present invention provides a humidity compensation system based on an adaptive filtering algorithm, which is applied to a VOCs online monitoring device. The system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the following steps are implemented:

[0026] Obtain a working scenario of a VOCs online monitoring device, and obtain a corresponding filter coefficient and step threshold according to the working scenario;

[0027] Using the filter coefficients and step-size thresholds as initial filter coefficients and initial step-size thresholds of an adaptive filter;

[0028] Obtaining a monitoring signal from a VOCs online monitoring device, inputting the monitoring signal into an adaptive filter, and obtaining signal interference data output by the adaptive filter, wherein the signal interference data includes a humidity interference signal and additional noise;

[0029] A VOCs signal monitored by the VOC online monitoring device is generated based on the monitoring signal and the signal interference data.

[0030] Optionally, when the computer program is executed by the processor, the following steps are further implemented:

[0031] The working scene of the VOCs online monitoring device is set in advance, and the device ID of the VOCs online monitoring device is bound to the working scene.

[0032] Optionally, when the computer program is executed by the processor, the following steps are further implemented:

[0033] Obtaining a device ID of a VOCs online monitoring device, and obtaining a working scenario of the VOCs online monitoring device according to the device ID;

[0034] The preset filter coefficients and step thresholds are obtained according to the working scenario.

[0035] Optionally, when the computer program is executed by the processor, the following steps are further implemented:

[0036] Obtain a large amount of test data corresponding to different work scenarios, and generate training samples based on the large amount of test data;

[0037] The adaptive filter is trained according to the training samples to generate filter coefficients and step thresholds corresponding to different working scenarios.

[0038] A third aspect of an embodiment of the present invention provides a non-volatile computer-readable storage medium, characterized in that the non-volatile computer-readable storage medium stores computer-executable instructions, which, when executed by one or more processors, enable the one or more processors to execute the above-mentioned humidity compensation method based on the adaptive filtering algorithm.

[0039] In the technical solution provided by an embodiment of the present invention, a working scenario of an online VOCs monitoring device is obtained, and corresponding filter coefficients and step thresholds are obtained based on the working scenario; the filter coefficients and step thresholds are used as the initial filter coefficients and initial step thresholds of an adaptive filter; a monitoring signal from the online VOCs monitoring device is obtained, inputted into the adaptive filter, and signal interference data output by the adaptive filter is obtained, the signal interference data including humidity interference signals and additional noise; and a VOCs signal monitored by the online VOC monitoring device is generated based on the monitoring signal and signal interference data. By collecting a large amount of data from different scenarios, the present invention establishes samples for automatic training and adaptive filtering modeling. The monitoring device's working environment meets the requirements of scenarios with a relative humidity of 0-100%, and continuous sampling is also possible, thereby improving the accuracy of VOCs data measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 1 is a flow chart of an embodiment of a humidity compensation method based on an adaptive filtering algorithm according to an embodiment of the present invention;

[0041] Figure 2 1 is a block diagram of an adaptive filtering structure of another embodiment of a humidity compensation method based on an adaptive filtering algorithm according to an embodiment of the present invention;

[0042] Figure 3a Schematic diagram of original signals of another embodiment of a humidity compensation method based on an adaptive filtering algorithm in an embodiment of the present invention;

[0043] Figure 3b Schematic diagram of a signal after humidity compensation according to another embodiment of a humidity compensation method based on an adaptive filtering algorithm in an embodiment of the present invention;

[0044] Figure 4 Schematic diagram of the hardware structure of another embodiment of a humidity compensation system based on an adaptive filtering algorithm in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0047] See also Figure 1 , Figure 1FIG. 1 is a flow chart of an embodiment of a humidity compensation method based on an adaptive filtering algorithm according to an embodiment of the present invention. Figure 1 Shown, including:

[0048] Step S100: Obtain a working scenario of the VOCs online monitoring device, and obtain a corresponding filter coefficient and step threshold according to the working scenario;

[0049] Step S200: Using the filter coefficients and step threshold as initial filter coefficients and initial step threshold of an adaptive filter;

[0050] Step S300: Acquire a monitoring signal from a VOCs online monitoring device, input the monitoring signal into an adaptive filter, and acquire signal interference data output by the adaptive filter, wherein the signal interference data includes a humidity interference signal and additional noise;

[0051] Step S400: Generate a VOCs signal monitored by a VOC online monitoring device according to the monitoring signal and the signal interference data.

[0052] In specific implementation, the embodiment of the present invention mainly applies signal monitoring of VOCs online monitoring equipment. The VOCs online monitoring equipment involves waste gas pollution monitoring of industrial enterprises, mainly monitoring volatile organic compounds in industrial enterprises.

[0053] An adaptive filtering humidity compensation algorithm distinguishes VOCs from humidity based on frequency characteristics. Humidity changes in nature are slow, reflected in the spectrum with relatively long wavelengths. VOC changes within the factory boundary are rapid, reflected in the spectrum with relatively short wavelengths. The processing avoids physical dehumidification and uses an adaptive digital filtering algorithm. Training samples are created for humidity changes in different scenarios, and the filter threshold is calibrated to ensure interference waveforms are filtered out. Humidity compensation is then performed to obtain the VOC signal waveform.

[0054] Adaptive digital filtering algorithms can filter uncertain random signals. By tracking signal changes and continuously adjusting the filter structure and parameters, the algorithm can achieve optimal filtering results. As an important component of adaptive filters, the performance of the algorithm directly determines the performance of the filter. Research on adaptive filtering algorithms is one of the most active research topics in the field of adaptive signal processing and is also a key research focus.

[0055] The basic idea of the adaptive filtering algorithm is to adaptively adjust the filter coefficients according to the characteristics of the input signal to achieve optimal filtering.

[0056] The structure of an adaptive filter function according to an embodiment of the present invention is as follows: Figure 2As shown in Figure 2, if the order of adaptive filtering is M, the filter coefficient is W, and the input signal sequence is X, the output is:

[0057]

[0058] e(n) = d(n) - y(n) (Formula 2)

[0059] Where d(n) is the desired signal and e(n) is the error signal.

[0060]

[0061] Let W = [w0,w1,L,w M-1 ] T ,X j =[x 1j ,x 2j ,L,x Nj ] T (Formula 4)

[0062] The output of the filter can then be written in matrix form:

[0063]

[0064]

[0065] Define the cost function:

[0066]

[0067] When the cost function in the above formula is minimized, it is considered that optimal filtering is achieved, and such adaptive filtering is called least mean square adaptive filtering (LMS).

[0068] For least mean square adaptive filtering, it is necessary to determine the filter coefficients that minimize the mean square error. Gradient descent is generally used to solve this problem. The iterative formula for the filter coefficient vector is:

[0069]

[0070] Where μ is the step size factor, is the gradient of the cost function.

[0071] Because the instantaneous gradient -2X j e j It is an unbiased estimate of the true gradient value. In practical applications, the instantaneous gradient can be used instead of the true gradient, that is:

[0072]

[0073] W j+1 =Wj +μe j X j (Formula 10)

[0074] Through step-by-step iteration, the optimal filter coefficients can be obtained to achieve adaptive filtering of the input signal.

[0075] Selecting the iteration step size under the requirements of meeting the convergence conditions can ensure the final convergence result, but this step size is fixed throughout the process. However, a more ideal situation is that in the initial stage of filtering, when the error value is large, the iteration step size can be taken to a larger value to achieve a faster convergence speed. As the error decreases and gradually approaches the optimal target, the iteration step size is also reduced accordingly, thereby obtaining better convergence accuracy. This is the variable step size adaptive filtering algorithm.

[0076] The computational complexity of an adaptive filter is the amount of computation required from receiving an input signal to producing a filter output. This includes the computational complexity required to update the weight coefficients. Different applications require different performance requirements for adaptive filters. Generally speaking, a completely optimal adaptive filter does not exist. Appropriate trade-offs must be made based on the specific requirements of the system.

[0077] To optimize computational complexity and implement filtering algorithms for batch online monitor data, this paper uses preset scenario filter coefficients and step sizes. By categorizing the monitoring environment into different scenarios, including VOCs raw material storage, transfer and transportation, pipelines, process production, liquid level, and discharge outlet concentration, each monitor in the system is assigned a specific monitoring scenario. Based on these scenarios, a large amount of test data is collected, training samples are created, and filter coefficients and step size thresholds for each scenario are generated and optimized in advance, serving as the preset scenario filter coefficients and step sizes for each scenario.

[0078] Each time the monitor transmits detection data to the server, the compensation algorithm will select a preset threshold for adaptive filtering based on the monitor's scenario, obtaining the humidity interference signal and the additional noise d. The test data serves as the expected signal x of the adaptive filter. x includes the VOCs signal, the humidity interference signal, and the additional noise. e is the difference between x and d, which is the VOCs signal.

[0079] The embodiments of the present invention collect a large amount of data from different scenarios, establish samples for automatic training, and perform adaptive filtering modeling. The operating environment of the monitor meets the scenario of relative humidity of 0-100%. This overcomes the problem of inaccurate VOCs measurement and unavailable data caused by factors such as humidity in low-priced instruments, filling the current market gap.

[0080] Furthermore, before obtaining the working scenario of the VOCs online monitoring device and obtaining the corresponding filter coefficient and step threshold according to the working scenario, the method further includes:

[0081] The working scene of the VOCs online monitoring device is set in advance, and the device ID of the VOCs online monitoring device is bound to the working scene.

[0082] Specifically, after successfully establishing the scenario filter threshold, in actual use, the monitor data is uploaded to the cloud server. After the monitor is installed, the monitoring scenario for each monitor is determined based on technical documents such as the environmental impact assessment report and combined with the engineer's on-site survey. This scenario is then configured on the platform. Specifically, the VOCs online monitoring device's device ID is bound to the operating scenario, allowing the corresponding operating scenario to be retrieved using the device ID.

[0083] Furthermore, a working scenario of the VOCs online monitoring device is obtained, and corresponding filter coefficients and step thresholds are obtained according to the working scenario, including:

[0084] Obtaining a device ID of a VOCs online monitoring device, and obtaining a working scenario of the VOCs online monitoring device according to the device ID;

[0085] The preset filter coefficients and step thresholds are obtained according to the working scenario.

[0086] During specific implementation, the device ID of the VOCs online monitoring device is obtained, and the working scenario of the VOCs online monitoring device is obtained according to the device ID; and then the preset filter coefficient and step threshold are obtained.

[0087] Taking the raw material storage scenario as an example, a pilot project used fully automated calculations of monitoring data from this scenario to determine the filter coefficients and step size thresholds. This computational complexity was significant, often requiring several hours or even a day to calculate the data for a single instrument, resulting in low efficiency in actual use. The values obtained through fully automated calculations based on the pilot project data served as the preset filter coefficients and step size for this scenario. During actual instrument operation, the algorithm began calculations based on these preset values. As the volume of data from different scenarios grew, developers periodically optimized the preset filter coefficients and step size.

[0088] Furthermore, before obtaining the working scenario of the VOCs online monitoring device and obtaining the corresponding filter coefficient and step threshold according to the working scenario, the method further includes:

[0089] Obtain a large amount of test data corresponding to different work scenarios, and generate training samples based on the large amount of test data;

[0090] The adaptive filter is trained according to the training samples to generate filter coefficients and step thresholds corresponding to different working scenarios.

[0091] During specific implementation, a large amount of test data corresponding to different working scenarios is obtained, and training samples are generated based on the large amount of test data; the adaptive filter is trained based on the training samples to generate filter coefficients and step thresholds corresponding to different working scenarios.

[0092] Furthermore, the adaptive filter is trained according to the training samples to generate filter coefficients and step thresholds corresponding to different working scenarios, including:

[0093] Obtaining filter coefficients of an adaptive filter according to the training samples;

[0094] Calculate the error after filtering, update the step size and filter coefficient according to the error, and obtain the filtering result;

[0095] Determine whether the error of the filtering result meets the preset error standard;

[0096] If the error of the filtering result meets the preset error standard, the current filtering coefficient and step size are obtained as the filtering coefficient and step size threshold corresponding to the current working scene.

[0097] In specific implementation, according to the training samples, the adaptive filter is input to obtain the filter coefficient of the adaptive filter; the error after filtering is calculated, and the step size and filter coefficient are updated according to the error to obtain the filtering result;

[0098] Determine whether the error of the filtering result meets the preset error standard;

[0099] If the error of the filtering result meets the preset error standard, the current filtering coefficient and step size are obtained as the filtering coefficient and step size threshold corresponding to the current working scene;

[0100] If the error of the filtering result does not meet the preset error standard, the filter coefficient of the adaptive filter is adjusted until the error of the filtering result meets the preset error standard.

[0101] The data used is from the monitoring device installed at the project factory boundary, with a sampling frequency of 30 seconds, a collection time of 50 hours, and 6091 collection points. The original signal is as follows Figure 3a As shown:

[0102] The VOCs signal after filtering out humidity interference is as follows Figure 3b As shown in the figure, the three VOCs signal waveforms are completely preserved, and the interference of humidity changes at other times is cleanly filtered out.

[0103] We collected data from 100 monitors over a year's operation, creating a dataset of 105,120,000 big data training samples and optimizing the aforementioned model. Ultimately, we achieved a highly effective humidity compensation algorithm model, demonstrating excellent filtering performance and computational efficiency.

[0104] The embodiment of the present invention provides a humidity compensation method based on an adaptive filtering algorithm. It collects a large amount of data under different scenarios, establishes samples for automatic training and adaptive filtering modeling. The working environment of the monitor meets the scenario of relative humidity of 0-100%. It overcomes the problem that low-priced instruments generally have inaccurate VOCs measurement and unavailable data due to factors such as humidity. It measures accurately and continuously, filling the current market gap.

[0105] This technology significantly improves the accuracy of data from low-cost online VOCs monitoring instruments operating in high-humidity environments, resolving the problem of inaccurate measurements in low-cost online VOCs monitors in high-humidity environments and filling a current market gap. It provides strong technical support for VOCs pollution prevention and control, facilitates the coordinated control of ozone and PM2.5, and improves ecological and environmental quality.

[0106] It should be noted that there is not necessarily a certain order between the above steps. A person skilled in the art can understand, based on the description of the embodiments of the present invention, that in different embodiments, the above steps may have different execution orders, that is, they may be executed in parallel, or may be executed interchangeably, etc.

[0107] The above describes the humidity compensation method based on the adaptive filtering algorithm in the embodiment of the present invention. The following describes the humidity compensation system based on the adaptive filtering algorithm in the embodiment of the present invention. Figure 4 , Figure 4 FIG. 1 is a schematic diagram of the hardware structure of another embodiment of a humidity compensation system based on an adaptive filtering algorithm according to an embodiment of the present invention. Figure 4 As shown, the system 10 includes: a memory 101, a processor 102, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor 101, the following steps are implemented:

[0108] Obtain a working scenario of a VOCs online monitoring device, and obtain a corresponding filter coefficient and step threshold according to the working scenario;

[0109] Using the filter coefficients and step-size thresholds as initial filter coefficients and initial step-size thresholds of an adaptive filter;

[0110] Obtaining a monitoring signal from a VOCs online monitoring device, inputting the monitoring signal into an adaptive filter, and obtaining signal interference data output by the adaptive filter, wherein the signal interference data includes a humidity interference signal and additional noise;

[0111] A VOCs signal monitored by the VOC online monitoring device is generated based on the monitoring signal and the signal interference data.

[0112] The specific implementation steps are the same as those in the method embodiment and will not be repeated here.

[0113] Optionally, when the computer program is executed by the processor 101, the following steps are further implemented:

[0114] The working scene of the VOCs online monitoring device is set in advance, and the device ID of the VOCs online monitoring device is bound to the working scene.

[0115] The specific implementation steps are the same as those in the method embodiment and will not be repeated here.

[0116] Optionally, when the computer program is executed by the processor 101, the following steps are further implemented:

[0117] Obtaining a device ID of a VOCs online monitoring device, and obtaining a working scenario of the VOCs online monitoring device according to the device ID;

[0118] The preset filter coefficients and step thresholds are obtained according to the working scenario.

[0119] The specific implementation steps are the same as those in the method embodiment and will not be repeated here.

[0120] Optionally, when the computer program is executed by the processor 101, the following steps are further implemented:

[0121] Obtain a large amount of test data corresponding to different work scenarios, and generate training samples based on the large amount of test data;

[0122] The adaptive filter is trained according to the training samples to generate filter coefficients and step thresholds corresponding to different working scenarios.

[0123] The specific implementation steps are the same as those in the method embodiment and will not be repeated here.

[0124] Optionally, when the computer program is executed by the processor 101, the following steps are further implemented:

[0125] Obtaining filter coefficients of an adaptive filter according to the training samples;

[0126] Calculate the error after filtering, update the step size and filter coefficient according to the error, and obtain the filtering result;

[0127] Determine whether the error of the filtering result meets the preset error standard;

[0128] If the error of the filtering result meets the preset error standard, the current filtering coefficient and step size are obtained as the filtering coefficient and step size threshold corresponding to the current working scene.

[0129] The specific implementation steps are the same as those in the method embodiment and will not be repeated here.

[0130] An embodiment of the present invention provides a non-volatile computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, which are executed by one or more processors, for example, to execute the above-described Figure 1 Method steps S100 to S400.

[0131] As an example, the non-volatile storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described in the embodiments of the present invention are intended to include one or more of these and / or any other suitable types of memory.

[0132] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A humidity compensation method based on an adaptive filtering algorithm, characterized in that: Applied to VOCs online monitoring equipment, the method includes: Set the working scene of the VOCs online monitoring device in advance and bind the device ID of the VOCs online monitoring device to the working scene; Obtaining a device ID of a VOCs online monitoring device, and obtaining a working scenario of the VOCs online monitoring device according to the device ID; Obtaining a large amount of test data corresponding to different work scenarios, and generating training samples based on the large amount of test data; Training the adaptive filter according to the training sample includes: obtaining a filter coefficient of the adaptive filter according to the training sample, calculating an error after filtering, updating a step size and a filter coefficient according to the error to obtain a filtering result, and determining whether the error of the filtering result meets a preset error standard. If so, obtaining the current filter coefficient and step size as the filter coefficient and step size threshold corresponding to the current working scene; Using the filter coefficient and step threshold as the initial filter coefficient and initial step threshold of the adaptive filter; Obtaining a monitoring signal from a VOCs online monitoring device, inputting the monitoring signal into an adaptive filter, and obtaining signal interference data output by the adaptive filter, wherein the signal interference data includes a humidity interference signal and additional noise; A VOCs signal monitored by a VOC online monitoring device is generated based on the monitoring signal and the signal interference data.

2. The humidity compensation method based on the adaptive filtering algorithm according to claim 1, characterized in that: After the step size and the filter coefficient are updated according to the error to obtain the filtering result, the method further includes: if the error of the filtering result does not meet the preset error standard, adjusting the filter coefficient of the adaptive filter until the error of the filtering result meets the preset error standard.

3. A humidity compensation system based on an adaptive filtering algorithm, characterized in that: Applied to VOCs online monitoring equipment, the system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the following steps are implemented: Set the working scene of the VOCs online monitoring device in advance and bind the device ID of the VOCs online monitoring device to the working scene; Obtaining a device ID of a VOCs online monitoring device, and obtaining a working scenario of the VOCs online monitoring device according to the device ID; Obtaining a large amount of test data corresponding to different work scenarios, and generating training samples based on the large amount of test data; Training the adaptive filter according to the training sample includes: obtaining a filter coefficient of the adaptive filter according to the training sample, calculating an error after filtering, updating a step size and a filter coefficient according to the error to obtain a filtering result, and determining whether the error of the filtering result meets a preset error standard. If so, obtaining the current filter coefficient and step size as the filter coefficient and step size threshold corresponding to the current working scene; Using the filter coefficient and step threshold as the initial filter coefficient and initial step threshold of the adaptive filter; Obtaining a monitoring signal from a VOCs online monitoring device, inputting the monitoring signal into an adaptive filter, and obtaining signal interference data output by the adaptive filter, wherein the signal interference data includes a humidity interference signal and additional noise; A VOCs signal monitored by a VOC online monitoring device is generated based on the monitoring signal and the signal interference data.

4. The humidity compensation system based on the adaptive filtering algorithm according to claim 3, characterized in that: When the computer program is executed by the processor, if the error of the filtering result does not meet the preset error standard, the filtering coefficient of the adaptive filter is adjusted until the error of the filtering result meets the preset error standard.

5. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores computer-executable instructions, which, when executed by one or more processors, enable the one or more processors to execute the humidity compensation method based on the adaptive filtering algorithm according to any one of claims 1 to 2.

Images