Detection method and system for furniture formaldehyde detection

Abstract

The invention discloses a detection method and system for furniture formaldehyde detection, relates to the technical field of formaldehyde detection, and improves the detection accuracy of furniture with formaldehyde exceeding the standard. Formaldehyde diffusion display spaces of various types of furniture are established, the formaldehyde diffusion display spaces corresponding to the detected furniture are spliced to obtain the test scene superposition model, and then the predicted formaldehyde detection concentration of each formaldehyde detection space in each time sequence in the test scene superposition model is obtained by improving the Fick diffusion law. Acquiring a real-time formaldehyde concentration value of the formaldehyde detection space, setting an abnormal mark in the formaldehyde detection space in the test scene superposition model according to a comparison result of the real-time formaldehyde concentration value and the predicted formaldehyde detection concentration, generating an abnormal pointing vector according to the spatial position of the formaldehyde detection space with the abnormal mark, and performing abnormal pointing according to the abnormal pointing vector. And the detected furniture with formaldehyde exceeding the standard is positioned according to the abnormal direction vector.

Description

Technical Field

[0001] The present invention relates to the technical field of formaldehyde detection, and specifically to a detection method and system for furniture formaldehyde detection. Background Art

[0002] In modern life, people's requirements for the quality of living and working environments are increasing day by day, and indoor air quality issues have received extensive attention. Among them, formaldehyde, as a common indoor pollutant, poses a serious threat to human health. Long-term exposure to an environment with excessive formaldehyde may trigger various diseases, such as respiratory diseases, skin diseases, and even increase the risk of cancer.

[0003] In previous formaldehyde detection technologies, most used a single sensor or a limited number of detection devices for detection. This method has problems such as limited detection range and incomplete detection data, and it is difficult to accurately reflect the distribution and diffusion of formaldehyde in the entire space. Moreover, traditional detection methods often can only provide formaldehyde concentration information at a certain moment or in a certain local area, and cannot dynamically monitor and analyze the diffusion process of formaldehyde in different types of furniture at different time periods.

[0004] In addition, when multiple pieces of furniture are placed indoors, the formaldehyde released by different furniture affects each other, making the diffusion of formaldehyde more complex. Existing technologies are difficult to accurately predict and analyze the formaldehyde concentration in such complex scenarios, resulting in the inability to timely discover the source of excessive formaldehyde, and thus unable to effectively take measures to reduce the indoor formaldehyde concentration and ensure people's health and safety. Therefore, a detection method and system for furniture formaldehyde detection are provided. Summary of the Invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide a detection method and system for furniture formaldehyde detection.

[0006] In order to achieve the above purpose, the present invention provides the following technical solutions:

[0007] A detection system for furniture formaldehyde detection, characterized in that it includes a scene formaldehyde collection module, a formaldehyde diffusion analysis module, and a scene formaldehyde detection module;

[0008] The scene formaldehyde collection module is used to install a number of micro spectrometers in the test scene, divide the test scene into a number of formaldehyde detection spaces of the same size, and then sequentially place various types of test furniture in the test scene separately, and collect the test formaldehyde diffusion spectrum data of each type of furniture through the micro spectrometers;

[0009] The formaldehyde diffusion analysis module is used to establish a density frame and several time series intervals. The density frame traverses the test formaldehyde diffusion spectrum data collected by different micro spectrometers for the same formaldehyde detection space in various test furniture. According to the traversal results, the upper limit values of normal formaldehyde diffusion concentration in each time series interval are generated, and then the formaldehyde diffusion display space for each type of furniture is established.

[0010] The scene formaldehyde detection module is used to place several test furniture in the test scene, splice the formaldehyde diffusion display spaces corresponding to the test furniture to obtain a test scene superposition model, and then obtain the predicted formaldehyde detection concentration in each formaldehyde detection space in each time series of the test scene superposition model through the improved Fick's diffusion law.

[0011] Obtain the real-time formaldehyde concentration value of the formaldehyde detection space. According to the comparison result between the real-time formaldehyde concentration value and the predicted formaldehyde detection concentration, set abnormal markings in the formaldehyde detection space in the test scene superposition model, generate an abnormal pointing vector according to the spatial position of the formaldehyde detection space with abnormal markings, and then locate the test furniture with excessive formaldehyde according to the abnormal pointing vector.

[0012] Further, the process of collecting the test formaldehyde diffusion spectrum data includes:

[0013] Place several types of test furniture in the test scene in sequence. The types of test furniture include wooden furniture, upholstered furniture, panel furniture, etc. It should be noted that each test furniture is in the state just out of the factory.

[0014] Divide the test scene into several formaldehyde detection spaces of the same size, and set the test data collection duration.

[0015] When various test furniture are in the test scene, each micro spectrometer collects the historical formaldehyde diffusion spectra of each formaldehyde detection space, and integrates the historical formaldehyde diffusion spectra corresponding to the same formaldehyde detection space, and then obtains the test formaldehyde diffusion spectrum data of each formaldehyde detection space.

[0016] Further, the process of generating the upper limit value of normal formaldehyde diffusion concentration includes:

[0017] Establish a two-dimensional coordinate system, map the historical formaldehyde diffusion spectra in the test formaldehyde diffusion spectrum data onto the two-dimensional coordinate system, and set several time series intervals with equal lengths according to the test data collection duration.

[0018] Set a density frame. The length of the density frame is the coordinate length of the time series interval, and the width is equal to half of the difference between the peak value and the valley value of the historical formaldehyde diffusion spectrum segment in each time series interval.

[0019] Traverse all historical formaldehyde diffusion spectrum segments upward from the coordinate axis where the time series interval is located through the density frame until there are no historical formaldehyde diffusion spectrum segments in the density frame;

[0020] Select the median of the numerical interval corresponding to the position where the density frame encloses the largest number of historical formaldehyde diffusion spectrum segments as the upper limit value of the normal formaldehyde diffusion concentration in the corresponding formaldehyde detection space within the corresponding time series interval;

[0021] Connect the upper limit values of the normal formaldehyde diffusion concentration in each time series interval in chronological order to obtain the upper limit curve of the normal formaldehyde diffusion concentration in the corresponding formaldehyde detection space.

[0022] Furthermore, the establishment process of the formaldehyde diffusion display space includes:

[0023] Establish a visualization scene model according to the space size of the test scenario, and divide several formaldehyde detection display spaces in the visualization scene model according to the distribution of the formaldehyde detection space;

[0024] Generate a test furniture model in proportion in the visualization scene model according to the position of each test furniture in the test scenario, and then map the upper limit curves of the normal formaldehyde diffusion concentration of various types of test furniture in each formaldehyde detection space to each formaldehyde detection display space;

[0025] Set the same time slider for each formaldehyde detection display space, so that when dragging the time slider, the expected formaldehyde concentration value is displayed according to the upper limit curve of the normal formaldehyde diffusion concentration in each formaldehyde detection display space, and then the formaldehyde diffusion display space of each type of furniture is obtained.

[0026] Furthermore, the establishment process of the test scenario superposition model includes:

[0027] Place multiple detection furniture in the test scenario, and upload the types of the detection furniture to the scene formaldehyde detection module, and then the scene formaldehyde detection module retrieves the corresponding formaldehyde diffusion display space;

[0028] According to the spatial position distribution of each detection furniture in the test scenario, perform a spatial flip on the corresponding formaldehyde diffusion display space, move the test furniture model in the formaldehyde diffusion display space to the spatial position of the detection furniture in the test scenario, and at the same time, each formaldehyde detection space moves synchronously with the test furniture model as the center;

[0029] Establish a three-dimensional coordinate system, splice the formaldehyde diffusion display spaces after spatial flipping of each detection furniture, and map them in the three-dimensional coordinate system to obtain the test scenario superposition model.

[0030] Furthermore, the calculation formula for the expected formaldehyde detection concentration of each time series is:

[0031]

[0032] Among them, T(x, y, z, t) and T0(x, y, z, t) respectively represent the predicted formaldehyde detection concentration in the formaldehyde detection space with coordinates (x, y, z, t) at the t-th and 0-th time series, Q i，t represents the predicted formaldehyde concentration value of the i-th detected furniture relative to the formaldehyde detection space with coordinates (x, y, z, t) at the t-th time series, r i and D i respectively represent the spatial distance from the i-th detected furniture to the formaldehyde detection space and the formaldehyde diffusion coefficient of the i-th detected furniture, f(Z, H, v) represents the environmental impact function, and Z, H, v respectively represent the temperature, humidity, and ventilation speed of the test scenario, θ i represents the error correction number between the i-th detected furniture and the formaldehyde detection space, erf is the error function, and N represents the total number of time series.

[0033] Furthermore, the process of setting abnormal annotations for the formaldehyde detection spaces in the test scenario superposition model includes:

[0034] Obtain the real-time formaldehyde concentration curves of each formaldehyde detection space in the test scenario;

[0035] Compare the real-time formaldehyde concentration curves of each formaldehyde detection space with the predicted formaldehyde detection concentration in chronological order. If there are no real-time formaldehyde concentration values in the real-time formaldehyde concentration curve that are greater than the predicted formaldehyde detection concentration for more than 1 / 3N number of time series, no operation is performed;

[0036] If there are real-time formaldehyde concentration values greater than the predicted formaldehyde detection concentration for more than 1 / 3N number of time series, set abnormal annotations for the corresponding formaldehyde detection spaces.

[0037] Furthermore, the process of locating the detected furniture with excessive formaldehyde includes:

[0038] For each formaldehyde detection space with abnormal annotations, compare the real-time formaldehyde concentration value of the formaldehyde detection space at its nearest spatial position. If it is determined that its real-time formaldehyde concentration value is greater than the real-time formaldehyde concentration value of the formaldehyde detection space at the nearest spatial position, use it as the end point and the other formaldehyde detection space as the starting point to generate a concentration vector. Conversely, swap the end point and the starting point. If the real-time formaldehyde concentration values are equal, connect a line between the two;

[0039] Repeat the above process of generating concentration vectors to extend the existing concentration vectors until the concentration vectors cannot be extended. Perform vector addition on each concentration vector to obtain an abnormal direction vector;

[0040] Set an abnormal distance range. If there is a detected piece of furniture within the abnormal distance range at the end position of the abnormal pointing vector, it is determined that the formaldehyde in the corresponding detected piece of furniture exceeds the standard. If there is no detected piece of furniture, it is determined that the formaldehyde in the detected piece of furniture closest to the end position of the abnormal pointing vector exceeds the standard.

[0041] A detection method for furniture formaldehyde detection, comprising the following steps:

[0042] Step S1: Install a number of micro spectrometers in the test scenario, divide the test scenario into several formaldehyde detection spaces of the same size, and then place various types of test furniture separately in the test scenario in sequence. Collect the test formaldehyde diffusion spectrum data of each type of furniture through the micro spectrometers.

[0043] Step S2: Establish a density box and several time series intervals. Traverse the test formaldehyde diffusion spectrum data collected by different micro spectrometers for the same formaldehyde detection space by various test furniture through the density box. Generate the upper limit value of the normal formaldehyde diffusion concentration under each time series interval according to the traversal result, and then establish the formaldehyde diffusion display space for each type of furniture.

[0044] Step S3: Place a number of detected pieces of furniture in the test scenario, splice the formaldehyde diffusion display spaces corresponding to the detected pieces of furniture to obtain a test scenario superposition model, and then obtain the predicted formaldehyde detection concentration in each formaldehyde detection space in each time series in the test scenario superposition model through the improved Fick's diffusion law.

[0045] Step S4: Obtain the real-time formaldehyde concentration value of the formaldehyde detection space. According to the comparison result between the real-time formaldehyde concentration value and the predicted formaldehyde detection concentration, set an abnormal annotation in the formaldehyde detection space in the test scenario superposition model. Generate an abnormal pointing vector according to the spatial position of the formaldehyde detection space with the abnormal annotation, and then locate the detected piece of furniture with excessive formaldehyde according to the abnormal pointing vector.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] 1. The present invention obtains the predicted formaldehyde detection concentration in each formaldehyde detection space in each time series through the improved Fick's diffusion law, providing strong data support for accurately locating the detected piece of furniture with excessive formaldehyde while fully considering the complex situation of the mutual influence of formaldehyde when multiple pieces of furniture exist simultaneously.

[0048] 2. The present invention compares the real-time formaldehyde concentration value with the predicted formaldehyde detection concentration, sets an abnormal annotation in the formaldehyde detection space in the test scenario superposition model, and generates an abnormal pointing vector according to the abnormal annotation, thereby achieving rapid and accurate location of the detected piece of furniture with excessive formaldehyde. Description of the Drawings

[0049] Figure 1 This is the schematic diagram of the present invention. Specific embodiments

[0050] 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 detail the specific embodiments, structures, features and their effects of the present invention as follows.

[0051] As Figure 1 shown, a detection system for furniture formaldehyde detection includes a scene formaldehyde collection module, a formaldehyde diffusion analysis module and a scene formaldehyde detection module;

[0052] The scene formaldehyde collection module is used to install a number of micro spectrometers in the test scene, divide the test scene into a number of formaldehyde detection spaces of the same size, and then place various types of test furniture in the test scene in turn. The test formaldehyde diffusion spectrum data of each type of furniture is collected by the micro spectrometer;

[0053] The formaldehyde diffusion analysis module is used to establish a density frame and a number of time series intervals, traverse the test formaldehyde diffusion spectrum data collected by different micro spectrometers for the same formaldehyde detection space by the density frame, generate the upper limit value of the normal formaldehyde diffusion concentration under each time series according to the traversal result, and then establish the formaldehyde diffusion display space of each type of furniture;

[0054] The scene formaldehyde detection module is used to place a number of detection furniture in the test scene, splice the formaldehyde diffusion display spaces corresponding to the detection furniture to obtain a test scene superposition model, and then obtain the predicted formaldehyde detection concentration of each formaldehyde detection space in each time series in the test scene superposition model through the improved Fick diffusion law;

[0055] Obtain the real-time formaldehyde concentration value of the formaldehyde detection space. According to the comparison result between the real-time formaldehyde concentration value and the predicted formaldehyde detection concentration, set an abnormal label in the formaldehyde detection space in the test scene superposition model, generate an abnormal pointing vector according to the spatial position of the formaldehyde detection space with the abnormal label, and then locate the detection furniture with excessive formaldehyde according to the abnormal pointing vector.

[0056] The working principle of the present invention is described below through embodiments:

[0057] The scene formaldehyde collection module evenly installs a number of micro spectrometers in the test scene, where the test scene is a closed space with a volume of 30 to 40 cubic meters, and the spectral capture range of each micro spectrometer can cover the entire test scene space. It should be noted that the temperature, humidity and ventilation speed of the test scene are within a constant range;

[0058] Place several types of test furniture separately in the test scenario in sequence. The types of test furniture include wooden furniture, upholstered furniture, panel furniture, etc. It should be noted that each piece of test furniture is in the state just out of the factory;

[0059] Divide the test scenario into several formaldehyde detection spaces of the same size, and set numbers a1, a2, a2, ……, a n for each formaldehyde detection space, where n is a natural number greater than 0;

[0060] Set the test data collection duration, and the test data collection duration is generally 7 days;

[0061] Collect the preset formaldehyde characteristic absorption band (2.7 - 3.1μm) for each micro - spectrometer, and set the sampling frequency to 1 time per minute. Then, when various test furniture is in the test scenario, each micro - spectrometer collects the historical formaldehyde diffusion spectra of each formaldehyde detection space;

[0062] When the test data collection duration ends, integrate the historical formaldehyde diffusion spectra corresponding to the same formaldehyde detection space, and then obtain the test formaldehyde diffusion spectral data of each formaldehyde detection space, and upload the test formaldehyde diffusion spectral data to the scenario formaldehyde collection module.

[0063] Furthermore, the scenario formaldehyde collection module sends several copies of test formaldehyde diffusion spectral data of all types of furniture to the formaldehyde diffusion analysis module;

[0064] Establish a two - dimensional coordinate system, map the historical formaldehyde diffusion spectra in the test formaldehyde diffusion spectral data onto the two - dimensional coordinate system, and set several time - series intervals of equal length according to the test data collection duration;

[0065] Set a density box. The length of the density box is the coordinate length of the time - series interval, and the width is equal to half of the difference between the peak and valley values of the historical formaldehyde diffusion spectral segments in each time - series interval;

[0066] Traverse all historical formaldehyde diffusion spectral segments upward from the coordinate axis where the time - series interval is located through the density box until there is no historical formaldehyde diffusion spectral segment in the density box;

[0067] Select the middle value of the numerical interval corresponding to the position where the density box encloses the largest number of historical formaldehyde diffusion spectral segments as the upper limit value of the normal formaldehyde diffusion concentration in the corresponding formaldehyde detection space within the corresponding time - series interval;

[0068] Connect the upper limit values of the normal formaldehyde diffusion concentration of each time - series interval in chronological order, and then obtain the upper limit curve of the normal formaldehyde diffusion concentration corresponding to the formaldehyde detection space;

[0069] Establish a visualization scene model according to the spatial size of the test scenario, and divide n formaldehyde detection display spaces in the visualization scene model according to the spatial distribution of formaldehyde detection;

[0070] According to the positions of each test furniture in the test scenario, generate a test furniture model in proportion in the visualization scene model, and then map the upper limit curves of the normal formaldehyde diffusion concentrations of various types of test furniture in each formaldehyde detection space to each formaldehyde detection display space;

[0071] Set the same time slider for each formaldehyde detection display space, so that when dragging the time slider, the expected formaldehyde concentration values are displayed in each formaldehyde detection display space according to the upper limit curve of the normal formaldehyde diffusion concentration, and then the formaldehyde diffusion display spaces of each type of furniture are obtained.

[0072] Furthermore, the formaldehyde dispersion analysis module sends the formaldehyde diffusion display spaces of all types of furniture to the scene formaldehyde detection module;

[0073] The staff places multiple test furniture in the test scenario and uploads the types of the test furniture to the scene formaldehyde detection module, and then the scene formaldehyde detection module retrieves the corresponding formaldehyde diffusion display space;

[0074] According to the spatial position distribution of each test furniture in the test scenario, perform a spatial flip on the corresponding formaldehyde diffusion display space, that is, move the test furniture model in the formaldehyde diffusion display space to the spatial position of the test furniture in the test scenario, and at the same time, each formaldehyde detection space moves synchronously with the test furniture model as the center;

[0075] Establish a three-dimensional coordinate system, splice the formaldehyde diffusion display spaces after spatial flipping of each test furniture, and map them to the three-dimensional coordinate system, and then obtain the test scenario superposition model;

[0076] Since when multiple furniture release formaldehyde, small-scale air convection will form around each furniture due to factors such as temperature and air flow, and the convections around different furniture will interfere with each other. As a result, compared with the case of formaldehyde diffusion of a single piece of furniture, the formaldehyde concentration field when multiple furniture release formaldehyde will not show a simple superposition state, that is, the formaldehyde released by each piece of furniture will compete for space with each other during the diffusion process to the surrounding;

[0077] Furthermore, adopt the improved Fick's diffusion law and the expected formaldehyde concentration values of each formaldehyde detection space in each formaldehyde diffusion display space of each test furniture at each time series to obtain the expected formaldehyde detection concentrations of each formaldehyde detection space in the test scenario superposition model at each time series;

[0078] The calculation formula for the expected formaldehyde detection concentrations of each time series is:

[0079]

[0080] where T(x, y, z, t) and T0(x, y, z, t) respectively represent the predicted formaldehyde detection concentration in the formaldehyde detection space with coordinates (x, y, z, t) at the t-th and 0-th time series, and Q i，t represents the predicted formaldehyde concentration value of the i-th detected furniture relative to the formaldehyde detection space with coordinates (x, y, z, t) at the t-th time series, r i and D i respectively represent the spatial distance from the i-th detected furniture to the formaldehyde detection space and the formaldehyde diffusion coefficient of the i-th detected furniture, f(Z, H, v) represents the environmental impact function, and Z, H, v respectively represent the temperature, humidity, and ventilation speed of the test scenario, θ i represents the error correction number between the i-th detected furniture and the formaldehyde detection space, erf is the error function, and N represents the total number of time series;

[0081] The described scenario formaldehyde acquisition module adopts the process of obtaining the test formaldehyde diffusion spectrum data to obtain the real-time formaldehyde concentration curve of each formaldehyde detection space in the test scenario;

[0082] Compare the real-time formaldehyde concentration curves of each formaldehyde detection space with the predicted formaldehyde detection concentration in chronological order. If there are no real-time formaldehyde concentration values in the real-time formaldehyde concentration curve that are greater than the predicted formaldehyde detection concentration for more than 1 / 3N number of time series, no operation is performed;

[0083] If there are real-time formaldehyde concentration values greater than the predicted formaldehyde detection concentration for more than 1 / 3N number of time series, an abnormal label is set for the corresponding formaldehyde detection space.

[0084] Furthermore, since formaldehyde diffuses from high-concentration areas to low-concentration areas in the air, for each formaldehyde detection space with an abnormal label, compare the real-time formaldehyde concentration value of the formaldehyde detection space at its nearest spatial position. If it is determined that its real-time formaldehyde concentration value is greater than the real-time formaldehyde concentration value of the formaldehyde detection space at the nearest spatial position, then use it as the end point and the other formaldehyde detection space as the starting point to generate a concentration vector. Conversely, if the end point and the starting point are interchanged, and if the real-time formaldehyde concentration values are equal, then connect a line between the two;

[0085] Repeat the above process of generating the concentration vector to extend the existing concentration vector until the concentration vector cannot be extended, and perform vector addition on each concentration vector to obtain the abnormal direction vector;

[0086] Set an abnormal distance range. If there is a detected furniture within the abnormal distance range at the end position of the abnormal pointing vector, it is determined that the formaldehyde of the corresponding detected furniture exceeds the standard. If there is no detected furniture, it is determined that the formaldehyde of the detected furniture closest to the end position of the abnormal pointing vector exceeds the standard.

[0087] The present invention also discloses a detection method for furniture formaldehyde detection, including the following steps:

[0088] Step S1: Install a number of micro spectrometers in the test scenario, divide the test scenario into several formaldehyde detection spaces of the same size, and then place various types of test furniture in the test scenario one by one. Collect the test formaldehyde diffusion spectrum data of each type of furniture through the micro spectrometers.

[0089] Step S2: Establish a density box and several time series intervals. Traverse the test formaldehyde diffusion spectrum data collected by different micro spectrometers for the same formaldehyde detection space by various test furniture through the density box. Generate the upper limit value of the normal formaldehyde diffusion concentration under each time series interval according to the traversal result, and then establish the formaldehyde diffusion display space for each type of furniture.

[0090] Step S3: Place a number of detected furniture in the test scenario, splice the formaldehyde diffusion display spaces corresponding to the detected furniture to obtain a test scenario superposition model, and then obtain the predicted formaldehyde detection concentration of each formaldehyde detection space in each time series in the test scenario superposition model through the improved Fick diffusion law.

[0091] Step S4: Obtain the real-time formaldehyde concentration value of the formaldehyde detection space. According to the comparison result between the real-time formaldehyde concentration value and the predicted formaldehyde detection concentration, set an abnormal label in the formaldehyde detection space in the test scenario superposition model, generate an abnormal pointing vector according to the spatial position of the formaldehyde detection space with the abnormal label, and then locate the detected furniture with excessive formaldehyde according to the abnormal pointing vector.

[0092] As described above, it is only a preferred embodiment of the present invention, and there is no limitation in any form to the present invention. Although the present invention has been disclosed as above with the preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments with equivalent changes within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A detection system for furniture formaldehyde detection, characterized in that, It includes a scene formaldehyde collection module, a formaldehyde diffusion analysis module, and a scene formaldehyde detection module; The scene formaldehyde collection module is used to install a number of micro spectrometers in the test scene, divide the test scene into a number of formaldehyde detection spaces of the same size, and then place various types of test furniture separately in the test scene in turn. The micro spectrometers are used to collect the test formaldehyde diffusion spectral data of each type of furniture; The formaldehyde diffusion analysis module is used to establish a density frame and a number of time series intervals, traverse the test formaldehyde diffusion spectral data collected by different micro spectrometers for the same formaldehyde detection space by various test furniture through the density frame, generate the upper limit values of the normal formaldehyde diffusion concentration under each time series interval according to the traversal results, and then establish the formaldehyde diffusion display spaces for each type of furniture; The scene formaldehyde detection module is used to place a number of detection furniture in the test scene, splice the formaldehyde diffusion display spaces corresponding to the detection furniture to obtain a test scene superposition model, and then obtain the predicted formaldehyde detection concentration of each formaldehyde detection space in each time series in the test scene superposition model through the improved Fick's diffusion law; Obtain the real-time formaldehyde concentration value of the formaldehyde detection space, set an abnormal annotation in the formaldehyde detection space in the test scene superposition model according to the comparison result between the real-time formaldehyde concentration value and the predicted formaldehyde detection concentration, generate an abnormal pointing vector according to the spatial position of the formaldehyde detection space with the abnormal annotation, and then locate the detection furniture with excessive formaldehyde according to the abnormal pointing vector.

2. The detection system for furniture formaldehyde detection according to claim 1, characterized in that, The acquisition process of the test formaldehyde diffusion spectral data includes: Place several types of test furniture separately in the test scene in turn, divide the test scene into a number of formaldehyde detection spaces of the same size, and set the test data acquisition duration; When various test furniture are in the test scene, each micro spectrometer collects the historical formaldehyde diffusion spectra of each formaldehyde detection space, and integrates the historical formaldehyde diffusion spectra corresponding to the same formaldehyde detection space, and then obtains the test formaldehyde diffusion spectral data of each formaldehyde detection space.

3. The detection system for furniture formaldehyde detection according to claim 2, wherein, The generation process of the upper limit value of the normal formaldehyde diffusion concentration includes: Establish a two-dimensional coordinate system, map the historical formaldehyde diffusion spectra in the test formaldehyde diffusion spectral data onto the two-dimensional coordinate system, and set a number of time series intervals of equal length according to the test data acquisition duration; Set a density frame, and traverse all the historical formaldehyde diffusion spectral segments upward from the coordinate axis where the time series interval is located through the density frame until there are no historical formaldehyde diffusion spectral segments in the density frame; Select the middle value of the numerical interval corresponding to the position with the largest number of historical formaldehyde diffusion spectral segments framed by the density frame as the upper limit value of the normal formaldehyde diffusion concentration, and connect the upper limit values of the normal formaldehyde diffusion concentration of each time series interval in chronological order, and then obtain the upper limit curve of the normal formaldehyde diffusion concentration corresponding to the formaldehyde detection space.

4. The detection system for furniture formaldehyde detection according to claim 3, wherein, The establishment process of the formaldehyde diffusion display space includes: Establish a visual scene model according to the spatial size of the test scene, and divide a number of formaldehyde detection display spaces in the visual scene model according to the distribution of the formaldehyde detection spaces; According to the positions of each test furniture in the test scenario, a test furniture model is generated proportionally in the visualization scenario model, and then the upper limit curves of the normal formaldehyde diffusion concentrations of various types of test furniture in each formaldehyde detection space are mapped into each formaldehyde detection display space.

5. The detection system for furniture formaldehyde detection according to claim 4, characterized in that, The establishment process of the test scenario superposition model includes: Retrieve the formaldehyde diffusion display space according to the types of the detected furniture, and perform a spatial flip on the corresponding formaldehyde diffusion display space according to the spatial position distribution of each detected furniture in the test scenario. Move the test furniture model in the formaldehyde diffusion display space to the spatial position of the detected furniture in the test scenario. At the same time, each formaldehyde detection space moves synchronously with the test furniture model as the center; Establish a three-dimensional coordinate system, splice the formaldehyde diffusion display spaces after spatial flipping of each detected furniture, and map them into the three-dimensional coordinate system to obtain the test scenario superposition model.

6. The detection system for furniture formaldehyde detection according to claim 5, characterized in that, Adopt the improved Fick's diffusion law and the predicted formaldehyde concentration values of each formaldehyde detection space in each formaldehyde diffusion display space of each detected furniture at each time series to obtain the predicted formaldehyde detection concentrations of each formaldehyde detection space in the test scenario superposition model at each time series.

7. The detection system for furniture formaldehyde detection according to claim 6, wherein, The process of setting abnormal annotations for the formaldehyde detection spaces in the test scenario superposition model includes: Obtain the real-time formaldehyde concentration curves of each formaldehyde detection space in the test scenario, compare the real-time formaldehyde concentration curves of each formaldehyde detection space with the predicted formaldehyde detection concentrations in sequence according to the time order, and set abnormal annotations for the corresponding formaldehyde detection spaces according to the comparison results.

8. The detection system for furniture formaldehyde detection according to claim 7, characterized in that, The positioning process of the detected furniture with excessive formaldehyde includes: For each formaldehyde detection space with an abnormal annotation, compare the real-time formaldehyde concentration value of the formaldehyde detection space at its nearest spatial position. If it is determined that its real-time formaldehyde concentration value is greater than the real-time formaldehyde concentration value of the formaldehyde detection space at the nearest spatial position, then use it as the end point and the other formaldehyde detection space as the starting point to generate a concentration vector. Conversely, the end point and the starting point are interchanged. If the real-time formaldehyde concentration values are equal, then connect a line between the two; Repeat the process of generating the concentration vector to extend the existing concentration vectors until the concentration vectors cannot be extended. Perform vector addition on each concentration vector to obtain an abnormal pointing vector; Set an abnormal distance range. If there is a detected furniture within the abnormal distance range at the end position of the abnormal pointing vector, it is determined that the formaldehyde of the corresponding detected furniture exceeds the standard. If there is no detected furniture, it is determined that the formaldehyde of the detected furniture closest to the end position of the abnormal pointing vector exceeds the standard.

9. A detection method for furniture formaldehyde detection, which is used to implement a detection system for furniture formaldehyde detection according to any one of claims 1-8, characterized in that, It includes the following steps: Step S1: Install several micro spectrometers in the test scenario, divide the test scenario into several formaldehyde detection spaces of the same size, and then place various types of test furniture in the test scenario separately in sequence. Collect the test formaldehyde dispersion spectrum data of each type of furniture through the micro spectrometers; Step S2: Establish a density frame and several time series intervals. Traverse the test formaldehyde diffusion spectrum data collected by different micro spectrometers for the same formaldehyde detection space through various test furniture. Generate the upper limit values of the normal formaldehyde diffusion concentration under each time series interval according to the traversal results, and then establish the formaldehyde diffusion display space for each type of furniture. Step S3: Place several pieces of test furniture in the test scenario, splice the formaldehyde diffusion display spaces corresponding to the test furniture to obtain a test scenario superposition model, and then obtain the predicted formaldehyde detection concentration in each formaldehyde detection space in each time series in the test scenario superposition model by improving Fick's diffusion law. Step S4: Obtain the real-time formaldehyde concentration value of the formaldehyde detection space. According to the comparison result between the real-time formaldehyde concentration value and the predicted formaldehyde detection concentration, set an abnormal annotation in the formaldehyde detection space in the test scenario superposition model. Generate an abnormal pointing vector according to the spatial position of the formaldehyde detection space with the abnormal annotation, and then locate the test furniture with excessive formaldehyde according to the abnormal pointing vector.

Images