Data acquisition and analysis method of intelligent sofa

Abstract

The application provides a data acquisition and analysis method of an intelligent sofa, comprising: setting an electrostatic sensor array on the intelligent sofa to acquire electrostatic signal intensity and polarity distribution, human body charge, and environmental humidity data of different areas on the sofa surface in real time to obtain electrostatic distribution data; under different air quality conditions including pollutant concentration and particulate matter content, a mapping relationship model of electrostatic characteristic parameters and air quality is trained through a support vector machine algorithm according to the electrostatic characteristic parameters; the real-time acquired sofa electrostatic signal intensity is input into the trained mapping relationship model of electrostatic characteristic and air quality to obtain the change of the electrostatic characteristic and evaluate indoor air quality in real time; if the evaluation result shows that the air quality is less than an air quality threshold value, an air purification device of the intelligent sofa is triggered, an air purifier is started, and the air exchange amount of a fresh air system is increased to improve the indoor air environment.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a data collection and analysis method for a smart sofa. Background Art

[0002] Smart sofas play a vital role in our daily lives. They not only provide a comfortable resting experience but also serve as a crucial tool for monitoring the home environment. Different sitting positions on sofas lead to variations in static electricity accumulation, raising an interesting technical question: can static electricity data collected from sofas be used to analyze home air quality? Static electricity is caused by uneven surface charge distribution, and factors such as dust and pollutants in the air can also affect static electricity accumulation. Sofas made of different materials and shapes also exhibit varying levels of static electricity accumulation. Furthermore, the human body carries a certain amount of charge, which transfers when in contact with the sofa. Taking all these factors into account, accurately collecting and distinguishing static electricity signals from sofas and correlating them with air quality presents a complex technical challenge. Collecting static electricity data requires highly sensitive sensors, while data processing and analysis algorithms must also account for numerous interfering factors, such as human motion and ambient humidity. Extracting effective static electricity signatures from noisy environments and building reliable air quality assessment models to achieve more comprehensive and detailed environmental perception, thus providing new possibilities for creating healthier and more comfortable living environments, remains a pressing technical challenge. Summary of the Invention

[0003] The present invention provides a data collection and analysis method for a smart sofa, which mainly includes:

[0004] By setting up an electrostatic sensor array on the smart sofa, the static signal intensity and polarity distribution, human body charge, and environmental humidity data of different areas on the sofa surface are collected in real time to obtain static distribution data;

[0005] Based on the static electricity distribution data, a static electricity accumulation model was established according to different sofa materials and shapes. Static electricity measurement equipment was used to conduct accumulation experiments under different conditions to obtain static electricity distribution measurement data, and the static electricity measurement data was normalized.

[0006] Based on the normalized electrostatic measurement data, wavelet transform and frequency domain analysis were used for signal processing to extract electrostatic characteristic parameters that reflect the data change trend and obtain air quality indicators. Correlation analysis was used to obtain the correlation strength between different electrostatic characteristic parameters and air quality indicators, and electrostatic characteristic parameters associated with air quality were screened out.

[0007] Under different air quality conditions, including pollutant concentration and particulate matter content, the mapping relationship model between electrostatic characteristic parameters and air quality is trained using the support vector machine algorithm based on the electrostatic characteristic parameters;

[0008] The real-time collected static signal strength of the sofa is input into the trained mapping relationship model between static characteristics and air quality to obtain the changes in static characteristics and evaluate the indoor air quality in real time.

[0009] If the evaluation result shows that the air quality is lower than the air quality threshold, the air purification device of the smart sofa will be triggered to turn on the air purifier and increase the ventilation volume of the fresh air system to improve the indoor air environment.

[0010] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0011] The present invention discloses a data collection and analysis method for a smart sofa. The present invention sets a high-sensitivity electrostatic sensor array on the smart sofa to collect the electrostatic signal intensity and polarity distribution, human body charge, and environmental humidity data in different areas of the sofa surface in real time to obtain electrostatic distribution data. Combined with the geometric shape data of the sofa, the detailed features of the folds and seams on the sofa surface are extracted, the folds and seams area is judged, the electrostatic accumulation risk coefficient of the area is determined, and an electrostatic accumulation model is established. Wavelet transform and frequency domain analysis signal processing are used to extract electrostatic characteristic parameters. Through a machine learning algorithm, a mapping relationship model between electrostatic characteristic parameters and air quality is established to achieve real-time evaluation of indoor air quality. When the air quality is lower than the threshold, the air purification device is automatically turned on to improve the indoor air environment. By correlating electrostatic signals with air quality, the present invention realizes intelligent air quality monitoring and regulation, thereby improving the comfort and health level of the indoor environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 The present invention provides a flow chart of a data collection and analysis method for a smart sofa. DETAILED DESCRIPTION

[0013] The following will describe the technical solutions in the embodiments of the present invention in detail with reference to the accompanying drawings. The described embodiments are only a part of the embodiments of the present invention.

[0014] like Figure 1 In this embodiment, a data collection and analysis method for a smart sofa may specifically include:

[0015] In step S101, an electrostatic sensor array is set on the smart sofa to collect the electrostatic signal intensity and polarity distribution, human body charge, and environmental humidity data of different areas on the sofa surface in real time to obtain electrostatic distribution data.

[0016] An electrostatic sensor array is provided on the surface of a sofa, wherein the electrostatic sensor array is arranged in a grid shape, and an electrostatic sensor is placed at each grid point to obtain electrostatic signal distribution data; the electrostatic signal distribution data is filtered and denoised using a wavelet transform to obtain filtered electrostatic signal data; the electric field intensity distribution on the sofa surface is calculated based on the filtered electrostatic signal data, and the electrostatic accumulation in the human body contact area is identified by analyzing the charge density to obtain electrostatic accumulation area data; the electrostatic accumulation area data is classified using a K-means clustering algorithm to identify different types of electrostatic interference sources and obtain electrostatic interference source classification results; and the electrostatic safety status is evaluated based on the electrostatic interference source classification results.

[0017] For example, an electrostatic sensor array is set up on the sofa surface based on its sensitivity characteristics, using a grid arrangement with one electrostatic sensor placed at each grid point and a spacing of 10 cm between sensors. The sensor detection threshold is determined based on the electrostatic signal intensity range. The sensor response time is adjusted by signal sampling accuracy and real-time acquisition frequency. The sensor array density layout is optimized using data transmission bandwidth to generate a high-precision electrostatic signal distribution map. Based on the initial measurement results, the sensor sensitivity is dynamically adjusted using a gradient descent method.

[0018] Wavelet transforms were used to filter and reduce noise in the collected electrostatic signal intensity and polarity distribution. Signal feature extraction was used to separate human body charge from environmental static interference. A weighted average method was used to integrate the static distribution data from different areas of the sofa surface to generate a global static distribution map. Time series analysis of the static distribution map was performed, and a moving average method was used to identify static accumulation trends.

[0019] The electric field intensity distribution on the sofa surface is calculated based on the static distribution map, and a charge density analysis algorithm is used to identify static electricity accumulation in areas of human contact. Coulomb's law is used to calculate the electrostatic force, and combined with the surface charge density distribution, the electrostatic discharge risk is predicted. Time series analysis of the static distribution data is used to determine the trend of static electricity accumulation and assess the static safety status of the sofa surface.

[0020] A K-means clustering algorithm is used to classify ESD distribution data and identify different types of ESD interference sources. Spatial correlation analysis of ESD distribution data is used to optimize sensor array layout, calculating the Pearson correlation coefficient of adjacent sensor data to adjust sensor density. Sensor sampling frequency is automatically adjusted based on ESD safety status assessment results, increasing the sampling frequency when static accumulation trends are evident and decreasing it to save energy. The data compression rate is dynamically adjusted based on the data transmission bandwidth, optimizing transmission efficiency while ensuring data quality.

[0021] The electrostatic sensor array on the sofa surface is arranged in a grid pattern with a spacing of 10 cm. Each grid point houses an electrostatic sensor with a sensitivity of 0.1 pC. The sensor detection threshold is set to 0.5 pC, the signal sampling accuracy is 16 bits, and the real-time acquisition frequency is 100 Hz. Using a 10 Mbps data transmission bandwidth, the sensor array density is optimized to generate a high-precision electrostatic signal distribution map with a resolution of 100 x 50 pixels. Initial measurement results show that the electrostatic signal intensity fluctuates between 0.2 and 0.8 pC. A gradient descent method with a learning rate of 0.01 is used to dynamically adjust the sensor sensitivity every 100 samples. The collected electrostatic signal is decomposed using a db4 wavelet transform with a five-layer decomposition and a soft threshold of 0.05 for data noise reduction. By comparing the correlation between adjacent sensor signals, the body charge signature is extracted and separated from environmental electrostatic interference. The electrostatic distribution data from different regions is integrated using a weighted average method, with weights set based on signal strength, to generate a global electrostatic distribution map with a resolution of 300 x 150 pixels. Time series analysis of the electrostatic distribution map is performed, using a 10-minute moving average window to identify trends in electrostatic accumulation. The electric field intensity distribution on the sofa surface is calculated based on the electrostatic distribution diagram, and the electric field intensity range is 0.1-2kV / m. By setting the charge density threshold to 1nC / cm 2 , identify the static electricity accumulation in the human body contact area. Use Coulomb's law to calculate the electrostatic force, combined with 10nC / m 2 The surface charge density distribution is used to predict the risk of electrostatic discharge. When the calculated electrostatic force exceeds 0.1mN, it is judged as a high-risk area. Based on the judgment standard that the electrostatic accumulation rate exceeds 0.5nC / min within 10 minutes, the electrostatic safety status assessment result of the sofa surface is obtained. The K-means clustering algorithm is used to classify the electrostatic distribution data, and the K value is set to 3 to identify the three sources of electrostatic interference: human body, fabric friction and environment. The Pearson correlation coefficient of adjacent sensor data is calculated, and when the coefficient is lower than 0.5, the sensor density in the area is increased. According to the results of the electrostatic safety status assessment, the sampling frequency is increased to 200Hz when the electrostatic accumulation trend is obvious, and otherwise reduced to 50Hz to save energy. The data transmission bandwidth is dynamically adjusted. When the bandwidth utilization rate exceeds 80%, the data compression ratio is increased from 1:1 to 2:1, optimizing transmission efficiency while ensuring data quality.

[0022] Step S102 : Based on the static electricity distribution data and according to different sofa materials and shapes, a static electricity accumulation model is established, and static electricity measurement equipment is used to perform accumulation experiments under different conditions to obtain static electricity distribution measurement data, and the static electricity measurement data is normalized.

[0023] A clustering algorithm is used to classify sofa materials to obtain leather, fabric, and suede material categories; the corresponding resistivity range is determined according to the material category to obtain material characteristic parameters; a static electricity accumulation model is constructed by combining the material characteristic parameters with the three-dimensional shape data of the sofa; an experimental plan is designed according to the static electricity accumulation model, and a static electricity accumulation experiment is carried out under different conditions specified in the experimental plan using static electricity measurement equipment; the static electricity measurement data obtained from the static electricity accumulation experiment is cleaned, and missing data in the static electricity measurement data is supplemented using the cubic spline interpolation method; the static electricity measurement data is unified into the range of 0-1 using the maximum and minimum value normalization method to obtain normalized static electricity distribution data; and a static electricity accumulation prediction model is established based on the normalized static electricity distribution data.

[0024] For example, sofa materials were classified based on static electricity distribution data. A K-means clustering algorithm was used to categorize the materials into leather, fabric, and suede. The resistivity range for each material was determined. The surface charge density of the materials was measured and combined with the resistivity to calculate electrostatic characteristic parameters, including the charge decay time constant and the maximum charge accumulation. Combined with the sofa's three-dimensional shape data, an electrostatic accumulation model was constructed, which took into account material properties, geometry, and environmental factors. Based on this electrostatic accumulation model, an experimental plan was designed and accumulation experiments were conducted using electrostatic measurement equipment under different conditions. A constant temperature and humidity chamber was used to maintain the ambient temperature between 20°C and 30°C, and the relative humidity varied between 30% and 70%. A standard friction device was used to simulate human contact, with the friction intensity controlled within the range of 0.1-1N. An electrostatic field strength meter was used to measure the electric field strength on the sofa surface, ranging from 0 to 100 kV / m. An electrostatic voltmeter was used to record the electrostatic voltage at different locations, measuring from 0 to 10 kV. An electrostatic ammeter was used to measure the electrostatic leakage current, measuring from 0 to 100 μA. Each set of experimental conditions was measured 5 times to obtain a complete electrostatic distribution measurement data set. The electrostatic measurement data was cleaned, and the outlier threshold was set to the mean ± 3 times the standard deviation, and data points outside this range were removed. The cubic spline interpolation method was used to fill in the missing data to ensure the continuity and smoothness of the data. The electrostatic data of different dimensions were unified into the range of 0-1 by the maximum and minimum normalization method. The calculation formula is X normalization = (X-Xmin) / (Xmax-Xmin), where X is the original data, Xmin and

[0025] Xmax are the minimum and maximum values ​​of this type of data respectively. A standardized static distribution data set is obtained, which contains information such as material type, shape characteristics, environmental conditions, static electricity intensity and distribution. Based on the normalized static electricity distribution data, a static electricity accumulation prediction model is established using the random forest regression algorithm. The input variables include material type, shape characteristics, environmental conditions and other factors, and the output variables are static electricity intensity and distribution. The model accuracy is evaluated using ten-fold cross validation, and the root mean square error (RMSE) and determination coefficient (R 2 ) as the evaluation metric. The hyperparameters of random forest were optimized by grid search, including the number of trees, ranging from 50 to 500, and the maximum depth, ranging from 5 to 20. The model with the smallest RMSE and R 2 The maximum parameter combination is used to obtain the final electrostatic accumulation model. This model can predict the electrostatic accumulation of sofas of different materials and shapes under various environmental conditions. During the electrostatic distribution data collection process, the K-means clustering algorithm is used to classify 100 sofa material samples, and the cluster number K is set to 5. After 50 iterations, five categories of leather, fabric, suede, synthetic leather and composite materials are obtained. For each material, the four-probe method is used to measure the resistivity. For example, the resistivity range of leather materials is 10^6-10^9Ω·m. The surface charge density of the material is measured using an electrostatic meter, and the value range is 0.1-10nC / cm 2. Combining resistivity and charge density, the charge decay time constant τ = ρε is calculated, where ρ is resistivity, ε is dielectric constant, and the τ value range is 0.1-100 seconds. The sofa shape data was obtained by a 3D scanner with a resolution of 1mm. The constructed static electricity accumulation model takes into account material properties, geometric shape and environmental factors, and the finite element method is used for numerical simulation. Based on the model design experimental plan, a constant temperature and humidity chamber is used to control the environment with a temperature range of 20-30℃ and a relative humidity of 30-70%, with a step size of 2℃ and 5%. The standard friction device simulates human body contact with a friction force range of 0.1-1N and a step size of 0.1N. The electrostatic field strength meter has a measurement range of 0-100kV / m and an accuracy of ±1%. The electrostatic voltmeter has a measurement range of 0-10kV and a resolution of 1V. The electrostatic ammeter has a measurement range of 0-100μA and an accuracy of ±0.1%. The measurement was repeated 5 times for each set of conditions, and a total of 10,000 data points were obtained. During the data cleaning process, the outlier threshold was set to μ±3σ, where μ is the mean and σ is the standard deviation, and about 300 outliers were removed. The cubic spline interpolation method was used to fill in 50 missing data points. After normalization, a standardized electrostatic distribution data set of 9750 valid data points was obtained. The random forest regression algorithm was used to establish an electrostatic accumulation prediction model. The input variables included 5 categories of material type, 10 parameters of shape characteristics, and 3 variables of environmental conditions. The output variables were 5 parameters of electrostatic intensity and distribution. The materials can be synthetic fiber materials such as polyester fiber, natural fiber materials such as cotton or wool, leather materials including artificial leather or genuine leather, plastic or polymer materials such as polyvinyl chloride (PVC), wood or wood composite materials. The shape features may be: total length is the overall length of the sofa, total width is the overall width of the sofa, total height is the overall height of the sofa, seat area is the area of ​​the seat part, seat depth is the distance from the front to the back of the seat, seat height is the height from the seat surface to the ground, armrest height is the height from the armrest to the seat surface, armrest width is the width of the armrest, backrest angle is the angle between the backrest and the seat surface, and backrest height is the height of the backrest. Environmental conditions include the temperature, relative humidity and atmospheric pressure of the environment. The electrostatic strength and distribution may include the maximum electrostatic voltage is the maximum electrostatic voltage that may appear on the surface of the sofa, the average electrostatic voltage is the average electrostatic voltage on the surface of the sofa, the electrostatic energy is the electrostatic energy accumulated on the surface of the sofa, the electrostatic field strength is the electrostatic field strength around the sofa, and the charge distribution is the charge distribution on the surface of the sofa, such as the charge density in different parts. The accuracy of the model was evaluated by ten-fold cross validation, with an RMSE of 0.15 and a coefficient of determination R 2 The grid search method was used to optimize the hyperparameters, and the number of trees was finally determined to be 300 with a maximum depth of 12. The resulting electrostatic accumulation model achieved a prediction accuracy of 92% on the test set.

[0026] Based on the geometric shape data of the sofa, the detailed features of the folds and seams on the sofa surface are extracted, the folds and seams area is identified, and the electrostatic accumulation risk coefficient of the area is determined. Combined with the material and electrostatic distribution data of different sofas, an electrostatic accumulation model is established.

[0027] Based on 3D scanning data of a sofa, the surface curvature distribution of the sofa was calculated using the discrete Gaussian curvature method, identifying surface wrinkle areas. For these surface wrinkle areas, seam line features were extracted to determine the precise location and extent of the wrinkle seams. Structured light 3D scanning was used to measure the seam depth and width of these wrinkle seams, and a geometric and electrical property model of these wrinkle seams was established. An electrostatic field simulation was performed to obtain the electric field intensity distribution of these wrinkle seams. If the electric field intensity distribution exceeded a preset threshold, the wrinkle seam area was determined to be at risk of static electricity accumulation. Electrostatic characteristic parameters of the sofa material, including dielectric constant, surface resistivity, and charge decay time constant, were extracted from a pre-established material database. The charge density and electric field intensity information from the electrostatic distribution data were combined to construct a basic static electricity accumulation model that incorporates material properties. A multilayer perceptron neural network was used to construct a static electricity accumulation prediction model. The input layer of the neural network includes material parameters, geometric features, and environmental factors, and the output layer represents the amount of static electricity accumulated in different areas. The model parameters of the neural network were optimized using a backpropagation algorithm to obtain the final static electricity accumulation model.

[0028] For example, based on the three-dimensional scanning data of the sofa, the discrete Gaussian curvature calculation method is used to calculate the curvature distribution of the sofa surface, and the surface wrinkle area is identified by setting the curvature threshold to 0.1cm^(-1). The Canny edge detection algorithm is used to extract the seam line features, and the dual thresholds are set to a low threshold of 50 and a high threshold of 150. Combining the curvature and edge information, the precise position and range of the wrinkle seam area are determined through the expansion and corrosion operations in the morphological operation. For the identified wrinkle seam area, the seam depth and width are measured using structured light three-dimensional scanning technology, and the scanning resolution is set to 0.1mm. Combined with the material resistivity data, a geometric and electrical characteristic model of the wrinkle seam area is established. The electrostatic field simulation is performed using COMSOL Multiphysics software, the grid size is set to 0.5mm, and the MUMPS direct solver is selected as the solver to calculate the electric field intensity distribution in the area. According to the maximum value and gradient of the electric field intensity, the electrostatic accumulation risk coefficient of the wrinkle seam area is obtained. Based on the sofa material classification results, corresponding electrostatic characteristic parameters were extracted from a pre-established material database. These parameters include dielectric constant (range: 1-10), surface resistivity (unit: Ω / sq, range: 10^6-10^14), and charge decay time constant (range: 0.1-100s). Combined with the charge density (unit: C / m^2) and electric field strength (unit: V / m) information from the electrostatic distribution data, a basic electrostatic accumulation model that considers material properties was constructed. This model uses an exponential decay function to describe the temporal evolution of electrostatic charge. The electrostatic accumulation risk factor in the wrinkle seam area was used as a weighting factor and integrated with the basic electrostatic accumulation model. A three-layer multilayer perceptron neural network was used to construct the electrostatic accumulation prediction model. The network structure consists of 10 neurons in the input layer, including 3 material parameters, 4 geometric features, and 3 environmental factors. The hidden layer has 20 neurons and the output layer has 5 neurons, representing the amount of electrostatic accumulation in different areas. The output of the basic electrostatic accumulation model serves as an additional input feature of the neural network. The model parameters were optimized by the back-propagation algorithm, with the learning rate set to 0.01 and the number of iterations to 1000 times, to obtain the final electrostatic accumulation model. In practical applications, the sofa was first scanned using a high-precision 3D laser scanner to obtain point cloud data with a resolution of 0.5mm. The point cloud data was processed using the discrete Gaussian curvature calculation method to calculate the curvature value of each point, and the curvature threshold was set to 0.1cm^(-1) to identify the surface wrinkle area. The Canny edge detection algorithm was then applied with the low threshold set to 50 and the high threshold set to 150 to extract the seam line features. Through 3x3 pixel morphological dilation and corrosion operations, the wrinkle area and seam features were fused to accurately locate the wrinkle seam area. Using structured light 3D scanning technology, the seam depth and width were measured with a resolution of 0.1mm, and data such as the depth range of 1-5mm and the width range of 2-8mm were obtained.The geometric data was combined with the pre-measured material resistivity, such as 10^9Ω·m for leather, to establish an electrostatic field model in COMSOL Multiphysics software. A grid size of 0.5mm was set, and the MUMPS direct solver was used to calculate the electric field distribution. The maximum electric field strength was 5kV / m, and the electrostatic accumulation risk factor was calculated to be 0.8. Electrostatic characteristic parameters were extracted from the material database, such as the dielectric constant of leather of 2.5, the surface resistivity of 10^11Ω / sq, and the charge decay time constant of 5s. Combined with the measured charge density of 2x10^-6C / m^2 and the electric field strength data, a basic model of electrostatic accumulation was constructed. The exponential decay function Q(t) = Q_0*e^(-t / τ) was used to describe the change of electrostatic charge over time. Q(t) is the residual electrostatic charge at time t, Q0 is the initial time, which refers to the electrostatic charge at t = 0, t is the time elapsed from the initial time, and τ is the time constant, which represents the time required for the charge to decay to 1 / e of its initial value (approximately 36.8%). The time constant τ reflects the rate of electrostatic charge decay: a larger τ indicates slower charge decay, and vice versa. Finally, a three-layer multilayer perceptron neural network was constructed. The input layer consisted of 10 neurons, including three material parameters (dielectric constant, surface resistivity, and decay time constant); four geometric features (curvature, depth, width, and area); and three environmental factors (temperature, humidity, and number of frictions). The hidden layer consisted of 20 neurons, and the output layer consisted of five neurons representing the static charge accumulation in different regions. The output of the basic model was used as an additional input feature, and the parameters were optimized using a backpropagation algorithm with a learning rate of 0.01 and 1000 iterations. The final model achieved 95% prediction accuracy on the test set.

[0029] In step S103, based on the normalized electrostatic measurement data, wavelet transform and frequency domain analysis are used to perform signal processing, extract electrostatic characteristic parameters used to reflect the data change trend, obtain air quality indicators, and use correlation analysis methods to obtain the correlation strength between different electrostatic characteristic parameters and air quality indicators, and screen out electrostatic characteristic parameters associated with air quality.

[0030] The normalized electrostatic measurement data is subjected to a wavelet transform and denoised using a soft thresholding method. The denoised electrostatic data is then subjected to a fast Fourier transform to obtain a frequency domain representation. The power spectral density is calculated, and frequency domain characteristic parameters, including dominant frequency, frequency band energy ratio, and harmonic distortion, are extracted from the data. These frequency domain characteristic parameters are combined with time domain characteristics to form an electrostatic characteristic parameter set, which is used to establish a correlation between the electrostatic characteristics and air quality. Synchronously collected air quality data is obtained and cleaned and preprocessed. Outliers are removed using the moving median method, missing values ​​are filled using linear interpolation, and a normalized air quality index dataset is obtained using z-score normalization. The correlation between the electrostatic characteristic parameters and the normalized air quality index is calculated using the Pearson correlation coefficient. If the correlation coefficient is greater than a preset threshold, a subset of electrostatic characteristic parameters strongly correlated with the air quality index is selected. Dimensionality reduction is performed using principal component analysis. The first preset principal components whose cumulative contribution rate reaches a preset value are selected and linearly combined to obtain the electrostatic characteristic parameters for air quality assessment.

[0031] Exemplarily, the normalized electrostatic measurement data is subjected to a wavelet transform. Based on the frequency characteristics and data length of the electrostatic signal, the db4 wavelet basis function and 5-level decomposition are selected. After eliminating high-frequency noise, the reconstructed signal is obtained as a smoothed electrostatic data sequence. The smoothed electrostatic data sequence is subjected to a fast Fourier transform to obtain a frequency domain representation, and the power spectral density is calculated. Frequency domain characteristic parameters are extracted, including the main frequency, the frequency band energy ratio, and the harmonic distortion. The main frequency is determined by finding the frequency corresponding to the maximum power spectral density, the frequency band energy ratio is obtained by calculating the ratio of the energy within a specific frequency band to the total energy, and the harmonic distortion is obtained by calculating the ratio of the harmonic component to the fundamental component. Time domain features such as mean, variance, skewness, and kurtosis are combined to form a set of electrostatic characteristic parameters. To establish a correlation between electrostatic characteristics and air quality, air quality data is collected simultaneously. Air quality indicator data such as PM2.5, PM10, ozone, and sulfur dioxide are collected using air quality monitoring equipment. The raw air quality data was cleaned and preprocessed. Outliers were removed using the moving median method, and missing values ​​were filled using linear interpolation. The processed data was z-score normalized to obtain a normalized air quality index dataset with a mean of 0 and a standard deviation of 1. The correlation between electrostatic characteristic parameters and air quality indicators was calculated using the Pearson correlation coefficient, with a correlation coefficient threshold of 0.7. A subset of electrostatic characteristic parameters strongly correlated with air quality indicators was selected. Dimensionality reduction was performed using principal component analysis. The selected features were first normalized, the covariance matrix between the features was calculated, and eigenvalue decomposition was performed. The top principal components with a cumulative contribution rate of 95% were selected and linearly combined to obtain the key electrostatic characteristic parameters used for air quality assessment. In practical applications, the 10,000 collected electrostatic measurement data points were first normalized to a range between 0 and 1. The normalized data was then subjected to a 5-level wavelet decomposition using the db4 wavelet basis function to obtain wavelet coefficients at different scales. Soft thresholding was used for denoising, with a threshold of approximately 0.3, effectively removing high-frequency noise. After reconstruction, a smoothed electrostatic data sequence is obtained, and the number of data points remains unchanged. A 1024-point fast Fourier transform is performed on the smoothed sequence to calculate the power spectral density. The frequency domain feature parameters are extracted, such as the main frequency is found to be around 50Hz, the 0-100Hz frequency band energy ratio accounts for about 80% of the total energy, and the harmonic distortion is about 5%. Combined with time domain features such as mean 0.5, variance 0.04, skewness 0.1, and kurtosis 3.2, a 15-dimensional electrostatic feature parameter set is formed. Air quality data, including PM2.5, is collected synchronously, with a range of 0-500μg / m 3 , PM10, which ranges from 0-600μg / m 3, ozone, with a range of 0-500ppb, sulfur dioxide, with a range of 0-500ppb and other indicators, with a sampling interval of 5 minutes, for a total of 24 hours of data. The moving median method is used with a window size of 5 to remove outliers, and the linear interpolation method is used to fill in about 2% of missing values. The normalized air quality index data set is obtained by z-score standardization. The Pearson correlation coefficient between the 15 electrostatic characteristic parameters and the 4 air quality indicators is calculated, and the threshold of 0.7 is set to screen out 8 strongly correlated electrostatic characteristic parameters. Principal component analysis is performed on these 8 features, and the top 3 principal components with a cumulative contribution rate of 95% are selected, and finally 3 key electrostatic characteristic parameters are obtained for air quality assessment.

[0032] Step S104 , under different air quality conditions, including pollutant concentration and particulate matter content, a mapping relationship model between electrostatic characteristic parameters and air quality is trained using a support vector machine algorithm based on the electrostatic characteristic parameters.

[0033] The electrostatic characteristic parameters and corresponding pollutant concentration and particulate matter content data under different air quality conditions are obtained for constructing a training data set; the training data set is subjected to Z-score standardization, and the standardized electrostatic characteristic parameters are screened using a recursive feature elimination method to determine an optimal feature combination; based on the optimal feature combination, the kernel function type, regularization parameter C and kernel function parameter γ of a support vector machine are optimized using a grid search method to obtain an optimal parameter combination; using the optimal feature combination and the optimal parameter combination, a support vector machine algorithm is used to train a mapping relationship model between the electrostatic characteristic parameters and air quality; corresponding sub-models are trained for different air quality conditions, and the sub-models are trained based on the mapping relationship model to improve the adaptability of the sub-models under various pollution levels.

[0034] Exemplarily, a training data set is constructed based on the electrostatic characteristic parameters under different air quality conditions and the corresponding pollutant concentration and particulate matter content data. The data is Z-score standardized, the mean μ and standard deviation σ of each feature are calculated, and the data is converted to a standard normal distribution with a mean of 0 and a standard deviation of 1 by (x-μ) / σ, which is applicable to data of different dimensions and distributions. The electrostatic characteristic parameters are screened using the recursive feature elimination method. The number of features is gradually increased from 1 to the total number of features, and a 5-fold cross-validation is performed on each feature subset to calculate the root mean square error. When the increase in the number of features results in a performance improvement of less than 1%, the number is set as the feature number threshold. Select the optimal feature combination to reduce model complexity and improve generalization ability. Based on the optimal feature combination screened out, the kernel function type, regularization parameter C and kernel function parameter γ of the support vector machine are optimized using the grid search method. Set the parameter search range. The kernel function types include linear kernel, polynomial kernel and radial basis kernel function RBF. The range of C is

[0035] [0.1, 1, 10, 100], and the range of γ is [0.001, 0.01, 0.1, 1]. 5-fold cross validation is used to evaluate the performance of each set of parameters and select the optimal parameter combination. Based on the optimized parameters and feature combinations, the support vector machine algorithm is used to train the mapping relationship model between electrostatic feature parameters and air quality. The sequential minimum optimization algorithm is used to solve the model parameters, and the maximum number of iterations is set to 1000, and the convergence threshold is 1e-3. The model performance is evaluated through 10-fold cross validation, and the root mean square error and determination coefficient are calculated to judge the prediction accuracy and fit of the model. For different air quality conditions, the corresponding sub-models are trained separately to improve the adaptability of the model under various pollution levels. In practical applications, 1000 sets of data under different air quality conditions are first collected, each set containing 20 electrostatic feature parameters and corresponding PM2.5, PM10, ozone, and sulfur dioxide concentrations. The data are Z-score standardized. For example, the mean of the original PM2.5 data is 50μg / m 3 , with a standard deviation of 20 μg / m 3 , after standardization, it becomes a distribution with mean 0 and standard deviation 1. The recursive feature elimination method starts with 1 feature and gradually increases to 20, calculating the root mean square error of 5-fold cross validation each time. When it increases to 15 features, the performance improvement drops to 0.8%, which is lower than the 1% threshold, so 15 features are selected as the optimal combination. The support vector machine parameters are optimized by grid search method, trying linear kernel, quadratic polynomial kernel and RBF kernel, searching C value in [0.1, 1, 10, 100], and γ value in [0.1, 1, 10, 100].

[0036] The search was performed in [0.001, 0.01, 0.1, 1]. After 5-fold cross-validation, the optimal parameters for the RBF kernel were selected, C = 10, and γ = 0.01. Using these parameters and features to train the support vector machine model, the sequential minimum optimization algorithm reached a convergence threshold of 1e-3 after 732 iterations. The 10-fold cross-validation results showed a root mean square error of 3.2 μg / m² for PM2.5 prediction. 3 , coefficient of determination R 2 The root mean square error of PM10 prediction is 5.1 μg / m 3 , coefficient of determination R 2 is 0.89, the root mean square error of ozone prediction is 4.8ppb, R 2 is 0.87, the root mean square error of sulfur dioxide prediction is 3.5ppb, R 2 The sub-models were trained for three conditions: AQI less than 100, 100-200, and greater than 200. The prediction accuracy on their respective datasets was 5-8% higher than that of the entire model.

[0037] Step S105 : Input the sofa electrostatic signal strength collected in real time into the trained mapping relationship model between electrostatic features and air quality, obtain the change of electrostatic features, and evaluate the indoor air quality in real time.

[0038] An electrostatic signal sequence from the sofa surface, collected by an electrostatic sensor array, is acquired, the electrostatic signal sequence comprising a preset number of data points. Data preprocessing is performed on the electrostatic signal sequence, using a median filter algorithm to remove sudden noise, and signal denoising is performed using a wavelet transform. Electrostatic characteristic parameters are extracted from the denoised electrostatic signal, and time-domain, frequency-domain, and time-frequency domain features are calculated to obtain a multidimensional feature vector. If the multidimensional feature vector has not been normalized, the multidimensional feature vector is normalized so that all eigenvalues ​​are scaled to the interval [-1, 1]. The normalized multidimensional electrostatic feature vector is input into a pre-trained support vector machine model to predict the concentrations of PM2.5, PM10, ozone, and sulfur dioxide in the current indoor air. Based on the predicted pollutant concentrations, individual air quality indices are calculated, and the maximum value is taken as the comprehensive air quality index. The air quality level interval to which the comprehensive air quality index belongs is determined, and the current indoor air quality level is determined.

[0039] For example, a high-precision electrostatic sensor array was used to collect the electrostatic signal intensity from the sofa surface in real time. Based on the changing characteristics of the electrostatic signal, the sampling frequency was set to 100 Hz, and the acquisition time window was set to 10 seconds, resulting in a raw electrostatic signal sequence containing 1000 data points. A sliding window method was used, updating the data every 1 second to maintain real-time and continuous data. The raw electrostatic signal sequence was preprocessed, and a median filter algorithm was used to remove sudden noise. Through experimental comparison, a filter window size of 5 was determined. Signal denoising was then performed using a wavelet transform, using the db4 wavelet basis function. Based on the signal frequency characteristics, the number of decomposition layers was set to 3. A soft thresholding method was used to remove high-frequency noise, with the threshold set to 3 times the noise standard deviation. Electrostatic characteristic parameters were extracted from the preprocessed electrostatic signal, and time-domain features such as mean, variance, kurtosis, and skewness were calculated. The power spectral density was calculated using a fast Fourier transform, extracting frequency-domain features such as the dominant frequency (the frequency corresponding to the maximum power spectral density) and the band energy ratio (the ratio of the energy in a specific frequency band to the total energy). Time-frequency domain features such as wavelet energy entropy are calculated, which is the normalized entropy of the wavelet coefficient energy at each scale. This ultimately forms a 15-dimensional feature vector, which is then normalized so that all eigenvalues ​​are scaled to the interval [-1, 1]. This normalized 15-dimensional electrostatic feature vector is input into a pre-trained support vector machine model, which is used to predict the concentrations of PM2.5, PM10, ozone, and sulfur dioxide in the current indoor air. PM2.5 refers to particles with an aerodynamic diameter of 2.5 microns or less. PM10 refers to particles with an aerodynamic diameter of 10 microns or less. Based on the predicted pollutant concentrations, the individual air quality indices (IAQIs) are calculated according to the Ambient Air Quality Standard (GB3095-2012), and the maximum value is taken as the overall air quality index (AQI). Air quality is categorized by AQI (Air Quality Index) value: 0-50 (Excellent), 51-100 (Good), 101-150 (Lightly Polluted), 151-200 (Moderately Polluted), 201-300 (Heavily Polluted), and >300 (Severely Polluted). The assessment results are updated every minute, enabling real-time monitoring and assessment of indoor air quality. In practical applications, a high-precision electrostatic sensor array collects electrostatic signals from the sofa surface at a frequency of 100Hz, generating a signal sequence consisting of 1,000 data points every 10 seconds. A 1-second sliding window is used, with 100 new data points updated per second, to maintain real-time data. The raw signal is first median filtered with a window size of 5, effectively removing 95% of impulse noise. Subsequently, a three-layer decomposition using the DB4 wavelet filter is applied, with a soft threshold set to three times the noise standard deviation (approximately 0.05mV). This successfully filters out high-frequency noise and improves the signal-to-noise ratio by 8dB. A 15-dimensional feature vector is extracted from the processed signal, including time domain features including mean, which ranges from -0.5mV to 0.5mV, and variance, whose typical value is 0.01mV. 2The kurtosis is normally distributed with a value of approximately 3, and the skewness ranges from -0.5 to 0.5. Frequency domain features are calculated using a 1024-point FFT. The dominant frequency is typically between 20-50 Hz, with the 0-100 Hz band energy accounting for approximately 80%. Wavelet energy entropy is typically between 2.5 and 3.5. After normalization, the feature vectors are fed into a pre-trained support vector machine model. The model predicts PM2.5 with a root mean square error of 5 μg / m on the test set. 3 , for PM10 it is 8μg / m 3 , for ozone is 10ppb, for sulfur dioxide is 5ppb. AQI is calculated based on the predicted results, such as PM2.5 predicted value is 75μg / m 3 When the air quality level is 104, the corresponding IAQI is 104. The maximum IAQI value of all pollutants is used as the final AQI to determine the air quality level. The assessment results are updated every minute. In a typical 8-hour test, the air quality level accurately captured three changes: from "good" to "slightly polluted" and then back to "good", with a 90% consistency with the results of professional air quality monitoring equipment.

[0040] Step S106: If the evaluation result shows that the air quality is less than the air quality threshold, the air purification device of the smart sofa is triggered, the air purifier is turned on, and the ventilation volume of the fresh air system is increased to improve the indoor air environment.

[0041] Obtain the air quality index measured in real time by the air quality sensor, and determine whether it exceeds a preset air quality threshold based on the air quality index; if the air quality index exceeds the preset air quality threshold, send a start instruction to the air purification device through the microcontroller; use a fuzzy control algorithm to process the air quality index and indoor temperature and humidity data to obtain control instructions for the air purifier operating mode and the ventilation volume of the fresh air system; adjust the wind speed of the air purifier and the ventilation volume of the fresh air system according to the control instructions; use a PID control algorithm to calculate the deviation between the air quality index and the target value, and obtain an adjustment amount for the intensity of the purification measure; modify the wind speed of the air purifier and the ventilation volume of the fresh air system according to the adjustment amount; and use the following formula to calculate the adjusted air purifier wind speed:

[0042] V fan =V base +ΔV

[0043] Where V fan Indicates the wind speed of the air purifier, V base represents the base wind speed, and ΔV represents the wind speed adjustment. The modified wind speed and ventilation volume are sent to the air purification device, which performs corresponding purification measures based on the received wind speed and ventilation volume. This formula is used to calculate the adjusted air purifier wind speed.

[0044] For example, based on the real-time evaluation of the air quality index AQI, the reference ambient air quality standard

[0045] GB3095-2012 sets multiple air quality thresholds: 100 for excellent, 150 for light pollution, 200 for moderate pollution, and 300 for heavy pollution. When the AQI exceeds the corresponding threshold, different levels of air purification measures are triggered. Using the Arduino Mega2560 microcontroller built into the smart sofa, a mechanism is established to link air quality assessment results with the air purification device. The microcontroller communicates with the air quality sensor via the I2C interface to obtain real-time AQI data and controls the air purifier and fresh air system via the RS485 interface. When the AQI exceeds the set threshold, the microcontroller sends a start command, automatically adjusting the purifier's wind speed and the fresh air system's ventilation volume based on the pollution level. A fuzzy control algorithm is used to dynamically adjust the air purifier's operating mode and the fresh air system's ventilation volume based on the AQI value and indoor temperature and humidity data. The fuzzy control process consists of three steps: fuzzification, inference, and defuzzification. The AQI and temperature and humidity data are converted into fuzzy sets; inference is performed based on preset fuzzy rules; and the fuzzy outputs are converted into specific control instructions. For example, when the AQI is between 100-150, the air purifier runs at medium speed and the fresh air system works at 30% of the ventilation volume; when the AQI is greater than 200, the air purifier runs at full speed and the fresh air system works at 80% of the ventilation volume.

[0046] The intensity of purification measures is dynamically adjusted based on the deviation of the AQI from the target value. The duration and intensity of air purification measures are adjusted by real-time monitoring of AQI trends. When the AQI remains below the set threshold for 30 consecutive minutes, the PID controller calculates the corresponding control variable and gradually reduces the air purifier wind speed and the ventilation volume of the fresh air system until it returns to standby mode, achieving intelligent and energy-saving operation. At the same time, the microcontroller exchanges real-time data with the air purification device via the MQTT protocol to ensure timely execution of control commands and real-time updates of status feedback. In actual application, the smart sofa integrates an Arduino Mega2560-based control system and monitors air quality in real time using a SharpGP2Y1010AU0F dust sensor. Data is collected every 5 seconds and the AQI is calculated by taking the average of 20 consecutive times. When the AQI reaches 101, a light pollution level response is triggered: the air purifier starts and runs at a medium speed of 1200 rpm, and the fresh air system runs at 30% ventilation volume (approximately 150m3 / s). 3 If the AQI rises to 201, a moderate pollution response is triggered: the purifier speed is increased to 2000rpm, and the ventilation volume of the fresh air system is increased to 80% (about 400m 3The control algorithm uses fuzzy control with triangular membership function. The input variables are AQI (range 0-500) and indoor relative humidity (range 20%-80%), and the output variables are purifier speed (range 0-3000rpm) and fresh air ventilation volume (range 0-500m 3 / h). The fuzzy rule base contains 25 rules, such as "IF AQI is High AND Humidity is Medium THEN F an_Speed ​​is High AND Ventilation is High." Defuzzification uses the center of gravity method to determine the specific control variable. Simultaneously, the PID controller uses a target AQI value of 100 as the setpoint, with a proportional coefficient Kp = 0.5, an integral time Ti = 300s, and a derivative time Td = 60s, adjusting the control output every 60 seconds. Communication with the air purification device is via the MQTT protocol, with publish / subscribe topics including "air_quality / aqi," "air_purifier / speed," and "ventilation / flow_rate," with a message refresh rate of 1Hz. In a typical operation, when the AQI was detected to rise from 80 to 130, purification measures were initiated within 5 seconds. After 15 minutes, the AQI dropped to 95, where it remained stable for 30 minutes. The purifier and fresh air system gradually adjusted to a low-speed state, achieving precise air quality control and optimizing energy efficiency.

[0047] The description of the above embodiments is only used to help understand the technical solutions and core ideas of this application; ordinary technicians in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A data collection and analysis method for a smart sofa, characterized in that: The method comprises: By setting up an electrostatic sensor array on the smart sofa, the static signal intensity and polarity distribution, human body charge, and environmental humidity data of different areas on the sofa surface are collected in real time to obtain static distribution data; Based on the static electricity distribution data, a static electricity accumulation model was established according to different sofa materials and shapes. Static electricity measurement equipment was used to conduct accumulation experiments under different conditions to obtain static electricity distribution measurement data, and the static electricity measurement data was normalized. Based on the normalized electrostatic measurement data, wavelet transform and frequency domain analysis were used for signal processing to extract electrostatic characteristic parameters that reflect the data change trend and obtain air quality indicators. Correlation analysis was used to obtain the correlation strength between different electrostatic characteristic parameters and air quality indicators, and electrostatic characteristic parameters associated with air quality were screened out. Under different air quality conditions, including pollutant concentration and particulate matter content, the mapping relationship model between electrostatic characteristic parameters and air quality is trained using the support vector machine algorithm based on the electrostatic characteristic parameters; The real-time collected sofa electrostatic signal strength is input into the trained mapping relationship model between electrostatic features and air quality to obtain the changes in electrostatic features and evaluate the indoor air quality in real time. If the evaluation result shows that the air quality is lower than the air quality threshold, the air purification device of the smart sofa will be triggered to turn on the air purifier and increase the ventilation volume of the fresh air system to improve the indoor air environment.

2. The method according to claim 1, characterized in that The electrostatic sensor array is set on the smart sofa to collect the electrostatic signal intensity and polarity distribution, human body charge, and environmental humidity data of different areas on the sofa surface in real time to obtain electrostatic distribution data, including: Setting up an electrostatic sensor array on the sofa surface, wherein the electrostatic sensor array is arranged in a grid pattern, and an electrostatic sensor is placed at each grid point to obtain electrostatic signal distribution data; Using wavelet transform to filter and reduce noise on the electrostatic signal distribution data to obtain filtered electrostatic signal data; Calculating the electric field intensity distribution on the sofa surface based on the filtered electrostatic signal data, identifying the electrostatic accumulation in the human body contact area by analyzing the charge density, and obtaining electrostatic accumulation area data; The electrostatic accumulation area data is classified using a K-means clustering algorithm to identify different types of electrostatic interference sources and obtain an electrostatic interference source classification result; The electrostatic safety status is evaluated according to the electrostatic interference source classification result.

3. The method according to claim 1, characterized in that Based on the static electricity distribution data, a static electricity accumulation model is established according to different sofa materials and shapes, and static electricity measurement equipment is used to conduct accumulation experiments under different conditions to obtain static electricity distribution measurement data, and the static electricity measurement data is normalized, including: Clustering algorithm is used to classify sofa materials, and leather, fabric and suede material categories are obtained; Determine the corresponding resistivity range according to the material category and obtain material characteristic parameters; Combining the material characteristic parameters with the three-dimensional shape data of the sofa to construct a static electricity accumulation model; Designing an experimental plan according to the electrostatic accumulation model, and using electrostatic measurement equipment to conduct electrostatic accumulation experiments under different conditions specified in the experimental plan; Performing data cleaning on the electrostatic measurement data obtained from the electrostatic accumulation experiment, and using a cubic spline interpolation method to fill in missing data in the electrostatic measurement data; The static measurement data is normalized to a range of 0-1 by a maximum-minimum value normalization method to obtain normalized static distribution data; Establishing a static electricity accumulation prediction model based on the normalized static electricity distribution data; It also includes: extracting the detailed features of the folds and seams on the sofa surface based on the geometric shape data of the sofa, judging the fold and seam area, determining the electrostatic accumulation risk coefficient of the area, and establishing a static electricity accumulation model by combining the materials and electrostatic distribution data of different sofas.

4. The method according to claim 3, characterized in that The method extracts the detailed features of the folds and seams on the sofa surface based on the geometric shape data of the sofa, determines the fold and seam area, determines the electrostatic accumulation risk coefficient of the area, and establishes an electrostatic accumulation model by combining the material and electrostatic distribution data of different sofas, including: Based on the 3D scanning data of the sofa, the discrete Gaussian curvature calculation method is used to calculate the curvature distribution of the sofa surface and obtain the surface wrinkle area; Extracting seam line features from the surface wrinkle area to determine the precise location and range of the wrinkle seam area; Measuring the seam depth and width of the pleated seam region using a structured light three-dimensional scanning method, and establishing a geometric and electrical characteristic model of the pleated seam region; Performing electrostatic field simulation to obtain the electric field intensity distribution in the wrinkle seam area; If the electric field intensity distribution exceeds a preset threshold, it is determined that there is a risk of static electricity accumulation in the wrinkle seam area; Extract the electrostatic characteristic parameters of the sofa material from the pre-established material database, including dielectric constant, surface resistivity and charge decay time constant; Combining the charge density and electric field strength information in the electrostatic distribution data, a basic model of electrostatic accumulation combined with material properties is constructed; A static electricity accumulation prediction model was constructed using a multi-layer perceptron neural network. The input layer of the neural network contained material parameters, geometric features, and environmental factors, and the output layer represented the amount of static electricity accumulation in different areas. The model parameters of the neural network are optimized by a back propagation algorithm to obtain a final static electricity accumulation model.

5. The method according to claim 1, wherein The normalized electrostatic measurement data is processed using wavelet transform and frequency domain analysis to extract electrostatic characteristic parameters that reflect the data change trend, obtain air quality indicators, and use correlation analysis to obtain the correlation strength between different electrostatic characteristic parameters and air quality indicators, thereby screening out electrostatic characteristic parameters associated with air quality, including: The normalized electrostatic measurement data is subjected to wavelet transform and denoised using the soft threshold method. Perform fast Fourier transform on the denoised electrostatic data to obtain frequency domain representation, calculate the power spectrum density, and extract frequency domain characteristic parameters from it, including main frequency, frequency band energy ratio and harmonic distortion; For the frequency domain characteristic parameters, combined with the time domain characteristics, an electrostatic characteristic parameter set is formed to establish an association between the electrostatic characteristics and the air quality; Acquire the synchronously collected air quality data, perform data cleaning and preprocessing on the air quality data, remove outliers using the moving median method, fill in missing values ​​using the linear interpolation method, and obtain a normalized air quality index data set through z-score standardization; The Pearson correlation coefficient is used to calculate the correlation between the electrostatic characteristic parameters and the normalized air quality index. If the correlation coefficient is greater than the preset threshold, the subset of electrostatic characteristic parameters that are strongly correlated with the air quality index is screened out. The principal component analysis method is used for dimensionality reduction, and the first preset principal components whose cumulative contribution rate reaches the preset value are selected. The electrostatic characteristic parameters for air quality assessment are obtained through linear combination.

6. The method according to claim 1, characterized in that The method of training a mapping relationship model between electrostatic characteristic parameters and air quality using a support vector machine algorithm under different air quality conditions, including pollutant concentration and particulate matter content, is as follows: Obtain electrostatic characteristic parameters and corresponding pollutant concentration and particulate matter content data under different air quality conditions to construct a training dataset; Performing Z-score normalization on the training data set, screening the electrostatic feature parameters after normalization using a recursive feature elimination method, and determining the optimal feature combination; According to the optimal feature combination, the kernel function type, regularization parameter C and kernel function parameter γ of the support vector machine are optimized using a grid search method to obtain the optimal parameter combination; Using the optimal feature combination and the optimal parameter combination, a support vector machine algorithm is used to train a mapping relationship model between electrostatic feature parameters and air quality; For different air quality conditions, corresponding sub-models are trained respectively, and the sub-models are trained based on the mapping relationship model to improve the adaptability of the sub-models under various pollution levels.

7. The method according to claim 1, characterized in that The real-time collected sofa electrostatic signal strength is input into a trained mapping relationship model between electrostatic features and air quality to obtain changes in electrostatic features and evaluate indoor air quality in real time, including: Acquire an electrostatic signal sequence from the sofa surface collected by an electrostatic sensor array, wherein the electrostatic signal sequence includes a preset number of data points; Performing data preprocessing on the electrostatic signal sequence, removing sudden noise using a median filter algorithm, and performing signal denoising through wavelet transform; Extracting electrostatic characteristic parameters from the electrostatic signal after signal denoising, calculating time domain features and frequency domain features, and obtaining a multi-dimensional feature vector; If the multidimensional feature vector has not been normalized, normalizing the multidimensional feature vector so that all eigenvalues ​​are scaled to the interval [-1, 1]; The standardized multidimensional electrostatic feature vector is input into a pre-trained support vector machine model to predict the concentrations of PM2.5, PM10, ozone, and sulfur dioxide in the current indoor air. Calculate the individual air quality indexes based on the predicted pollutant concentrations, take the maximum value as the comprehensive air quality index, determine the air quality grade interval to which the comprehensive air quality index belongs, and determine the current indoor air quality grade.

8. The method according to claim 1, characterized in that If the evaluation result shows that the air quality is less than the air quality threshold, the air purification device of the smart sofa is triggered to turn on the air purifier and increase the ventilation volume of the fresh air system to improve the indoor air environment, including: Obtaining an air quality index measured in real time by an air quality sensor, and determining whether the air quality exceeds a preset air quality threshold based on the air quality index; If the air quality index exceeds a preset air quality threshold, a start instruction is sent to the air purification device via the microcontroller; Using a fuzzy control algorithm to process the air quality index and indoor temperature and humidity data, and obtain control instructions for the air purifier working mode and the ventilation volume of the fresh air system; adjusting the wind speed of the air purifier and the ventilation volume of the fresh air system according to the control instruction; Calculating the deviation between the air quality index and the target value using a PID control algorithm to obtain an adjustment amount for the intensity of the purification measure; Modify the wind speed of the air purifier and the ventilation volume of the fresh air system according to the adjustment amount; The following formula is used to calculate the adjusted air purifier wind speed: V fan =V base +△V Where V fan Indicates the wind speed of the air purifier, V base Indicates the basic wind speed, ΔV indicates the adjustment of wind speed; Sending the modified wind speed and ventilation volume to the air purification device, and the air purification device performs corresponding purification measures according to the received wind speed and ventilation volume; This formula is used to calculate the adjusted air purifier wind speed.

Images