Formaldehyde removal method utilizing turbulence model and model training

Abstract

The invention provides a formaldehyde removal method utilizing a turbulence model and model training. The formaldehyde removal method comprises the following steps: acquiring a three-dimensional data model and a formaldehyde distribution data set of a to-be-detected house; establishing a turbulence model of the to-be-detected house based on the three-dimensional data model and the formaldehyde distribution data set; simulating the formaldehyde emission state of the to-be-detected house under different ventilation conditions based on the turbulence model and the formaldehyde distribution data set, and predicting to obtain at least one ventilation position and at least one ventilation direction with the fastest formaldehyde emission speed; and ventilation is carried out at each ventilation position in the corresponding ventilation direction. In the embodiment of the invention, the turbulence model of the to-be-detected house can be established based on the three-dimensional data model and the formaldehyde distribution data set to predict the ventilation position and the ventilation direction in the to-be-detected house at the highest formaldehyde emission speed, so that the to-be-detected house can be ventilated in the ventilation direction corresponding to each ventilation position; and the formaldehyde removal time required by natural ventilation is greatly shortened.

Description

Technical Field

[0001] The present application relates to the technical field of indoor formaldehyde removal, and in particular to a formaldehyde removal method using a turbulence model and model training. Background Art

[0002] Internationally, 12 indicators (CO, CO2, NO x , SO2, formaldehyde, inhalable particulate matter, total indoor bacteria count, temperature, relative humidity, wind speed, illumination and noise) to quantitatively reflect the indoor environmental quality. Among them, formaldehyde and various VOCs are the main causes of indoor air pollution problems. According to the data from the China Indoor Environment Monitoring Center and the Health Medical Center, formaldehyde, benzene, ammonia and radioactive pollution are the key factors causing indoor environmental pollution, with formaldehyde pollution intensity being the first. According to the Indoor Air Quality Standard (GB / T 18883-2022), the average one-hour indoor formaldehyde concentration should not be higher than 0.08mg / m 3 Studies have shown that residential formsaldehyde concentrations below national standards can also produce certain non-carcinogenic effects and carcinogenic risks to the human body.

[0003] Long-term, continuous ventilation is a simple and effective formaldehyde removal method, and is widely used for indoor air purification in newly renovated homes. However, this method is limited by the layout of the house and wall barriers, resulting in a long formaldehyde removal cycle, difficulty removing formaldehyde in ventilation dead zones, and poor results in low-temperature environments. Therefore, after renovating a house, it is often left to air dry for a long time, resulting in a long formaldehyde removal cycle and poor results. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention discloses a formaldehyde removal method using a turbulence model and model training, which can solve the technical problems in the prior art that after people decorate their houses, a long airing time is often required, the formaldehyde removal cycle is long and the effect is poor.

[0005] To achieve the above objectives, the present application provides a formaldehyde removal method using a turbulence model and model training, the formaldehyde removal method using a turbulence model and model training comprising the following steps:

[0006] Obtain a three-dimensional data model and formaldehyde distribution dataset of the house to be inspected;

[0007] Establishing a turbulence model of the house to be inspected based on the three-dimensional data model;

[0008] Simulating the formaldehyde emission state of the house to be inspected under different ventilation conditions based on the turbulence model and the formaldehyde distribution dataset, and predicting at least one ventilation position in the house to be inspected where the formaldehyde emission rate is fastest and at least one ventilation direction corresponding to the at least one ventilation position;

[0009] ventilate the house to be detected in a ventilation direction corresponding to each ventilation position.

[0010] In a possible embodiment, a three-dimensional data model and a formaldehyde distribution dataset of the house to be detected are acquired, including:

[0011] Size information of the house to be detected is acquired, and a space in the house to be detected is meshed based on the size information, to establish the three-dimensional data model;

[0012] Formaldehyde concentrations at different positions and different heights in the house are monitored, and the formaldehyde distribution dataset in the house to be detected is established based on the monitoring results of the formaldehyde concentrations.

[0013] In a possible embodiment, the size information of the house to be detected is acquired, and the space in the house to be detected is meshed based on the size information, to establish the three-dimensional data model, including:

[0014] A house type drawing or a plan of the house to be detected is acquired;

[0015] Based on the boundary condition setting and the related parameter setting based on the house type drawing or the plan, a triangular face meshing or a non-structural hybrid mode body meshing is performed on a room or a structure in the house to be detected; the number of the meshing is greater than or equal to one million.

[0016] In a possible embodiment, the turbulent flow model of the house to be detected is established based on the three-dimensional data model and the formaldehyde distribution dataset, including:

[0017] Simulation parameters of the three-dimensional data model and a first preset formula group are acquired;

[0018] Based on the simulation parameters and the first preset formula group, a cross-section cloud simulation is performed on the three-dimensional data model, to obtain the turbulent flow model of the house to be detected.

[0019] In a possible embodiment, the first preset formula group includes:

[0020]

[0021] wherein, u, v, w are velocity components of a micro-group control body (with a size of dx, dy, dz) in x, y, z directions under a Cartesian coordinate system; p is fluid density; m is kinematic viscosity coefficient; V is three direction components of velocity; p c is formaldehyde mass concentration; G is formaldehyde diffusion coefficient; S cwherein S represents the production rate of formaldehyde inside the indoor system; k represents the turbulent fluctuation kinetic energy per unit mass flow; ε represents the dissipation rate of fluctuation kinetic energy; C1=1.44, C2=1.92, σ ε =1.22, the time-averaged equations (1), (2), (3), the k equation (5), and the ε equation (6) constitute the basic control equations of the standard k-ε model, and the algebraic expressions of μt and ε make the equations closed.

[0022] In a possible embodiment, the formaldehyde emission state of the to-be-detected house under different ventilation conditions is simulated based on the turbulent flow model and the formaldehyde distribution dataset, and at least one ventilation position with the fastest formaldehyde emission speed in the to-be-detected house and at least one ventilation direction corresponding to the at least one ventilation position are predicted, including:

[0023] Air flow data field in the to-be-detected house is obtained based on the turbulent flow model;

[0024] A formaldehyde emission model in the to-be-detected house is obtained based on the air flow data field and the formaldehyde distribution dataset;

[0025] The formaldehyde emission concentration under different ventilation conditions is simulated based on the formaldehyde emission model, and at least one ventilation position with the fastest formaldehyde emission speed in the to-be-detected house and at least one ventilation direction corresponding to the at least one ventilation position are predicted.

[0026] In a possible embodiment, the ventilation of the to-be-detected house at each ventilation position in a ventilation direction corresponding to the each ventilation position includes:

[0027] A ventilation device is arranged at the each ventilation position, and the to-be-detected house is ventilated through the ventilation device;

[0028] Based on the turbulent flow model and the formaldehyde distribution dataset, a formaldehyde over-standard risk point in the to-be-detected house is determined, and a temperature rising device is arranged at the formaldehyde over-standard risk point.

[0029] In a possible embodiment, the ventilation device includes an air circulation fan with adjustable height and intermittent operation.

[0030] The temperature rising device includes a heater with adjustable temperature.

[0031] In a possible embodiment, after the ventilation of the to-be-detected house at each ventilation position in a ventilation direction corresponding to the each ventilation position, the method further includes:

[0032] perform first formaldehyde detection on the to-be-detected house; if the average formaldehyde concentration in the to-be-detected house is greater than or equal to a first preset concentration, or the formaldehyde concentration of a single detection point in the to-be-detected house is greater than or equal to a second preset concentration, the formaldehyde in the to-be-detected house fails to pass the acceptance test, and formaldehyde plugging is performed in a formaldehyde over-limit area or adsorption is performed by using an adsorbent;

[0033] If the formaldehyde in the to-be-detected house fails to pass the acceptance test, after a first preset time interval, perform second formaldehyde detection on the to-be-detected house; if the formaldehyde concentration of a single detection point in the to-be-detected house is greater than or equal to a third preset concentration, repeatedly perform: ventilate the to-be-detected house at each ventilation position in a ventilation direction corresponding to the ventilation position.

[0034] In a possible embodiment, the first preset concentration is 0.08 mg / m 3 ; the second preset concentration is 0.04 mg / m 3 ; the third preset concentration is 0.08 mg / m 3 ; and the first preset time interval is 24 hours.

[0035] The technical scheme provided by the embodiments of the present application has the following technical effects:

[0036] First, in the embodiments of the present application, the ventilation position with the fastest formaldehyde emission speed and the ventilation direction in the to-be-detected house can be predicted by establishing a turbulent flow model of the to-be-detected house based on a three-dimensional data model and a formaldehyde distribution data set, so that the to-be-detected house can be ventilated at each ventilation position in a ventilation direction corresponding to the ventilation position, the formaldehyde release rate is accelerated, the residual amount of formaldehyde in the room is significantly reduced, the potential risk caused by the continuous release of formaldehyde after the formaldehyde removal treatment is effectively reduced, and the formaldehyde removal time required by natural ventilation is greatly shortened.

[0037] Second, natural ventilation of a room generally takes several months to one year after people finish decorating the room, and the formaldehyde removal period of the embodiments of the present application is 2 to 3 days, which greatly shortens the formaldehyde removal time required by natural ventilation.

[0038] Third, the present application does not involve formaldehyde removal substances commonly used in the prior art, including strong oxidizing agents and photocatalysts, which will not cause health damage to on-site construction personnel and will not cause corrosion to indoor furniture. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0040] Figure 1 is a flowchart of a formaldehyde removal method using a turbulent flow model and model training provided by an embodiment of the present application Figure 1 ;

[0041] Figure 2 is a flowchart of a formaldehyde removal method using a turbulent flow model and model training provided by an embodiment of the present application Figure 2 ;

[0042] Figure 3 is a flowchart of a formaldehyde removal method using a turbulent flow model and model training provided by an embodiment of the present application Figure 3 ;

[0043] Figure 4 is a flowchart of a formaldehyde removal method using a turbulent flow model and model training provided by an embodiment of the present application Figure 4 ;

[0044] Figure 5 is a flowchart of a formaldehyde removal method using a turbulent flow model and model training provided by an embodiment of the present application Figure 5 ;

[0045] Figure 6 is a flowchart of a formaldehyde removal method using a turbulent flow model and model training provided by an embodiment of the present application Figure 6 ;

[0046] Figure 7 is a simplified schematic diagram of a three-dimensional data model in a formaldehyde removal method using a turbulent flow model and model training provided by an embodiment of the present application;

[0047] Figure 8 is a grid division model of a three-dimensional data model in a formaldehyde removal method using a turbulent flow model and model training provided by an embodiment of the present application;

[0048] Figure 9 is a schematic diagram of an indoor air flow velocity field of a whole house turbulent flow model under natural ventilation conditions in a formaldehyde removal method using a turbulent flow model and model training provided by an embodiment of the present application;

[0049] Figure 10A schematic diagram of the indoor air flow velocity field of the whole house under the condition of the turbulent flow model and the model training formaldehyde removal method provided in an embodiment of the present application in the condition of enhanced ventilation;

[0050] Figure 11 A schematic diagram of the formaldehyde concentration contour and the optimal flow enhancement ventilation coordinate and flow direction of the whole house under the condition of the turbulent flow model and the model training formaldehyde removal method provided in an embodiment of the present application in the condition of natural ventilation (z=0.5m);

[0051] Figure 12 A schematic diagram of the formaldehyde concentration contour of the whole house under the condition of the turbulent flow model and the model training formaldehyde removal method provided in an embodiment of the present application after the end of enhanced ventilation (z=0.5m);

[0052] Figure 13 A schematic diagram of the formaldehyde concentration contour of the whole house under the condition of the turbulent flow model and the model training formaldehyde removal method provided in an embodiment of the present application after 24h of the end of enhanced ventilation (z=0.5m);

[0053] Figure 14 A schematic diagram of the formaldehyde concentration contour of the whole house under the condition of the turbulent flow model and the model training formaldehyde removal method provided in an embodiment of the present application in the condition of natural ventilation (z=1.6m);

[0054] Figure 15 A schematic diagram of the formaldehyde concentration contour of the whole house under the condition of the turbulent flow model and the model training formaldehyde removal method provided in an embodiment of the present application after the end of enhanced ventilation (z=1.6m);

[0055] Figure 16 A schematic diagram of the formaldehyde concentration contour of the whole house under the condition of the turbulent flow model and the model training formaldehyde removal method provided in an embodiment of the present application after 24h of the end of enhanced ventilation (z=1.6m). DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0057] It should be noted that the "one embodiment" or "an embodiment" described in the specification of the present application means that a specific feature, structure or characteristic described in the specification can be included in at least one implementation of the present application. It should be understood that in the specification and claims of the embodiments of the present application and the above-mentioned drawings, the terms "upper", "lower", "top", "bottom" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the indicated device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. The terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can be explicitly or implicitly included one or more of the features. In addition, the terms "first", "second" and the like are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0058] As shown in Figures 1 to 16 The present application provides a formaldehyde removal method using a turbulent flow model and model training, which can be used to remove formaldehyde in a house to be detected, and includes the following steps:

[0059] S1: obtaining a three-dimensional data model and a formaldehyde distribution data set of the house to be detected.

[0060] In one possible embodiment, the three-dimensional data model and the formaldehyde distribution data set of the house to be detected can be obtained. The three-dimensional data model of the house to be detected can include a house type diagram or a plan distribution diagram, and the size of the calculation domain can be determined based on the three-dimensional data model.

[0061] Optionally, in order to make the subsequent operation more efficient, the three-dimensional data model of the house to be detected can be processed, specifically, the convex window and the open balcony on the house type can be simplified, and only the effective ventilation area is considered at each door and window part.

[0062] Optionally, the formaldehyde concentration in the house to be detected can be measured, and the formaldehyde distribution data set can be established based on the formaldehyde concentration in the house to be detected. The formaldehyde concentration in different regions and different heights in the house to be detected can be measured at fixed points, and the formaldehyde distribution data set can be established based on the measurement results of the fixed points.

[0063] S2: establishing a turbulent flow model of the house to be detected based on the three-dimensional data model.

[0064] Optionally, the residential network model can be simulated with parameter settings and cross-section cloud simulation, thereby establishing a whole-house turbulence model. Specifically, the turbulence model of the house to be detected can be established based on the three-dimensional data model and the formaldehyde distribution dataset. Specifically, the three-dimensional data model of the house to be detected can be simulated with parameter settings by using a computational fluid dynamics (CFD) software such as Tecplot360, and a standard k-ε model and a component transport model are established by using Fluent software to complete parameter solving.

[0065] S3: Simulate the formaldehyde emission state of the house to be detected under different ventilation conditions based on the turbulence model and the formaldehyde distribution dataset, and predict at least one ventilation position with the fastest formaldehyde emission speed in the house to be detected and at least one ventilation direction corresponding to the at least one ventilation position.

[0066] Optionally, the formaldehyde emission state of the house to be detected under different ventilation conditions can be simulated based on the turbulence model and the formaldehyde distribution dataset, the optimal flow velocity field in the house to be detected is predicted, and at least one ventilation position with the fastest formaldehyde emission speed in the house to be detected and at least one ventilation direction corresponding to the at least one ventilation position are predicted.

[0067] S4: Ventilate the house to be detected at each ventilation position with the ventilation direction corresponding to each ventilation position.

[0068] Optionally, the house to be detected can be ventilated at each ventilation position with the ventilation direction corresponding to each ventilation position based on the simulation result of the formaldehyde emission state of the house to be detected in S3. A ventilation device can be arranged at each ventilation position, so that the house to be detected can be ventilated along the ventilation direction based on the ventilation device.

[0069] In the embodiments of the present application, the ventilation position with the fastest formaldehyde emission speed and the ventilation direction in the house to be detected can be predicted by establishing a turbulence model of the house to be detected based on the three-dimensional data model and the formaldehyde distribution dataset, so that the house to be detected can be ventilated at each ventilation position with the ventilation direction corresponding to each ventilation position, thereby greatly shortening the time required for formaldehyde removal by natural ventilation.

[0070] In one possible embodiment, performing S1: obtaining the three-dimensional data model and the formaldehyde distribution dataset of the house to be detected can specifically include the following steps:

[0071] S101: Obtain size information of the house to be detected, and perform grid division on the space in the house to be detected based on the size information to establish a three-dimensional data model.

[0072] Optionally, the size information of the house to be detected is acquired to determine the calculation domain size of the house to be detected, and the gradual grid division is performed based on the building body and the calculation domain of the house to be detected, the boundary condition of the house is determined, and the grid model of the house is established.

[0073] S102: The formaldehyde concentration at different positions and different heights in the house is monitored, and the formaldehyde distribution dataset in the house to be detected is established based on the monitoring result of the formaldehyde concentration.

[0074] Optionally, during the formaldehyde concentration monitoring, all movable doors, windows, cabinet doors, drawers, cover plates and the like in the whole house are kept open, the number of formaldehyde monitoring points is determined according to the area of each compartment of the house, at least one monitoring point is set per 10 square meters, each compartment should include at least one center point, and the formaldehyde concentration of three z-axis height surfaces of 0.5m, 1.1m and 1.6m is detected at each point. The detection method adopts portable instrument in-situ detection or national standard method sampling detection.

[0075] In this embodiment, a three-dimensional data model can be established by grid division of the size information of the house to be detected, and a formaldehyde distribution dataset in the house to be detected can be established by monitoring the formaldehyde concentration at different positions and different heights in the house, so that a turbulent flow model of the house to be detected can be established based on the three-dimensional data model and the formaldehyde distribution data subsequently.

[0076] In one possible embodiment, when S101: the size information of the house to be detected is acquired, and the space in the house to be detected is grid divided based on the size information to establish a three-dimensional data model, the following steps can be specifically included:

[0077] S103: Obtain the house type drawing or plan drawing of the house to be detected.

[0078] Optionally, the house type drawing or plan drawing of the house to be detected can be acquired. The house type drawing and the plan drawing can include the shape and size information of each room in the house to be detected, and can also include the door and window information and furniture information of each room. The house type drawing or plan drawing can avoid the measurement error of manual measurement, and the furniture information in the house type drawing or plan drawing can be used to identify the formaldehyde release source or air flow obstacle, thereby improving the authenticity of the simulation result.

[0079] S104: Boundary condition setting and related parameter setting are performed based on the house type drawing or plan drawing, and triangular face grid division or non-structural hybrid mode body grid division is performed on the rooms or structures in the house to be detected; the number of grids after grid division is greater than or equal to one million.

[0080] Optionally, CAD software is used to model the building body and the calculation domain, Hypermesh, ANSA or Gambit software reads the model and performs meshing and boundary condition setting, Fluent software reads the mesh file and performs related parameter setting, triangular (Tri) surface meshing is performed on the ground (main, secondary bedroom, living room, dining room), doors and windows on the outer wall, other surfaces (including furniture, bathroom and kitchen floor, wall surface and ceiling surface of each room), and the remaining space is meshed by non-structured hybrid mode (Tet / Hybrid) body meshing, and the number of model meshes is greater than or equal to one million.

[0081] Specifically, in order to make the meshing more efficient, the bay window and open balcony on the house type drawing or plan can be simplified, and only the effective ventilation area of each door and window is considered. The building body and the calculation domain can be gradually meshed, the boundary conditions are determined, and the Figure 3 The grid model of the residence shown in the drawing, considering the actual house size, the grid independent solution is obtained after several trial calculations, specifically: the triangular (Tri) surface meshing of 0.05m is performed on the wooden floor of each room in the house to be detected, the doors and windows on the outer wall, and the triangular (Tri) surface meshing of 0.10m is performed on other surfaces (including furniture, bathroom and kitchen floor, wall surface and ceiling surface of each room), and then non-structured hybrid mode (Tet / Hybrid) body meshing is performed, and the number of model meshes is about 2 million.

[0082] In this embodiment, when performing the operations of S103 and S104, structured data input and intelligent mesh processing can be used to provide a high-precision and high-efficiency calculation basis for subsequent formaldehyde diffusion simulation, thereby supporting the core technology of rapid formaldehyde removal.

[0083] In one possible embodiment, when performing S2: establishing a turbulent flow model of the house to be detected based on the three-dimensional data model and the formaldehyde distribution data set, the following steps can be specifically performed:

[0084] S201: Obtain simulation parameters of the three-dimensional data model and a first preset formula group.

[0085] Optionally, the simulation parameters of the residence grid model can be set by using computational fluid dynamics (CFD) software such as Tecplot360, and then the standard k-ε model and the component transport model can be established by using Fluent software to complete parameter solving. The solver parameter settings, operating environment parameter settings, formaldehyde material attribute parameter settings, and air material attribute parameter settings in Fluent are shown in Tables 1, 2, 3, and 4, respectively.

[0086] Table 1 Solver parameter settings

[0087]

[0088]

[0089] Table 2 operating environment parameter settings

[0090]

[0091] Table 3 formaldehyde material attribute parameter settings

[0092]

[0093] Table 4 air material attribute parameter settings

[0094] Thermal properties Parameter setting Specific heat at constant pressure (Cp) 1006.43 J / (kg K) Density (D) 1.225 kg / m 3 ]] Kinematic viscosity (Viscosity) 1.7894e-05 kg / (m s)

[0095] S202: Based on the simulation parameters and the first preset formula group, a section cloud simulation is performed on the three-dimensional data model to obtain a turbulence model of the house to be detected.

[0096] Optionally, based on the simulation parameters and the first preset formula group, the three-dimensional data model can be subjected to a section cloud simulation as shown in Figure 9 and Figure 10 , so as to obtain the turbulence model of the house to be detected, so that the indoor air flow velocity field of different regions in the house to be detected can be calculated through the turbulence model in the subsequent process, and the prediction of the ventilation position and the ventilation direction can be realized in the subsequent process.

[0097] In one possible embodiment, the first preset formula group includes:

[0098]

[0099] wherein u, v, and w are velocity components of a micro-group control body (with a size of dx, dy, and dz) in the x, y, and z directions under a Cartesian coordinate system; p is a fluid density; m is a kinematic viscosity coefficient; V is a three-direction component of a velocity; pc is a formaldehyde mass concentration; G is a formaldehyde diffusion coefficient; S c is a production rate of indoor formaldehyde; k represents a turbulent fluctuation kinetic energy per unit mass flow; e represents a fluctuation kinetic energy dissipation rate; C1=1.44, C2=1.92, s ε =1.22, the time-averaged equations (1), (2), and (3) and the k equation (5) and the e equation (6) constitute basic control equations of a standard k-e model, and the algebraic expressions of m and e make the equations closed.

[0100] In a possible embodiment, when the step S3 of simulating the formaldehyde emission state of the house to be detected under different ventilation conditions based on the turbulence model and the formaldehyde distribution dataset is performed, and the at least one ventilation position with the fastest formaldehyde emission speed in the house to be detected and the at least one ventilation direction corresponding to the at least one ventilation position are predicted, the step can specifically include the following steps:

[0101] The step S301 of obtaining the air flow data field in the house to be detected based on the turbulence model is performed.

[0102] Optionally, the indoor air flow velocity field data of different regions in the house to be detected can be calculated based on the turbulence model.

[0103] The step S302 of performing model training based on the air flow data field and the formaldehyde distribution dataset to obtain the formaldehyde emission model in the house to be detected is performed.

[0104] Optionally, the TensorFlow, PyTorch, MATLAB, or other machine learning framework can be used to program the neural network model, the air flow velocity field data is used as the input of the model training, and the average formaldehyde concentration of the whole house is used as the output of the model training to perform the model training, and finally the formaldehyde emission model in the house to be detected is obtained. The formaldehyde emission intensity under different flow velocity field conditions is simulated to predict the formaldehyde emission model in the house to be detected.

[0105] The neural network model can be trained based on the air flow data field and the formaldehyde distribution dataset. Specifically, the TensorFlow, PyTorch, MATLAB, or other machine learning framework can be used to program the RBF neural network model, the indoor air flow velocity field data of different regions calculated by the turbulence model is used as the input of the RBF neural network model, the average formaldehyde concentration of the whole house is used as the output of the RBF neural network model, the dataset is divided into three subsets of training, verification, and prediction according to the ratio of 8:1:1, the input and output parameter matrices are defined, the radial basis function center, width, and the weight from the hidden layer to the output layer are initialized.

[0106] Optionally, the activation function of the RBF neural network is represented as:

[0107]

[0108] The output of the RBF neural network is represented as:

[0109]

[0110] For the expected output value d of the sample, the variance of the basis function is represented as:

[0111]

[0112] where ||x p -c i || is the Euclidean norm; c i is the center of the Gaussian function; and σ is the variance of the Gaussian function. is the p-th input sample; p = 1, 2, …, P, P is the total number of training samples; c i is the center of the network hidden layer node; w ij is the connection weight between the hidden layer and the output layer; i = 1, 2, …, h, h is the number of hidden layer nodes; y j is the actual output of the j-th output node of the network corresponding to the input sample.

[0113] Optionally, the RBF neural network is trained, the iteration termination accuracy is defined, the value of the root mean square error of the output is calculated, it is determined whether the loss is within the set accuracy range, if yes, the training is stopped, and if no, the next operation is performed. The training algorithm is based on the K-means clustering method to obtain the basis function center c, and then the variance σ i and the weight w between the hidden layer and the output layer are solved, the gradient descent method is used for iterative calculation, the weight, the center and the width are adaptively adjusted by using the learning process, and the parameter assignment update process is represented as:

[0114]

[0115] where w ij (t) is the adjusted weight between the i-th input neuron and the j-th hidden layer node in the t-th iteration calculation; c ij (t) is the center component of the j-th hidden layer node for the i-th input neuron in the t-th iteration calculation; d ij (t) is the width corresponding to the center c ij (t); η is the learning rate; α is the set iteration coefficient; and E is the loss function, which is the mean square error here.

[0116] S303: Based on the formaldehyde emission model, the formaldehyde emission concentration under different ventilation conditions is simulated, and at least one ventilation position with the fastest formaldehyde emission speed in the house to be detected and at least one ventilation direction corresponding to the at least one ventilation position are predicted.

[0117] Optionally, the formaldehyde emission concentration under different ventilation conditions can be simulated based on the formaldehyde emission model, and the air flow velocity field when the formaldehyde emission speed in the house to be detected is the fastest (or the average formaldehyde concentration is the lowest) is predicted, and at least one ventilation position and at least one ventilation direction corresponding to the at least one ventilation position are obtained based on the air flow velocity field.

[0118] The trained RBF neural network can be used to simulate the formaldehyde emission intensity under different air circulation speed field conditions, and to predict the air circulation speed field when the average formaldehyde concentration in the whole house is the lowest. Two enhanced ventilation coordinates and the corresponding circulation directions are obtained according to the prediction results, and the solution results are as shown in Figure 11 .

[0119] In one possible embodiment, the step S4 of ventilating the house to be tested at each ventilation position in the ventilation direction corresponding to each ventilation position can specifically include the following steps:

[0120] S401: Set a ventilation device at each ventilation position, and ventilate the house to be tested through the ventilation device.

[0121] Optionally, a ventilation device can be set at each ventilation position, and the house to be tested is de-aldehyded through the ventilation device in the ventilation direction corresponding to each ventilation position. The ventilation device can be operated intermittently.

[0122] S402: Determine the formaldehyde over-standard risk points in the house to be tested based on the turbulent flow model and the formaldehyde distribution data set, and set a temperature rising device at the formaldehyde over-standard risk points.

[0123] Optionally, according to the distribution of the formaldehyde concentration in the whole house, the formaldehyde over-standard risk points in the house to be tested can be determined based on the turbulent flow model and the formaldehyde distribution data set, and a temperature rising device is set at the formaldehyde over-standard risk points, so as to accelerate the de-aldehyde speed of the formaldehyde over-standard risk points.

[0124] Optionally, in order to further improve the de-aldehyde speed of the formaldehyde over-standard risk points, one or more of polyethylene glycol, polyurethane, and ammonia pine oil can be used as a formaldehyde blocking agent for de-aldehyde at these risk points, and a carbon bag filled with high-iodine-value coconut activated carbon or nutshell activated carbon can be used as an adsorbent for formaldehyde adsorption, so as to further improve the de-aldehyde efficiency.

[0125] Specifically, two ventilation positions and two ventilation directions corresponding to the two ventilation positions can be predicted by using the trained RBF neural network. Two sets of ventilation devices can be set at the two ventilation positions, and the ventilation devices are air circulation fans that can be intermittently operated, have a timing function, and are highly adjustable, with a single opening time of 1.5 h and an interval time of 15 min. According to the distribution of the formaldehyde concentration in the whole house, a temperature rising device is set at the high over-standard risk points near the wooden furniture, and the temperature rising device is an electric heater with adjustable temperature, which can be continuously heated for 48 h to make the air temperature of the target point reach 37℃. After the setting is completed, the ventilation device and the temperature rising device are started, all doors and windows in the whole house are kept open, and 12 h of enhanced ventilation treatment is implemented. After the treatment is completed, natural ventilation is maintained. Finally, the test results are as shown in Figure 12 and Figure 15The formaldehyde removal results shown in Figure 12 and Figure 15 are 0.015 mg / m 3 and 0.019 mg / m 3 , which are lower than the indoor formaldehyde one-hour average concentration limit of 0.08 mg / m 3 specified in the indoor air quality standard (GB / T 18883-2022), thus having good formaldehyde removal effect.

[0126] In a possible embodiment, the ventilation device comprises an air circulation fan with adjustable height and intermittent operation, and the temperature raising device comprises a heater with adjustable temperature.

[0127] Optionally, the air circulation fan can be an intermittent ventilation device with timing function and adjustable height, the single opening time of the air circulation fan can be 1.5 hours, and the interval time can be 15 minutes. The heater can continuously heat for 48 hours, and the heater can make the temperature of the formaldehyde over-limit risk point reach more than 37 degrees Celsius.

[0128] In a possible embodiment, after performing S4: ventilating the house to be detected at each ventilation position in the ventilation direction corresponding to each ventilation position, the method further comprises:

[0129] S501: performing first formaldehyde detection on the house to be detected; if the formaldehyde average in the house to be detected is greater than or equal to a first preset concentration, or the formaldehyde value of a single detection point in the house to be detected is greater than or equal to a second preset concentration, the formaldehyde acceptance of the house to be detected fails, and formaldehyde plugging or adsorption by adsorbent is performed in the formaldehyde over-limit area.

[0130] Optionally, in order to accept the formaldehyde removal method in the present application using the turbulent flow model and model training, formaldehyde detection can be performed on the house to be detected, if the formaldehyde concentration of the house to be detected is less than the first preset concentration, and the formaldehyde value of no detection point in the house to be detected is greater than or equal to the second preset concentration, it is considered that the formaldehyde acceptance of the house to be detected is passed.

[0131] Optionally, if the formaldehyde average in the house to be detected is greater than or equal to the first preset concentration, or the formaldehyde value of a single detection point in the house to be detected is greater than or equal to the second preset concentration, it is considered that the formaldehyde acceptance effect of the house to be detected is not passed, and formaldehyde plugging or adsorption by adsorbent can be performed in the formaldehyde over-limit area,

[0132] S502: If the formaldehyde test of the house to be tested fails, a second formaldehyde test is performed on the house to be tested after a first preset time interval; if the mean formaldehyde value in the house to be tested is greater than or equal to a third preset concentration, S4 is repeated: the house to be tested is ventilated at each ventilation position in the ventilation direction corresponding to each ventilation position.

[0133] Optionally, if the formaldehyde inspection of the house to be inspected fails, the house to be inspected can be subjected to enhanced ventilation treatment within the first preset time, and after the enhanced ventilation treatment is completed, nano-photocatalysts can be sprayed at the risk points of formaldehyde exceeding the standard to treat the formaldehyde.

[0134] Optionally, after a first preset time interval, a second formaldehyde test can be performed on the house to be tested. If the formaldehyde test of the house to be tested passes, the formaldehyde removal is completed. If the formaldehyde test of the house to be tested fails, step S4 can be repeated until the formaldehyde test passes.

[0135] In a possible embodiment, the first preset concentration is 0.08 mg / m 3 The second preset concentration is 0.04 mg / m 3 The third preset concentration is 0.08 mg / m 3 The first preset time is 24 hours. The first preset concentration, the second preset concentration, the third preset concentration, and the first preset time can be adjusted based on actual production and living needs. When a more stringent formaldehyde removal environment is required, the first preset concentration, the second preset concentration, the third preset concentration can be lowered, or the first preset time can be extended. The first preset concentration can be consistent with the second preset concentration, so that the formaldehyde removal method using the turbulence model and model training can be accepted for the inspected house based on a certain acceptance standard.

[0136] It should be noted that the above-mentioned order of the embodiments of the present application is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. The above description is of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0137] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

Claims

1. A formaldehyde removal method using a turbulence model and model training, characterized in that: The following steps are involved: Obtain a three-dimensional data model and formaldehyde distribution dataset of the house to be inspected; Establishing a turbulence model of the house to be inspected based on the three-dimensional data model; Simulating the formaldehyde emission state of the house to be inspected under different ventilation conditions based on the turbulence model and the formaldehyde distribution dataset, and predicting at least one ventilation position in the house to be inspected where the formaldehyde emission rate is fastest and at least one ventilation direction corresponding to the at least one ventilation position; The house to be inspected is ventilated at each ventilation position in a ventilation direction corresponding to each ventilation position.

2. The formaldehyde removal method using a turbulence model and model training according to claim 1, characterized in that: The step of obtaining a three-dimensional data model and a formaldehyde distribution data set of a house to be inspected includes: Acquiring dimension information of the house to be detected, and dividing the space within the house to be detected into grids based on the dimension information to establish the three-dimensional data model; The formaldehyde concentrations at different locations and heights in the house are monitored at fixed points, and a formaldehyde distribution data set in the house to be detected is established based on the monitoring results of the formaldehyde concentrations.

3. The formaldehyde removal method using a turbulence model and model training according to claim 2, characterized in that: The step of obtaining the size information of the house to be detected, and dividing the space within the house to be detected into grids based on the size information to establish the three-dimensional data model includes: Obtaining a floor plan or floor plan of the house to be inspected; Boundary conditions and related parameters are set based on the floor plan or floor plan, and triangular surface meshing or non-structural mixed mode volume meshing is performed on the rooms or structures in the house to be inspected; the number of grids after the meshing is greater than or equal to one million.

4. The formaldehyde removal method using a turbulence model and model training according to claim 1, characterized in that: The step of establishing the turbulence model of the house to be inspected based on the three-dimensional data model and the formaldehyde distribution dataset includes: Acquiring simulation parameters and a first preset formula group of the three-dimensional data model; Based on the simulation parameters and the first preset formula group, a section cloud simulation is performed on the three-dimensional data model to obtain a turbulence model of the house to be detected.

5. The formaldehyde removal method using a turbulence model and model training according to claim 4, characterized in that: The first preset formula group includes: Where u, v, w are the velocity components of the control volume of the micelle (size dx, dy, dz) in the Cartesian coordinate system in the x, y, and z directions; ρ is the fluid density; μ is the kinematic viscosity coefficient; V is the three directional components of the velocity; ρc is the formaldehyde mass concentration; Γ is the formaldehyde diffusion coefficient; S c is the production rate of formaldehyde inside the indoor system; k is the turbulent pulsation kinetic energy per unit mass flow; ε is the dissipation rate of pulsation kinetic energy; C1 = 1.44, C2 = 1.92, σ ε =1.22, the time-averaged equations (1), (2), (3) and the k equation (5) and the ε equation (6) constitute the basic governing equations of the standard k-ε model. The algebraic expressions of μt and ε make the equations closed.

6. The formaldehyde removal method using a turbulence model and model training according to claim 1, characterized in that: The method of simulating the formaldehyde emission state of the house to be inspected under different ventilation conditions based on the turbulence model and the formaldehyde distribution dataset, and predicting at least one ventilation position with the fastest formaldehyde emission rate in the house to be inspected and at least one ventilation direction corresponding to the at least one ventilation position, includes: Obtaining an air circulation data field in the house to be detected based on the turbulence model; Performing model training based on the air circulation data field and the formaldehyde distribution data set to obtain a formaldehyde emission model in the house to be detected; Based on the formaldehyde emission model, the formaldehyde emission concentration under different ventilation conditions is simulated to predict at least one ventilation position with the fastest formaldehyde emission rate in the house to be tested and at least one ventilation direction corresponding to the at least one ventilation position.

7. The formaldehyde removal method using a turbulence model and model training according to claim 1, characterized in that: Ventilating the house to be inspected at each ventilation position in a ventilation direction corresponding to each ventilation position includes: A ventilation device is provided at each ventilation position, and the house to be inspected is ventilated by the ventilation device; Based on the turbulence model and the formaldehyde distribution data set, the formaldehyde exceeding risk point in the house to be inspected is determined, and a heating device is set at the formaldehyde exceeding risk point.

8. The formaldehyde removal method using a turbulence model and model training according to claim 7, characterized in that: The ventilation device includes an air circulation fan that is height-adjustable and operates intermittently; The temperature increasing device comprises a heater with adjustable temperature.

9. The formaldehyde removal method using a turbulence model and model training according to claim 1, characterized in that: After ventilating the house to be inspected at each ventilation position in the ventilation direction corresponding to each ventilation position, the method further includes: Performing a first formaldehyde test on the house to be tested; if the average formaldehyde value in the house to be tested is greater than or equal to a first preset concentration, or the formaldehyde value at a single test point in the house to be tested is greater than or equal to a second preset concentration, the formaldehyde test of the house to be tested fails, and formaldehyde blocking or adsorption using an adsorbent is performed in the area where the formaldehyde exceeds the standard; If the formaldehyde inspection of the house to be inspected fails, a second formaldehyde inspection is conducted on the house to be inspected after a first preset time interval; if the formaldehyde value of a single inspection point in the house to be inspected is greater than or equal to a third preset concentration, the following steps are repeated: ventilating the house to be inspected at each ventilation position in the ventilation direction corresponding to each ventilation position.

10. The formaldehyde removal method using a turbulence model and model training according to claim 9, characterized in that: The first preset concentration is 0.08 mg / m 3 The second preset concentration is 0.0 mg / m 3 The third preset concentration is 0.08 mg / m 3 ; The first preset time is 24 hours.

Images