Multifunctional integrated stove and oven control system based on Internet of Things

Abstract

The invention belongs to the technical field of smart home, and particularly relates to a multifunctional integrated stove and oven control system based on the Internet of Things, and the system comprises the steps: obtaining the environment data of an area where a human body stands, and calculating the current sensible temperature of the human body under the environment data according to the environment data; and the dynamic adjusting module uses a genetic algorithm to calculate a ventilation control strategy required for adjusting the current sensible temperature value to the target sensible temperature value, and the current environment temperature is adjusted to the environment temperature capable of enabling the human body to maintain the target sensible temperature through ventilation control, so that the sensible temperature sensed by the human body is regulated and controlled. According to the method, the problem that a traditional air conditioning system cannot be adjusted according to the standing area of a person in the kitchen environment can be solved, temperature adjustment can be controlled according to the specific requirement of the human body for temperature sensing, and the adjusted and controlled temperature better meets the actual requirement of the human body.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart home, and particularly relates to a multi-functional integrated stove oven control system based on the Internet of Things. Background Art

[0002] In a smart kitchen, with the increasing number of cooking devices, such as stoves, ovens, steamers, microwave ovens, etc., these devices generate a large amount of heat during operation. Especially when multiple devices work simultaneously, this high-temperature environment will cause the local temperature in the kitchen to rise rapidly, forming an obvious heat island effect. Particularly when the operator needs to approach the heat source, such as standing beside the stove or opening the oven to add food, the temperature in the area where the human body stands may instantly rise to 40°C or higher, that is, the local temperature where the human body is located may be much higher than the overall environmental temperature and exceed the comfortable temperature range of the human body's sense of touch (usually 20°C - 26°C). This high-temperature environment will not only make people feel stuffy, but may also cause fatigue and discomfort.

[0003] The comfortable range of the human body's sense of touch is a standard obtained from physiological and psychological research. The sense of touch temperature is a comprehensive index that combines various factors such as temperature, humidity, wind speed, and thermal radiation, and can more accurately reflect the true feelings of the human body. When the environmental temperature exceeds this range, the comfort level of the human body will be greatly reduced. However, in a kitchen environment with high humidity, the evaporation of sweat is blocked and the heat dissipation efficiency is reduced, further intensifying the stuffy feeling. Traditional kitchen air conditioning systems usually adjust based on the overall environmental temperature and cannot provide a precise solution for local high-temperature areas. Due to the extremely uneven temperature distribution in the kitchen, a single temperature setting value is difficult to meet the actual needs of different areas. For example, even when the overall environmental temperature is within the comfortable range, the human body close to the heat source may still feel a significant high-temperature impact.

[0004] In addition, traditional air conditioning systems often ignore the true feelings of the human body towards temperature (i.e., the sense of touch temperature), and only rely on the physical environmental temperature for control. This method cannot comprehensively consider the influence of factors such as humidity, wind speed, and thermal radiation on the comfort of the human body, resulting in a poor actual temperature perception effect for the human body. Summary of the Invention

[0005] To solve the above problems existing in the prior art, the present invention provides a multi-functional integrated stove oven control system based on the Internet of Things, which solves the problem that traditional air conditioning systems ignore the true feelings of the human body towards temperature (i.e., the sense of touch temperature), only rely on the physical environmental temperature for control, and cannot target the large temperature changes in different areas in a special environment such as the kitchen to regulate the temperature around people.

[0006] The object of the present invention can be achieved by the following technical solutions: It includes a positioning and tracking module, a regional multi-parameter detection module, a perceived temperature calculation module, a dynamic adjustment module, and an execution module connected in sequence;

[0007] The positioning and tracking module is used to real-time track the position data of the human body in the kitchen and transmit the position data to the regional multi-parameter detection module;

[0008] The regional multi-parameter detection module is used to obtain the environmental data of the position of the human activity area and transmit the data to the perceived temperature calculation module. The environmental data includes local temperature, local humidity, and local heat radiation data;

[0009] The perceived temperature calculation module is used to calculate the current perceived temperature value based on the environmental temperature according to a preset perceived temperature calculation model;

[0010] The dynamic adjustment module uses a genetic algorithm to calculate the ventilation control strategy required to adjust the current perceived temperature value to the target perceived temperature value;

[0011] The dynamic adjustment module sends the control instruction generated by the ventilation strategy to the execution module. The execution module receives and executes the control instruction. The control instruction includes controlling the number of operating fans, power, and blowing angle in the execution module, as well as the adjustment temperature and adjustment angle of the air conditioner.

[0012] Preferably, the perceived temperature calculation model is determined by training a neural network model using training data, and includes the following steps:

[0013] Obtain training data. The training data includes multiple groups of environmental data and their corresponding calculated current perceived temperature values. The environmental data includes local temperature, local humidity, and local heat radiation data;

[0014] Use the training data to learn and train a convolutional neural network model to generate a perceived temperature calculation model.

[0015] Preferably, the ventilation control strategy generated by the dynamic adjustment module includes:

[0016] Taking the perceived temperature calculation model as the solution function of the genetic algorithm, under the constraints of the constraint conditions, taking the minimum difference between the current perceived temperature value predicted by the perceived temperature calculation model and the target perceived temperature value as the goal, perform multiple iterative solutions to obtain a ventilation strategy for maintaining the target perceived temperature value;

[0017] Among them, the constraint condition formula includes local temperature, local humidity, local heat radiation data, and in the execution module, the power, quantity, and blowing angle range of the fan, and the power, quantity, and blowing angle range of the air conditioner.

[0018] Preferably, the perceived temperature calculation module further includes a model optimization unit, and the model optimization unit uses a Bayesian framework to optimize the perceived temperature calculation model.

[0019] Preferably, during the iteration of the perceived temperature calculation model, the model optimization unit uses the root mean square error function as the loss function to optimize the perceived temperature calculation model, including the following steps:

[0020] S1: Forward propagation. First, perform one forward propagation, and calculate the sample prediction value using the current parameters of the perceived temperature calculation model.

[0021] S2: Calculate the loss value. Use the sample prediction value and the actual value actually obtained by the regional multi-parameter detection module to calculate the loss of the perceived temperature calculation model.

[0022] S3: Backward propagation. Use the stochastic gradient descent algorithm to calculate the gradient of the loss with respect to the weights and biases of each layer.

[0023] S4: Update the parameters. Use the gradient descent method to update the weights and biases in the convolutional neural network layer along the negative gradient direction.

[0024] Preferably, in step S2, the root mean square error function is used to calculate the loss, and the calculation formula is as follows:

[0025]

[0026] where y p represents the true value of the i-th sample, and y a represents the prediction value of the perceived temperature calculation model for the i-th sample, and n is the number of training quantities.

[0027] Preferably, in step S4, the update rules for the weights and biases in the convolutional layer are:

[0028]

[0029] where γ is the learning rate of the perceived temperature calculation model, are the gradients of the root mean square error function with respect to the weights and biases respectively;

[0030] l represents the l-th convolutional layer of the perceived temperature calculation model.

[0031] Preferably, it further includes a regional oil fume concentration acquisition module and an oil fume concentration evaluation module. The oil fume concentration acquisition module is used to acquire the oil fume concentration in the environment and transmit it to the oil fume concentration evaluation module. The oil fume concentration evaluation module maps the oil fume concentration to the preset oil fume concentration threshold range and transmits the mapping result to the dynamic adjustment module. The dynamic adjustment module generates a power adjustment instruction for the range hood according to the mapping result.

[0032] Preferably, the regional oil fume concentration acquisition module includes a particulate matter sensor and a VOC sensor.

[0033] The beneficial effects of the present invention are as follows:

[0034] By acquiring the environmental data of the area where the human body stands and calculating the current perceived temperature of the human body under the environmental data, the dynamic adjustment module uses the genetic algorithm to calculate the ventilation control strategy required to adjust the current perceived temperature value to the target perceived temperature value, and ventilates and controls the current environmental temperature to the environmental temperature that allows the human body to maintain the target perceived temperature, so as to realize the regulation of the perceived temperature perceived by the human body. This method can not only solve the problem that the traditional air conditioning system cannot be adjusted according to the standing area of people in the kitchen environment, but also can control the temperature adjustment according to the specific temperature perception needs of the human body, making the regulated temperature more in line with the actual needs of the human body. And the perceived temperature calculation model trains the convolutional neural network model through a large number of training data and continuously optimizes the model performance to better adapt to different kitchen environments and user needs. Description of the Drawings

[0035] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0036] Figure 1 It is the structural block diagram of the control system of the present invention;

[0037] Figure 2 It is the optimization step block diagram of the model optimization unit of the present invention. Detailed Embodiments

[0038] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following describes in detail the specific embodiments, structures, features and their effects of the present invention with reference to the accompanying drawings and preferred embodiments.

[0039] Please refer to Figure 1 - Figure 2, this embodiment provides a multifunctional integrated stove oven control system based on the Internet of Things. The control system includes a positioning and tracking module, a regional multi-parameter detection module, a body-sensed temperature calculation module, a dynamic adjustment module, and an execution module that are connected in sequence. Among them, the positioning and tracking module, the regional multi-parameter detection module, the body-sensed temperature calculation module, the dynamic adjustment module, and the execution module are interconnected through the network to form an ecosystem that works in cooperation. The cooking equipment in the kitchen includes a stove, an oven, a microwave oven, etc.

[0040] Since people need to move to different positions to perform different operations according to different cooking steps during the cooking process, in order to better grasp the specific position of people, the positioning and tracking module is used to track the position data of the human body in the kitchen in real time. In order to prevent the heat dissipation of the cooking equipment in the kitchen from interfering with the judgment of the presence of people by the positioning and tracking module, the positioning and tracking module uses positioning technology and an infrared camera for positioning. After the positioning module captures the position of the person, it transmits the position data to the regional multi-parameter detection module. The thermal imaging camera is installed in the center of the kitchen ceiling, and the human body contour is recognized in real time through OpenCV and matched with the coordinates of the positioning technology. The position where the detected human body area is located includes the position data and the standing posture of the human body.

[0041] As mentioned above, the body-sensed temperature is affected by multiple environmental parameters and is a comprehensive index. It combines multiple factors such as temperature, humidity, wind speed, and thermal radiation, and can more accurately reflect the true feelings of the human body. When the environmental temperature exceeds this range, the comfort level of the human body will be greatly reduced. Moreover, combined with the previous description, it is different when we stand in front of the working cooking equipment and stand in front of other regional positions. Therefore, the environmental temperature varies in different regional positions, and the temperature in the subsequent kitchen needs to be adjusted according to the comfortable temperature of the human body. It is necessary to comprehensively consider the influence of various environmental factors on the body-sensed temperature in different regions.

[0042] The regional multi-parameter detection module is used to obtain the environmental data of the human activity area position and transmit the data to the body-sensed temperature calculation module. The environmental data includes local temperature, local humidity, and local thermal radiation data. After receiving the position of the human body captured by the positioning and tracking module, the regional multi-parameter detection module detects various environmental parameters within a certain space around the human body, and then transmits the detection results to the subsequent body-sensed temperature calculation module. According to the standing posture of the user detected by the previous positioning and tracking module, the calculation method of the bounding box is used to calculate a certain space here, so that the calculated certain space can cover the entire area of the human body.

[0043] The multi-parameter detection module includes a temperature sensor, a humidity sensor, an ultrasonic anemometer, an infrared thermal radiation sensor, and a current transformer. The multi-parameter detection module obtains the position information of the human body based on positioning and tracking. This position information includes the specific coordinate information of the location where the human body is located, such as two-dimensional plane coordinates or three-dimensional space coordinate information. The regional multi-parameter detection module uses the temperature sensor, humidity sensor, ultrasonic anemometer, infrared thermal radiation sensor, and current transformer to complete the detection of relevant data according to the specific coordinate information. Among them, the infrared thermal radiation sensor is used to directly capture the local thermal radiation data at a specific coordinate position. The current transformer is set at the power supply end of the stove or oven and is used to indirectly calculate the thermal radiation intensity of the cooking device. Since generally when the value of the thermal radiation intensity increases, that is, when a person stands around the working cooking device, therefore, through the detection value of the current transformer, the data can be mutually verified with the data of the infrared thermal radiation sensor.

[0044] For example, after obtaining the stove power P through the current transformer and combining the material data of the cookware, such as the cast iron thermal efficiency η = 35%, calculate the effective radiation of the stove when working at power P.

[0045] r is the radius of the cookware.

[0046] Use Q radiation to calculate the detection range threshold interval of the infrared thermal radiation sensor, and verify the detection value of the infrared thermal radiation sensor through this interval.

[0047] The perceived temperature calculation module is used to calculate the current perceived temperature value based on the environmental temperature according to a preset perceived temperature calculation model; the preset perceived temperature calculation model is trained using a large amount of historical environmental data and the corresponding perceived temperature calculation values as a training set. Input the locally detected temperature, local humidity, and local thermal radiation data into the preset perceived temperature calculation model to obtain the perceived temperature value at the current environmental temperature; the perceived temperature calculation module sends the calculated perceived temperature value to the dynamic adjustment module.

[0048] The dynamic adjustment module uses the genetic algorithm to calculate the ventilation control strategy required to adjust the current perceived temperature value to the target perceived temperature value; the function of the dynamic adjustment module is realized by integrating the calculation program of the genetic algorithm in a microcomputer.

[0049] Among them, the ventilation control strategy generated by the dynamic adjustment module includes:

[0050] Taking the perceived temperature calculation model as the solution function of the genetic algorithm, under the constraints of the constraint conditions, taking the minimum difference between the currently predicted perceived temperature value and the target perceived temperature value by the perceived temperature calculation model as the goal, perform multiple iterative solutions to obtain the ventilation strategy to maintain the target perceived temperature value.

[0051] Among them, the constraint conditions include local temperature, local humidity, local thermal radiation data, and in the execution module, the power, quantity, and blowing angle range of the fans, and the power, quantity, and blowing angle range of the air conditioners;

[0052] The dynamic adjustment module sends the control instructions generated by the ventilation strategy to the execution module. The execution module receives and executes the control instructions. The control instructions include controlling the number of fans turned on, power, and blowing angle in the execution module, and the adjusted temperature and adjusted angle of the air conditioner, so as to realize the dynamic adjustment of the environment in the kitchen and make the user in a comfortable body-sensation temperature environment.

[0053] By obtaining the environmental data of the area where the human body stands and calculating the current body-sensation temperature of the human body under the environmental data, the dynamic adjustment module uses the genetic algorithm to calculate the ventilation control strategy required to adjust the current body-sensation temperature value to the target body-sensation temperature value. The ventilation controls the current environmental temperature to be the environmental temperature that can allow the human body to maintain the target body-sensation temperature, so as to realize the regulation of the body-sensation temperature perceived by the human body. This method can not only solve the problem that the traditional air-conditioning system cannot be adjusted according to the human standing area in the kitchen environment, but also can control the temperature adjustment according to the specific temperature perception needs of the human body, making the regulated temperature more in line with the actual needs of the human body.

[0054] In one embodiment, the body-sensation temperature calculation module is determined by training a neural network model using training data, including the following steps:

[0055] Obtain training data. The training data includes multiple groups of environmental data and their corresponding calculated current body-sensation temperature values. The environmental data includes local temperature, local humidity, and local thermal radiation data;

[0056] Use the training data to learn and train the convolutional neural network model to generate a body-sensation temperature calculation model. The training process includes optimizing the model. The optimization process is implemented by the model optimization unit in the body-sensation temperature calculation module. Among them, during the iteration of the body-sensation temperature calculation model, the model optimization unit uses the Bayesian framework to optimize the body-sensation temperature calculation model. Here, the Bayesian optimization is to construct a probability model (usually called a surrogate model) of the objective function and use this model to determine the next sampling point in order to find the optimal parameter combination. Apply the Bayesian optimization framework to the hyperparameter tuning of the convolutional neural network (CNN). Hyperparameters refer to those parameters that need to be set before training, such as learning rate, batch size, number of layers, number of neurons in each layer, type of activation function, regularization coefficient, etc. Among them, a Gaussian process can be selected as the surrogate model to approximate the objective function.

[0057] Please refer to Figure 2, the model optimization unit optimizes the perceived temperature calculation model using the root mean square error function as the loss function, including the following steps:

[0058] S1: Forward propagation. First, perform one forward propagation and calculate the sample prediction value using the current parameters of the perceived temperature calculation model.

[0059] S2: Calculate the loss value. Use the sample prediction value and the actual value actually obtained by the regional multi-parameter detection module to calculate the loss of the perceived temperature calculation model. Among them, the root mean square error function (RMSE) is used to calculate the loss, and the calculation formula is as follows:

[0060]

[0061] Among them, y p represents the true value of the i-th sample, and y a represents the prediction value of the perceived temperature calculation model for the i-th sample, and n is the number of training quantities.

[0062] S3: Backward propagation. Use the stochastic gradient descent algorithm to calculate the gradients of the loss with respect to the weights and biases of each layer.

[0063] S4: Update parameters. Use the gradient descent method to update the weights and biases in the convolutional neural network layer along the negative gradient direction, including the following steps:

[0064] S41: Obtain the gradients of the current layer from the backward propagation respectively, where represents the sensitivity of RMSE to the convolutional kernel weight matrix;

[0065] represents the sensitivity of RMSE to the convolutional kernel bias, where l represents the l-th convolutional layer of the perceived temperature calculation model;

[0066] For example, if the convolutional kernel size is 3×3, then W l is a 3×3 matrix, and the gradient is also a matrix of the same size;

[0067] S42: Use the learning rate γ of the perceived temperature calculation model to control the step size of model parameter update:

[0068]

[0069] S43: Update the parameters along the negative gradient direction:

[0070] W l ←W l -ΔW l

[0071] b l ←bl -Δb l

[0072] Calculate the gradients of the model parameters through the backpropagation algorithm, and update the parameters along the gradient direction to minimize the loss, so that the weights and biases of each layer of the convolutional neural network are gradually iteratively optimized to gradually improve the prediction accuracy of the body sensation temperature calculation model.

[0073] Detect the location of the human body through the human body position detection technology, and then use a variety of sensors to detect the real-time temperature, and perceive the actual environmental temperature and body sensation temperature of the area where the human body is located in real time. Accordingly, dynamically adjust the air supply mode (such as wind direction, wind speed and temperature) of the air conditioning system to adjust the environmental temperature until the body sensation temperature reaches the preset comfort range threshold. This method can not only solve the problem that the traditional air conditioning system cannot control the temperature adjustment according to the specific temperature perception needs of the human body in the specific area in the kitchen environment. In addition, through the refined control of the temperature, the goal of energy conservation and environmental protection can be achieved, providing a more intelligent and user-friendly kitchen environment for users.

[0074] In the kitchen environment, the role of the range hood is to effectively remove the oil fumes generated during the cooking process to keep the air fresh and reduce the potential harm to human health. The power of the range hood generally has multiple gears, but generally when users are cooking, they choose the power of the range hood according to experience, and the general judgment experience is inaccurate. However, the range hood will generate a certain amount of noise when it operates, and generally when users are cooking, if the range hood always operates at a high power, a high noise level will be generated. However, as the cooking steps are different, the concentration of the oil fumes generated is different. For example, when the wok on the stove is opened, after the range hood works for a certain period of time, the concentration of the oil fumes will decrease, or after the cooking requires the pot lid to be covered, the concentration of the oil fumes will drop. At this time, the range hood does not need such a high power to achieve the adsorption of the oil fumes, but users may not notice that they need to make corresponding adjustments to the power of the range hood.

[0075] Since the environmental influence value of the perceived temperature is affected by the environmental humidity, the control device used also includes a ventilator, that is, there is a certain air flow. Therefore, it is necessary to control the subsequent range hood according to the specific oil fume concentration. There are an area oil fume concentration acquisition module and an oil fume concentration evaluation module. The area oil fume concentration acquisition module includes a particulate matter sensor and a VOC sensor. Here, the area oil fume concentration acquisition module also detects the regional position of the human body detected by the position tracking module. The oil fume concentration acquisition module is used to acquire the oil fume concentration in the environment and transmit it to the oil fume concentration evaluation module. The oil fume concentration evaluation module maps the oil fume concentration to the preset oil fume concentration threshold range and transmits the mapping result to the dynamic adjustment module. The dynamic adjustment module generates a power adjustment instruction for the range hood according to the mapping result. Here, the specific corresponding relationship between the oil fume concentration threshold range, the oil fume concentration, and the range hood power is the same as the principle of the intelligent range hood being specifically limited according to the oil fume concentration in the specific cooking environment under the existing technology.

[0076] The above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments by using the disclosed technical content within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modification, equivalent change, and modification made to the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A multifunctional integrated stove oven control system based on the Internet of Things, characterized by: It includes a positioning tracking module, a regional multi-parameter detection module, a body temperature calculation module, a dynamic adjustment module and an execution module which are connected in sequence; The positioning and tracking module is used to track the position data of the human body in the kitchen in real time and transmit the position data to the regional multi-parameter detection module; The regional multi-parameter detection module is used to obtain environmental data of the human activity area and transmit the data to the body temperature calculation module, wherein the environmental data includes local temperature, local humidity and local thermal radiation data; The body temperature calculation module is used to calculate the current body temperature value based on the ambient temperature based on a preset body temperature calculation model; The dynamic adjustment module uses a genetic algorithm to calculate the ventilation control strategy required to adjust the current body temperature value to the target body temperature value; The dynamic adjustment module generates control instructions from the ventilation strategy and sends them to the execution module. The execution module receives and executes the control instructions, which include controlling the number of fans started, power and blowing angle in the execution module and the adjustment temperature and adjustment angle of the air conditioner.

2. The multifunctional integrated stove oven control system based on the Internet of Things according to claim 1 is characterized in that: The body temperature calculation model includes using training data to train a neural network model, including the following steps: Acquire training data, the training data including multiple sets of environmental data and corresponding current body temperature values ​​calculated respectively, the environmental data including local temperature, local humidity and local thermal radiation data; The training data is used to train the convolutional neural network model to generate a body temperature calculation model.

3. The multifunctional integrated stove oven control system based on the Internet of Things according to claim 2 is characterized in that: The dynamic adjustment module generates a ventilation control strategy including: The sensible temperature calculation model is used as a solution function of the genetic algorithm. Under the constraints of the constraints, multiple iterations are performed with the goal of minimizing the difference between the current sensible temperature value predicted by the sensible temperature calculation model and the target sensible temperature value, so as to obtain a ventilation strategy that maintains the target sensible temperature value. Among them, the constraint condition formula includes local temperature, local humidity, local thermal radiation data and the power, quantity and blowing angle range of the fan, and the power, quantity and blowing angle range of the air conditioner in the execution module.

4. The multifunctional integrated stove oven control system based on the Internet of Things according to claim 1 is characterized in that: The body temperature calculation module also includes a model optimization unit, which optimizes the body temperature calculation model using a Bayesian framework.

5. The multifunctional integrated stove oven control system based on the Internet of Things according to claim 4 is characterized in that: In the iteration process of the body temperature calculation model, the model optimization unit optimizes the body temperature calculation model by taking the mean square root error function as the loss function, including the following steps: S1: forward propagation, firstly performing a forward propagation, and calculating the sample prediction value using the current parameters of the body temperature calculation model; S2: Calculate the loss value, using the sample prediction value and the actual value actually obtained by the regional multi-parameter detection module to calculate the loss of the body temperature calculation model; S3: Back propagation, using the stochastic gradient descent algorithm to calculate the gradient of the loss with respect to the weights and biases of each layer; S4: Update parameters and use gradient descent to update the weights and biases in the convolutional neural network layer along the negative gradient direction.

6. The multifunctional integrated stove oven control system based on the Internet of Things according to claim 5 is characterized in that: In step S2, the loss is calculated using the root mean square error function, and the calculation formula is as follows: Among them, y p represents the true value of the i-th sample, y a It represents the predicted value of the body temperature calculation model for the i-th sample, and n is the number of training samples.

7. The multifunctional integrated stove oven control system based on the Internet of Things according to claim 5 is characterized in that: in, In step S4, the update rule for the weights and biases in the convolutional layer is: Among them, γ is the learning rate of the body temperature calculation model, are the gradients of the mean square root error function with respect to weights and biases respectively; l represents the lth convolutional layer of the body temperature calculation model.

8. The multifunctional integrated stove oven control system based on the Internet of Things according to claim 1 is characterized in that: It also includes a regional oil fume concentration acquisition module and an oil fume concentration assessment module. The oil fume concentration acquisition module is used to acquire the oil fume concentration in the environment and transmit it to the oil fume concentration assessment module. The oil fume concentration assessment module maps the oil fume concentration with a preset oil fume concentration threshold range and transmits the mapping result to the dynamic adjustment module. The dynamic adjustment module generates a power adjustment instruction for the range hood according to the mapping result.

9. The multifunctional integrated stove oven control system based on the Internet of Things according to claim 8, characterized in that: The regional oil smoke concentration acquisition module includes a particle sensor and a VOC sensor.

Images