Control method of heating equipment and heating equipment

Abstract

The invention relates to the technical field of heating equipment, and discloses a heating equipment control method and heating equipment.The method comprises the steps that a first average thermal sensation index at the current moment is obtained on the basis of indoor environment data at the current moment and in combination with an average thermal sensation index model; based on the first average thermal sensation index, the target average thermal sensation index and the current water supply temperature of the heating equipment, the first water supply temperature at the target moment is obtained; predicting a second average thermal sensation index at the target moment based on the first average thermal sensation index and the first water supply temperature; the first water supply temperature at the target moment is optimized in combination with the target average thermal sensation index, and the target water supply temperature is obtained; and at the target moment, operating parameters of the heating equipment are adjusted based on the target water supply temperature. The heating equipment can adjust the water supply temperature in advance according to the change of the external environment temperature, it is ensured that indoor personnel are in a relatively comfortable thermal environment, and the comfort of the indoor environment is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of heating equipment, and in particular to a control method of heating equipment and the heating equipment. Background Art

[0002] As the world pays more and more attention to energy conservation and emission reduction, traditional heating and cooling methods are facing challenges due to high energy consumption and environmental pollution. Heating equipment such as air source heat pumps have attracted widespread attention for their high efficiency and environmental protection. However, when facing complex and changing environmental conditions, existing air source heat pumps cannot adjust in time according to environmental changes, resulting in low energy efficiency of air source heat pumps and reduced user comfort experience. Summary of the invention

[0003] The technical problem solved by the present invention is to provide a control method for heating equipment, which effectively solves the technical problem of delayed response of the heating equipment.

[0004] The above technical problems are solved by the following technical solutions:

[0005] A method for controlling a heating device, the method comprising:

[0006] Get the current indoor environment data;

[0007] Based on the indoor environment data at the current moment and in combination with the average thermal sensation index model, a first average thermal sensation index at the current moment is obtained;

[0008] Based on the first average thermal sensation index, the target average thermal sensation index and the current water supply temperature of the heating device, obtaining a first water supply temperature at a target time, wherein the target time is a time after the current time;

[0009] predicting a second average thermal sensation index at a target time based on the first average thermal sensation index and the first water supply temperature;

[0010] Optimizing the first water supply temperature at the target time based on the second average thermal sensation index and the target average thermal sensation index to obtain a target water supply temperature;

[0011] At the target time, the operating parameters of the heating equipment are adjusted based on the target water supply temperature, and the operating parameters at least include the fan speed or compressor output power of the heating equipment.

[0012] Compared with the background technology, the control method of the present invention has the following beneficial effects: the first average thermal sensation index at the current moment is obtained by combining the indoor environment data at the current moment with the average thermal sensation index model; and the first water supply temperature at a moment after the current moment is obtained according to the first average thermal sensation index at the current moment, the target average thermal sensation index and the current water supply temperature of the heating equipment. The second average thermal sensation index at the target moment is predicted according to the first average thermal sensation index and the first water supply temperature. By predicting the second average thermal sensation index at the target moment, the possible thermal comfort state of the personnel at the target moment can be informed in advance, so that corresponding measures can be taken to adjust the indoor environment to maintain the thermal comfort of the human body.

[0013] Further, the first water supply temperature at the target time is optimized according to the second average thermal sensation index and the target average thermal sensation index to obtain the target water supply temperature; at the target time, the operating parameters of the heating equipment are adjusted according to the target water supply temperature by the model predictive control (MPC) controller, thereby adjusting the current water supply temperature of the heating equipment. By continuously predicting the second average thermal sensation index at the target time, determining the target water supply temperature, and adjusting the operating parameters of the heating equipment according to the target water supply temperature, the heating equipment can adjust the water supply temperature in advance according to the change of the external ambient temperature, ensuring that the indoor personnel are in a relatively comfortable thermal environment, and effectively improving the comfort of the indoor environment.

[0014] In one embodiment, predicting the second average thermal sensation index at the target time based on the first average thermal sensation index and the first water supply temperature includes:

[0015] In a current prediction period, sorting the plurality of first average thermal sensation indexes and the plurality of first water supply temperatures in chronological order;

[0016] Dividing the sorted first average thermal sensation indexes and the first water supply temperatures into a plurality of time series data sets based on a sliding window;

[0017] The multiple time series data sets are input into a target neural network model to obtain the second average thermal sensation index, and the target neural network model is constructed based on time series information.

[0018] Beneficial effect: By sorting multiple first average thermal sensation indexes and multiple first water supply temperatures in chronological order within the current prediction period, a time series data structure that can reflect the time-varying law of the first average thermal sensation index and the first water supply temperature is obtained. Through the time series data structure, the specific values ​​and changes of the first average thermal sensation index and the first water supply temperature at different time nodes can be seen, thus laying a foundation for subsequent analysis and prediction.

[0019] The first average thermal sensation index and the first water supply temperature data arranged in chronological order are slid forward according to the set number of sliding steps. Each time a slide is made, a new small data set containing data at multiple time points is intercepted; after multiple slides, the entire time series data structure can be divided into multiple small time series data sets. By dividing multiple small time series data sets by sliding windows, each time series data set reflects the change pattern of the first average thermal sensation index and the first water supply temperature in a specific short period of time, which helps to understand the relationship between the first average thermal sensation index and the first water supply temperature at different stages and their respective change trends in more detail. Moreover, the data intercepted by different windows present a variety of change patterns due to different time periods, corresponding indoor and outdoor environments, and personnel activities, which can enable subsequent models to learn more comprehensive data laws.

[0020] When the divided multiple time series data sets are input into the target neural network model, the target neural network model will learn the rules in the time series data sets through its internal structure and algorithm mechanism. The target neural network model will eventually predict the second average thermal sensation index at the target time based on the current input time series data set and the learned rules, thus providing a reference for knowing the future thermal comfort state of the human body in advance and reasonably regulating heating.

[0021] In one embodiment, the method further comprises:

[0022] calculating a predicted loss based on the second average thermal sensation index and the target average thermal sensation index;

[0023] The parameters of the target neural network model are updated based on the prediction loss to obtain the updated target neural network model.

[0024] Beneficial effect: The prediction loss reflects the degree of deviation between the prediction made by the target neural network model and the ideal situation. The prediction loss is calculated by the second average thermal sensation index and the target average thermal sensation index to know the quality of the prediction result of the target neural network model. After the prediction loss is calculated, the parameters of the target neural network model are adjusted according to the loss value, so that the target neural network model can more accurately predict the average thermal sensation index, thereby providing a more reliable basis for the subsequent control of the heating equipment and ensuring that the indoor environment can be maintained in a state that meets the thermal comfort requirements of the human body.

[0025] In one embodiment, the calculation formula for calculating the predicted loss based on the second average thermal sensation index and the target average thermal sensation index is:

[0026]

[0027] Where L is the loss function; is the second mean thermal sensation index at the i-th time step, PMV target is the target average thermal sensation index; E(t) is the total value of system energy consumption within time t; λ is the energy consumption weight coefficient.

[0028] In one embodiment, obtaining the first water supply temperature at the target time based on the first average thermal sensation index, the target average thermal sensation index and the current water supply temperature of the heating device includes:

[0029] In each of the time series data sets, the current water supply temperature at the current moment is optimized based on minimizing an objective function and combining the first average thermal sensation index and the target average thermal sensation index to obtain a first water supply temperature at the target moment, wherein the objective function is constructed based on a difference between the first average thermal sensation index and the target average thermal sensation index.

[0030] Beneficial effect: By continuously combining the thermal sensation information provided by the first average thermal sensation index and the target average thermal sensation index in each time series data set, as well as the feedback of the objective function, the current water supply temperature at the current moment is gradually optimized until a water supply temperature that minimizes the objective function is found, thereby obtaining the first water supply temperature at the target moment. By simultaneously considering the second average thermal sensation index and the target average thermal sensation index, the changing trend of thermal sensation can be more comprehensively grasped, thereby optimizing the water supply temperature more accurately.

[0031] In one embodiment, the current water supply temperature at the current moment is optimized, and the calculation formula for obtaining the first water supply temperature at the target moment is:

[0032]

[0033] Among them, y(t+k) is the first average thermal sensation index of the kth step, y ref (t+k) is the target average thermal sensation index, u(t+k) is the current water supply temperature at the kth step, N is the prediction time domain length, λ is the weight coefficient for controlling energy consumption; u(t)1 is the first water supply temperature at the target moment.

[0034] In one embodiment, the current water supply temperature in the kth step is greater than or equal to a first preset water supply temperature and less than or equal to a second preset water supply temperature, and the second preset water supply temperature is greater than the first preset water supply temperature;

[0035] The first average thermal sensation index of the kth step is greater than or equal to the first target average thermal sensation index and less than or equal to the second target average thermal sensation index, and the second target average thermal sensation index is greater than the first target average thermal sensation index.

[0036] In one embodiment, the first water supply temperature at the target time is optimized based on the second average thermal sensation index and the target average thermal sensation index, and a calculation formula for obtaining the target water supply temperature is:

[0037]

[0038] Where u(t) is the target water supply temperature at the target time, PMV pred (t) is the second mean thermal sensation index, PMV target is the target average thermal sensation index, and u(t)1 is the first water supply temperature at the target moment.

[0039] In one embodiment, the indoor environment data at least includes air temperature or relative humidity; the calculation formula for obtaining the first average thermal sensation index at the current moment is:

[0040] PMV=(0.303e -0.036M +0.028){MW-3.05×10 -3 [5773-6.99(MW)-Pa]-0.42[(MW)-58.15]-1.7×10 -5 M(5867-Pa)-0.0014M(34-T i )-3.96×10 8 f cl [(T cl +273) 4 -(T mv +273) 4 ]-f cl h c (T cl -T i )}

[0041]

[0042] Where M is metabolic rate; W is external work; T a is the air temperature; p a is the partial pressure of water vapor in air; h c is the convective heat transfer coefficient; T cl is the clothing surface temperature; f cl I is the clothing surface area coefficient; cl is the thermal resistance of clothing; RH is the relative humidity; v is the air velocity.

[0043] On the other hand, the present invention further provides a heating device, comprising: a memory, a processor, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0044] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the control method of the heating equipment as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A schematic flow chart of a method for controlling a heating device according to an embodiment of the present invention;

[0047] Figure 2 A schematic flow chart of a method for controlling a heating device according to another embodiment of the present invention;

[0048] Figure 3 A schematic flow chart of a method for controlling a heating device according to another embodiment of the present invention;

[0049] Figure 4 A schematic flow chart of a method for controlling a heating device according to another embodiment of the present invention;

[0050] Figure 5 A schematic structural diagram of a control device for a heating device according to an embodiment of the present invention;

[0051] Figure 6 This is a schematic structural diagram of a heating device according to another embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] According to an embodiment of the present invention, Figure 1 As shown, on the one hand, a control method for a heating device is provided, comprising the following steps:

[0055] Step S100, obtaining the indoor environment data at the current moment;

[0056] Step S200: based on the indoor environment data at the current moment and in combination with the average thermal sensation index model, obtain a first average thermal sensation index at the current moment;

[0057] Step S300, based on the first average thermal sensation index, the target average thermal sensation index and the current water supply temperature of the heating equipment, obtaining the first water supply temperature at a target time, where the target time is a time after the current time;

[0058] Step S400: predicting a second average thermal sensation index at a target time based on the first average thermal sensation index and the first water supply temperature;

[0059] Step S500, optimizing the first water supply temperature at the target time based on the second average thermal sensation index and the target average thermal sensation index to obtain a target water supply temperature;

[0060] Step S600: at the target time, adjusting the operating parameters of the heating equipment based on the target water supply temperature, the operating parameters at least including the fan speed or compressor output power of the heating equipment.

[0061] In this embodiment, first, the air temperature, average radiation temperature, relative humidity, air flow rate, etc. of the indoor environment can be measured according to multiple integrated indoor environment sensor modules in the room; thereby obtaining the indoor environment data at the current moment. Then, according to the indoor environment data at the current moment and combined with the average thermal sensation index model, the first average thermal sensation index at the current moment is obtained. Further, according to the first average thermal sensation index at the current moment, the target average thermal sensation index and the current water supply temperature of the heating equipment, the first water supply temperature at the moment after the current moment is obtained. Then, according to the first average thermal sensation index and the first water supply temperature, the second average thermal sensation index at the target moment is predicted. By predicting the second average thermal sensation index at the target moment, the possible thermal comfort state of the personnel at the target moment can be informed in advance, so that corresponding measures can be taken to adjust the indoor environment to maintain the thermal comfort of the human body. Among them, the average thermal sensation index (PMV) is an indicator that comprehensively considers the thermal balance and thermal comfort of the human body. PMV takes into account multiple aspects such as environmental factors (such as temperature, humidity, wind speed, radiation temperature) and human factors (such as metabolic rate, clothing thermal resistance).

[0062] Further, according to the second average thermal sensation index and the target average thermal sensation index, the first water supply temperature at the target moment is optimized to obtain the target water supply temperature; at the target moment, the MPC controller adjusts the operating parameters of the heating equipment according to the target water supply temperature. By continuously predicting the second average thermal sensation index at the target moment, determining the target water supply temperature and adjusting the operating parameters of the heating equipment according to the target water supply temperature, the heating equipment can adjust the water supply temperature in advance according to the changes in the external ambient temperature, ensuring that the indoor personnel are in a relatively comfortable thermal environment, and effectively improving the comfort of the indoor environment. Among them, the operating parameters of the heating equipment at least include the fan speed or compressor output power of the heating equipment. By adjusting the fan speed of the heating equipment, the heat exchange with the outdoor air can be accelerated; by adjusting the output power of the compressor, the heating or cooling capacity of the heating equipment can be improved, thereby adjusting the indoor temperature.

[0063] In step S200, the first average thermal sensation index is calculated by combining indoor environmental data and human factors. The indoor environmental data includes air temperature or relative humidity, etc.; the human factors include metabolic rate, clothing surface area coefficient, clothing surface temperature and clothing thermal resistance, etc. Human factors such as metabolic rate can be set to light exercise, and the thermal resistance of clothing changes with indoor temperature. Human factors can be set to quantitative values ​​for direct use; the calculation formula for the first average thermal sensation index at the current moment is:

[0064] PMV=(0.303e -0.036M +0.028){MW-3.05×10 -3[5773-6.99(MW)-Pa]-0.42[(MW)-58.15]-1.7×10 -5 M(5867-Pa)-0.0014M(34-T i )-3.96×10 9 f cl [(T cl +273) 4 -(T mv +273) 4 ]-f cl h c (T cl -T i )}

[0065]

[0066] Where M is metabolic rate; W is external work; T a is the air temperature; p a is the partial pressure of water vapor in air; h c is the convective heat transfer coefficient; T cl is the clothing surface temperature; f cl I is the clothing surface area coefficient; cl is the thermal resistance of clothing; RH is the relative humidity; v is the air velocity.

[0067] like Figure 2 As shown, in one embodiment, step S400 includes the following steps:

[0068] Step S410: In the current prediction period, a plurality of first average thermal sensation indexes and a plurality of first water supply temperatures are sorted in chronological order.

[0069] In step S410, a time series data structure that can reflect the time-varying law of the first average thermal sensation index and the first water supply temperature is obtained by sorting the first average thermal sensation index and the first water supply temperature in the current prediction period in chronological order. The time series data structure can be used to see the specific values ​​and changes of the first average thermal sensation index and the first water supply temperature at different time nodes, thereby laying a foundation for subsequent analysis and prediction.

[0070] Step S420: dividing the sorted plurality of first average thermal sensation indices and the plurality of first water supply temperatures into a plurality of time series data sets based on a sliding window.

[0071] In step S420, the first average thermal sensation index and the first water supply temperature data arranged in chronological order are slid forward according to the set number of sliding steps. Each time a slide is performed, a new small data set containing data at multiple time points is intercepted; after multiple slides, the entire time series data structure can be divided into multiple small time series data sets. By dividing multiple small time series data sets by sliding windows, each time series data set reflects the change pattern of the first average thermal sensation index and the first water supply temperature in a specific short period of time, which helps to understand the relationship between the first average thermal sensation index and the first water supply temperature at different stages and their respective change trends in more detail. Moreover, the data intercepted by different windows present various change patterns due to different time periods, corresponding indoor and outdoor environments, and personnel activities, which can enable subsequent models to learn more comprehensive data rules. For example, if the current prediction period is within one hour in the future, the sliding window starts from the starting position of the data, frames the relevant data within 60 minutes each time, and then slides forward according to a step size of 5 minutes, thereby obtaining 12 time series data sets. It is understandable that the step length can be selected according to actual usage requirements, and can also be 6 minutes, 7 minutes, 8 minutes, 9 minutes, 10 minutes, etc., without any specific limitation.

[0072] Step S430: Input multiple time series data sets into the target neural network model to obtain a second average thermal sensation index, and the target neural network model is constructed based on the time series information.

[0073] In step S430, after the divided multiple time series data sets are input into the target neural network model, the target neural network model will learn the rules in the time series data sets through the internal structure and algorithm mechanism, and capture the dependency and nonlinear characteristics of the time series data sets. By continuously learning the dependency and nonlinear characteristics of the time series data sets, the model eventually predicts the future average thermal sensation index based on the currently input time series data sets and the learned rules, and obtains the second average thermal sensation index, thereby providing a reference for knowing the future thermal comfort state of the human body in advance and reasonably regulating heating.

[0074] Among them, the target neural network model is built based on time series information. A neural network model capable of processing time series data can be selected, such as the long short-term memory network (LSTM). LSTM has excellent long-term dependency modeling capabilities, nonlinear processing capabilities, multi-dimensional data fusion capabilities, and self-learning and model updating capabilities in prediction tasks. By capturing the time dependency of environmental factors such as temperature and humidity, LSTM is suitable for the refined regulation of heating equipment.

[0075] Furthermore, the state equation of LSTM is as follows:

[0076]

[0077] Among them, f t (l) is the forget gate activation vector at the current moment; is the input gate activation vector at the current moment; is the output gate activation vector at the current moment; is the candidate unit state vector at the current moment; is the unit state vector at the current moment; is the output vector at the current moment, i.e. the input of the next layer W is the weight matrix; b is the bias vector; (l) is the parameter of the corresponding layer; σ represents the sigmoid function; * represents the Hadamard product; is the prediction result of the output layer (l), i.e., the second average thermal sensation index; W y is the weight of the output layer; b y is the bias of the output layer.

[0078] Furthermore, in order to prevent gradient vanishing or gradient exploding during training and to speed up training, a residual neural network is introduced into the target neural network model to keep the gradient stable.

[0079] In one embodiment, step S500 includes: in each time series data set, based on minimizing the objective function and combining the first average thermal sensation index and the target average thermal sensation index, optimizing the current water supply temperature at the current moment to obtain the first water supply temperature at the target moment, and the objective function is constructed based on the difference between the first average thermal sensation index and the target average thermal sensation index.

[0080] In this embodiment, by continuously combining the thermal sensation information provided by the first average thermal sensation index and the target average thermal sensation index in each time series data set, as well as the feedback of the objective function, the current water supply temperature at the current moment is gradually optimized until a water supply temperature that minimizes the objective function is found, thereby obtaining the first water supply temperature at the target moment. By simultaneously considering the second average thermal sensation index and the target average thermal sensation index, the changing trend of thermal sensation can be more comprehensively grasped, thereby optimizing the water supply temperature more accurately. Among them, the objective function is constructed based on the difference between the first average thermal sensation index and the target average thermal sensation index, reflecting the deviation between the target average thermal sensation index currently expected to be achieved and the first average thermal sensation index.

[0081] Furthermore, the current water supply temperature at the current moment is optimized, and the calculation formula for obtaining the first water supply temperature at the target moment is:

[0082]

[0083] Among them, y(t+k) is the first average thermal sensation index of the kth step, y ref (t+k) is the target average thermal sensation index, u(t+k) is the current water supply temperature at the kth step, N is the prediction time domain length, λ is the weight coefficient for controlling energy consumption; u(t)1 is the first water supply temperature at the target moment.

[0084] Further, the current water supply temperature in step k is greater than or equal to the first preset water supply temperature and less than or equal to the second preset water supply temperature, and the second preset water supply temperature is greater than the first preset water supply temperature;

[0085] The first average thermal sensation index of the kth step is greater than or equal to the first target average thermal sensation index and less than or equal to the second target average thermal sensation index, and the second target average thermal sensation index is greater than the first target average thermal sensation index. The expression is:

[0086]

[0087] Among them, u min is the first preset water supply temperature, i.e., the lower limit of the water supply temperature; u max is the second preset water supply temperature, i.e., the upper limit of the water supply temperature; min is the average thermal sensation index of the first target; max is the second target average thermal sensation index. Specifically, u min It can be 20℃, u max Can be 60℃, y min Can be -0.5, y max It can be 0.5, which can be set according to actual usage requirements without any specific restrictions.

[0088] Furthermore, the calculation formula of step S500 is:

[0089]

[0090] Where u(t) is the target water supply temperature at the target time, PMV pred (t) is the second mean thermal sensation index, PMV target is the target average thermal sensation index, and u(t)1 is the first water supply temperature at the target moment.

[0091] like Figure 3 As shown, in one embodiment, the method further includes the following steps:

[0092] Step S510: Calculate the predicted loss based on the second average thermal sensation index and the target average thermal sensation index.

[0093] In step S510, the prediction loss reflects the degree of deviation between the prediction made by the target neural network model and the ideal situation. The prediction loss is calculated by the second average thermal sensation index and the target average thermal sensation index to know the quality of the prediction result of the target neural network model. For example, if the loss value is smaller, it means that the model's prediction of the thermal sensation index is more accurate and more in line with the actual human thermal comfort state; while a larger loss value indicates that the model needs to be further optimized and improved to better reflect the actual thermal sensation situation. Calibrate or retrain according to the error between the second average thermal sensation index and the target average thermal sensation index to improve the accuracy of the target neural network model. As the system runs, new real-time data will continuously update feedback, provide new input for the target neural network model, and adjust the prediction results according to the real-time data to make the predicted results closer to the target average thermal sensation index.

[0094] Among them, the target average thermal sensation index is the PMV value corresponding to the desired thermal comfort state of the human body. By comparing the second average thermal sensation index and the target average thermal sensation index, it can be determined how the indoor environment needs to be adjusted to achieve the ideal thermal comfort state.

[0095] Furthermore, based on the second average thermal sensation index and the actual average thermal sensation index at the target time, the calculation formula for calculating the predicted loss is:

[0096]

[0097] Where L is the loss function; is the second mean thermal sensation index at the i-th time step, PMV target is the target average thermal sensation index; E(t) is the total value of system energy consumption in time t; λ is the energy consumption weight coefficient. E(t) can be directly obtained from the electric meter connected to the heating equipment.

[0098] Step S520: Update the parameters of the target neural network model based on the prediction loss to obtain an updated target neural network model.

[0099] In step S520, after the predicted loss is calculated, the target neural network model parameters are adjusted according to the loss value, so that the target neural network model can more accurately predict the average thermal sensation index, thereby providing a more reliable basis for subsequent control of the heating equipment and ensuring that the indoor environment can be maintained in a state that meets the thermal comfort requirements of the human body.

[0100] Furthermore, the parameters of the target neural network model are optimized and updated based on the back-propagation algorithm.

[0101] Specifically, the gradient of the loss function to each parameter in the target neural network model is calculated based on the predicted loss, so that the contribution of each parameter to the loss function and how to adjust the parameter to reduce the value of the loss function can be understood. For example, if the gradient of a parameter is positive, increasing the parameter will cause the loss function to increase, so the parameter is reduced during the update. After each iterative update, the target neural network model will re-predict and calculate a new predicted loss value. As the number of iterations increases, the parameters of the target neural network model will gradually adjust to a state that minimizes the predicted loss value, thereby improving the prediction accuracy of the target neural network model for the average thermal sensation index.

[0102] In one of the embodiments, the target average thermal sensation index includes a first target average thermal sensation index and a second target average thermal sensation index; when the first average thermal sensation index is less than the first target average thermal sensation index, the operating parameters of the heating equipment are adjusted to increase the first average thermal sensation index; when the first average thermal sensation index is greater than the second target average thermal sensation index, the operating parameters of the heating equipment are adjusted to reduce the first average thermal sensation index; when the first average thermal sensation index is greater than the first target average thermal sensation index and less than the second target average thermal sensation index, based on the predicted environmental change trend and the target average thermal sensation index, the operating parameters of the heating equipment are dynamically adjusted to maintain the first average thermal sensation index between the first target average thermal sensation index and the second target average thermal sensation index.

[0103] In this embodiment, when the first average thermal sensation index is less than the first target average thermal sensation index, it indicates that the human body feels cold. In order to improve the thermal comfort of the indoor environment, it is necessary to increase the heat supply. Therefore, the current water supply temperature is increased by adjusting the operating parameters of the heating equipment, thereby increasing the indoor temperature to increase the first average thermal sensation index and bring the human body's thermal sensation closer to the comfortable range. For example, the first target average thermal sensation index is set to -0.5. When the first average thermal sensation index is less than -0.5, the MPC controller will automatically adjust the operating parameters of the heating equipment, including increasing the fan speed, accelerating the heat exchange with the outdoor hot air, and absorbing the heat in the outdoor air; further increasing the compressor output power, improving the heating capacity of the heating equipment, and ensuring that the heating equipment absorbs more heat in a short time; thereby increasing the water supply temperature and the air outlet temperature of the heating equipment, accelerating the rise of the indoor temperature, and then increasing the first average thermal sensation index.

[0104] When the first average thermal sensation index is greater than the second target average thermal sensation index, it indicates that the human body feels hot. At this time, it is necessary to reduce the indoor heat, so the current water supply temperature is lowered by adjusting the operating parameters of the heating equipment, thereby lowering the indoor temperature and reducing the first average thermal sensation index. For example, the second target average thermal sensation index is set to 0.5. When the first average thermal sensation index is greater than 0.5, the MPC controller automatically adjusts the operating parameters of the heating equipment, increases the fan speed, accelerates the heat exchange with the outdoor hot air, and releases the heat in the indoor air; further increases the compressor output power, improves the cooling capacity of the heating equipment, and ensures that the heating equipment releases more heat in a short time; thereby reducing the water supply temperature and the air outlet temperature of the heating equipment, accelerating the drop in indoor temperature, and then reducing the first average thermal sensation index.

[0105] When the first average thermal sensation index is greater than the first target average thermal sensation index and less than the second target average thermal sensation index, the indoor environment is in a relatively comfortable state; due to the dynamic changes in environmental factors, the MPC controller will dynamically adjust the operating parameters of the heating equipment according to the predicted environmental change trend and the target average thermal sensation index, so that the first average thermal sensation index is maintained between the first target average thermal sensation index and the second target average thermal sensation index, reducing the fluctuation of the first average thermal sensation index. By continuously adjusting the operating parameters of the heating equipment, the first average thermal sensation index is adjusted to provide indoor personnel with a relatively stable and comfortable thermal environment, prevent drastic fluctuations in indoor temperature, and improve the user's comfort experience.

[0106] like Figure 4 As shown, in one embodiment, the method further includes:

[0107] Step 110: Acquire environmental data and standard environmental data, where the environmental data includes indoor environmental data and outdoor environmental data, and the standard environmental data is environmental data collected by the Meteorological Bureau;

[0108] Step 120: compare the outdoor environment data at the current moment with the standard environment data at the corresponding moment. If the comparison error is within the target error range, the outdoor environment data at the current moment is used as a test data set.

[0109] Step 130: predict the environmental change trend based on the test data set and the indoor environmental data to obtain a predicted environmental change trend.

[0110] In this embodiment, by acquiring the current environmental data and the standard environmental data, the collected outdoor environmental data at the current moment is compared with the environmental data at the corresponding moment collected by the meteorological bureau; when the error is less than the target error, the outdoor environmental data at the current moment is used as a test data set, and the environmental change trend is predicted by the test data set, which can improve the accuracy of the environmental change trend prediction, thereby improving the accuracy of the subsequent dynamic adjustment of the operating parameters of the heating equipment. Among them, the target error can be 10%, 15%, 20%, 25%, etc., which can be determined according to actual usage requirements.

[0111] The environmental change trend is further predicted based on the test data set and the indoor environmental data to obtain the predicted environmental change trend. Among them, the environmental trend can be predicted in combination with the autoregressive moving average model or the neural network model. For example, the test data set and the indoor environmental data are input into the LSTM model, and the LSTM model can automatically extract the patterns and regularities in the data. For example, the LSTM model can learn the relationship between outdoor temperature changes, indoor personnel activities and indoor temperature changes, and predict the future trend of indoor environmental changes based on the learned relationship. By training a large amount of historical data, the LSTM model can make multi-step predictions on future environmental factors and show the possible trend of environmental changes in the future. By predicting the trend of environmental changes, it is possible to know in advance whether the indoor environment will develop in a more comfortable or uncomfortable direction in the future, so that the operating parameters of the heating equipment can be adjusted in advance to maintain indoor thermal comfort.

[0112] According to an embodiment of the present invention, Figure 5 As shown, on the other hand, a control device for a heating device is also provided, comprising:

[0113] The acquisition module 100 is used to acquire the indoor environment data at the current moment.

[0114] The first calculation module 200 is used to obtain the first average thermal sensation index at the current moment based on the indoor environment data at the current moment and in combination with the average thermal sensation index model; the indoor environment data at least includes air temperature or relative humidity; the calculation formula for obtaining the first average thermal sensation index at the current moment is:

[0115] PMV=(0.303e -0.036M +0.028){MW-3.05×10 -3 [5773-6.99(MW)-Pa]-0.42[(MW)-58.15]-1.7×10 -5 M(5867-Pa)-0.0014M(34-T i )-3.96×10 8 f cl[(T cl +273) 4 -(T mv +273) 4 ]-f cl h c (T cl -T i )}

[0116]

[0117] Where M is metabolic rate; W is external work; T a is the air temperature; p a is the partial pressure of water vapor in air; h c is the convective heat transfer coefficient; T cl is the clothing surface temperature; f cl I is the clothing surface area coefficient; cl is the thermal resistance of clothing; RH is the relative humidity; v is the air velocity.

[0118] The second calculation module 300 is used to obtain a first water supply temperature at a target time based on the first average thermal sensation index, the target average thermal sensation index and the current water supply temperature of the heating equipment, where the target time is a time after the current time.

[0119] The prediction module 400 is used to predict the second average thermal sensation index at a target time based on the first average thermal sensation index and the first water supply temperature.

[0120] The optimization module 500 is used to optimize the first water supply temperature at the target time based on the second average thermal sensation index and the target average thermal sensation index to obtain the target water supply temperature; the calculation formula is:

[0121]

[0122] Where u(t) is the target water supply temperature at the target time, PMV pred (t) is the second mean thermal sensation index, PMV target is the target average thermal sensation index, and u(t)1 is the first water supply temperature at the target moment.

[0123] The control module 600 is used to adjust the operating parameters of the heating equipment based on the target water supply temperature at the target time, and the operating parameters at least include the fan speed or compressor output power of the heating equipment.

[0124] In one embodiment, the prediction module 400 includes:

[0125] A sorting unit, for sorting the plurality of first average thermal sensation indices and the plurality of first water supply temperatures in chronological order in a current prediction period;

[0126] a dividing unit, configured to divide the sorted plurality of first average thermal sensation indices and the plurality of first water supply temperatures into a plurality of time series data sets based on a sliding window;

[0127] The first prediction unit is used to input multiple time series data sets into a target neural network model to obtain a second average thermal sensation index, and the target neural network model is constructed based on time series information.

[0128] In one embodiment, the optimization module 500 includes:

[0129] The first calculation unit is used to calculate the predicted loss based on the second average thermal sensation index and the target average thermal sensation index, and the calculation formula is:

[0130]

[0131] Where L is the loss function; is the second mean thermal sensation index at the i-th time step, PMV target is the target average thermal sensation index; E(t) is the total value of system energy consumption within time t; λ is the energy consumption weight coefficient;

[0132] The updating unit is used to update the parameters of the target neural network model based on the prediction loss to obtain an updated target neural network model.

[0133] In one embodiment, the optimization module 500 further includes:

[0134] The optimization unit is used to optimize the current water supply temperature at the current moment in each time series data set based on minimizing the objective function and combining the first average thermal sensation index and the target average thermal sensation index to obtain the first water supply temperature at the target moment, wherein the objective function is constructed based on the difference between the first average thermal sensation index and the target average thermal sensation index; the calculation formula for obtaining the first water supply temperature at the target moment is:

[0135]

[0136] Among them, y(t+k) is the first average thermal sensation index of the kth step, y ref(t+k) is the target average thermal sensation index, u(t+k) is the current water supply temperature at the kth step, N is the prediction time domain length, λ is the weight coefficient for controlling energy consumption; u(t) is the target water supply temperature at the target moment. The current water supply temperature at the kth step is greater than or equal to the first preset water supply temperature and less than or equal to the second preset water supply temperature, and the second preset water supply temperature is greater than the first preset water supply temperature; the first average thermal sensation index at the kth step is greater than or equal to the first target average thermal sensation index and less than or equal to the second target average thermal sensation index, and the second target average thermal sensation index is greater than the first target average thermal sensation index.

[0137] Figure 6 A schematic structural diagram of an embodiment of a heating device provided by an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the heating device.

[0138] like Figure 6 As shown, the heating device may include: a processor (processor) 602 , a communication interface (Communications Interface) 604 , a memory (memory) 606 , and a communication bus 608 .

[0139] The processor 602, the communication interface 604, and the memory 606 communicate with each other via a communication bus 608. The communication interface 604 is used to communicate with other devices such as a client or other server network elements. The processor 602 is used to execute a program 610, which can specifically execute the relevant steps in the above-mentioned control method embodiment for a heating device.

[0140] Specifically, the program 610 may include program code including computer executable instructions.

[0141] The processor 602 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention. The one or more processors included in the heating device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0142] The memory 606 is used to store the program 610. The memory 606 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0143] The program 610 may be specifically called by the processor 602 to enable the heating device to execute the relevant steps in the above-mentioned control method embodiment for the heating device.

[0144] It can be understood by those skilled in the art that Figure 6 The structure shown is only for illustration and does not limit the structure of the above-mentioned device. Figure 6 More or fewer components as shown, or with Figure 6 Different configurations are shown.

[0145] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0146] In the specific contents of the above-mentioned specific implementation methods, the various technical features can be combined in any non-contradictory manner. In order to make the description concise, not all possible combinations of the above-mentioned technical features are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0147] The specific contents of the above specific embodiments only express several embodiments of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be based on the attached claims.

Claims

1. A method for controlling a heating device, characterized in that: The method comprises: Get the current indoor environment data; Based on the indoor environment data at the current moment and in combination with the average thermal sensation index model, a first average thermal sensation index at the current moment is obtained; Based on the first average thermal sensation index, the target average thermal sensation index and the current water supply temperature of the heating device, obtaining a first water supply temperature at a target time, wherein the target time is a time after the current time; predicting a second average thermal sensation index at a target time based on the first average thermal sensation index and the first water supply temperature; Optimizing the first water supply temperature at the target time based on the second average thermal sensation index and the target average thermal sensation index to obtain a target water supply temperature; At the target time, the operating parameters of the heating equipment are adjusted based on the target water supply temperature, and the operating parameters at least include the fan speed or compressor output power of the heating equipment.

2. The control method of the heating equipment according to claim 1, characterized in that: The step of predicting the second average thermal sensation index at a target time based on the first average thermal sensation index and the first water supply temperature includes: In a current prediction period, sorting the plurality of first average thermal sensation indexes and the plurality of first water supply temperatures in chronological order; Dividing the sorted first average thermal sensation indexes and the first water supply temperatures into a plurality of time series data sets based on a sliding window; The multiple time series data sets are input into a target neural network model to obtain the second average thermal sensation index, and the target neural network model is constructed based on time series information.

3. The control method of the heating equipment according to claim 2, characterized in that: The method further comprises: calculating a predicted loss based on the second average thermal sensation index and the target average thermal sensation index; The parameters of the target neural network model are updated based on the prediction loss to obtain the updated target neural network model.

4. The control method of the heating equipment according to claim 3, characterized in that: The calculation formula for calculating the predicted loss based on the second average thermal sensation index and the target average thermal sensation index is: Where L is the loss function; is the second mean thermal sensation index at the i-th time step, PMV target is the target average thermal sensation index; E(t) is the total value of system energy consumption within time t; λ is the energy consumption weight coefficient.

5. The control method of the heating equipment according to claim 2, characterized in that: The obtaining, based on the first average thermal sensation index, the target average thermal sensation index and the current water supply temperature of the heating device, the first water supply temperature at the target time includes: In each of the time series data sets, the current water supply temperature at the current moment is optimized based on minimizing an objective function and combining the first average thermal sensation index and the target average thermal sensation index to obtain a first water supply temperature at the target moment, wherein the objective function is constructed based on a difference between the first average thermal sensation index and the target average thermal sensation index.

6. The control method of the heating equipment according to claim 5, characterized in that: The current water supply temperature at the current moment is optimized, and the calculation formula for the first water supply temperature at the target moment is obtained as follows: Among them, y(t+k) is the first average thermal sensation index of the kth step, y ref (t+k) is the target average thermal sensation index, u(t+k) is the current water supply temperature at the kth step, N is the prediction time domain length, λ is the weight coefficient for controlling energy consumption; u(t)1 is the first water supply temperature at the target moment.

7. The control method of the heating equipment according to claim 6, characterized in that: The current water supply temperature in the kth step is greater than or equal to the first preset water supply temperature and less than or equal to the second preset water supply temperature, and the second preset water supply temperature is greater than the first preset water supply temperature; The first average thermal sensation index of the kth step is greater than or equal to the first target average thermal sensation index and less than or equal to the second target average thermal sensation index, and the second target average thermal sensation index is greater than the first target average thermal sensation index.

8. The control method of heating equipment according to claim 1, characterized in that: The first water supply temperature at the target time is optimized based on the second average thermal sensation index and the target average thermal sensation index to obtain a calculation formula for the target water supply temperature: Where u(t) is the target water supply temperature at the target time, PMV pred (t) is the second mean thermal sensation index, PMV target is the target average thermal sensation index, and u(t)1 is the first water supply temperature at the target moment.

9. The control method of heating equipment according to claim 1, characterized in that: The indoor environment data at least includes air temperature or relative humidity; the calculation formula for obtaining the first average thermal sensation index at the current moment is: Where M is metabolic rate; W is external work; T a is the air temperature; p a is the partial pressure of water vapor in air; h c is the convective heat transfer coefficient; T cl is the clothing surface temperature; f cl I is the clothing surface area coefficient; cl is the thermal resistance of clothing; RH is the relative humidity; v is the air velocity.

10. A heating device, characterized in that: include: A memory, a processor, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the control method of the heating equipment according to any one of claims 1 to 9.

Images