A method and system for controlling the indoor thermal environment of a retirement building

Abstract

The present application relates to the technical field of building environment control, in particular to a kind of control method and system of indoor thermal environment of old-age building, the present application is first used for the influencing factor of indoor temperature prediction, then the value of influencing factor is collected, then the value of influencing factor is pretreated, in the pretreatment operation process, the numerical value of influencing factor is pretreated by using correlation coefficient, so that the data input can reflect the importance degree of the data involved in calculation when using deep learning model to predict, improve the accuracy of prediction, and then improve the accuracy of thermal environment control.

Description

Technical Field

[0001] This invention relates to the field of building environment control technology, and in particular to a method and system for controlling the indoor thermal environment of elderly care buildings. Background Technology

[0002] Energy is a crucial material foundation for human progress and development, a fundamental condition for human survival, and one of the most influential issues in the world today. With societal progress and rising living standards, people have increasingly higher demands for building comfort, especially given the growing concern for the living needs of the elderly. This has led to increased loads on equipment used to maintain indoor thermal comfort, and consequently, increased unit loads on various buildings. Heating, ventilation, and air conditioning (HVAC) systems are essential for regulating indoor environments, and the requirement for high-precision control presents a significant challenge.

[0003] Existing technologies include solutions for controlling air conditioning to achieve indoor thermal environment control. For example, Chinese invention patent (CN110671798A) discloses an indoor thermal environment control system based on artificial intelligence technology to predict thermal sensation. This system involves: Step 1. Setting an initial value for the user's comfortable skin temperature based on recommended comfort temperature values. An infrared thermal imaging camera captures an infrared image of the user, and the skin temperature is identified based on the thermal image. Step 2. If the user inputs thermal sensations such as "too cold" or "too hot" through the HMI, the user's skin temperature comfort range is updated accordingly. However, the above solution suffers from relatively low control accuracy when controlling the indoor thermal environment. Summary of the Invention

[0004] In view of this, the present invention proposes a method and system for controlling the indoor thermal environment of elderly care buildings, which is used to improve the accuracy of indoor thermal environment control.

[0005] To achieve the above objectives, a method for controlling the indoor thermal environment of elderly care buildings is provided, the method comprising:

[0006] S1: Obtain the influencing factors used for indoor temperature prediction;

[0007] S2: Collect the values ​​of the influencing factors used for indoor temperature prediction;

[0008] S3: Perform a preprocessing operation on the values ​​of the influencing factors used for indoor temperature prediction to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction.

[0009] S3 specifically involves: performing a correlation analysis on the influencing factors used for indoor temperature prediction, and then performing a preprocessing operation on the influencing factors used for indoor temperature prediction based on the magnitude of the correlation coefficient to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction.

[0010] S4: Develop a model for predicting indoor temperature;

[0011] S5: Train the model for predicting indoor temperature;

[0012] S6: Input the preprocessed values ​​of the influencing factors used for indoor temperature prediction into the indoor temperature prediction model to obtain the indoor temperature prediction result;

[0013] S7: Control the indoor thermal environment based on the indoor temperature prediction results.

[0014] Preferably, the correlation analysis of the influencing factors used for indoor temperature prediction specifically involves:

[0015] The indoor temperature, outdoor temperature, outdoor relative humidity, outdoor wind speed, and solar radiation values ​​were obtained. Then, the correlation coefficients between the outdoor temperature, outdoor relative humidity, outdoor wind speed, and solar radiation values ​​and the indoor temperature were calculated using the product difference method.

[0016] Preferably, the preprocessing operation of the influencing factors used for indoor temperature prediction based on the correlation coefficient specifically includes:

[0017] Sa: Normalize the values ​​of the influencing factors used for indoor temperature prediction to obtain the normalized values ​​of the influencing factors used for indoor temperature prediction;

[0018] Sb: The correlation coefficient between the values ​​of the influencing factors used for indoor temperature prediction and the indoor temperature value is normalized to obtain the normalized correlation coefficient value;

[0019] Sc: Multiply the normalized values ​​of the influencing factors used for indoor temperature prediction by the corresponding normalized correlation coefficient values ​​to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction.

[0020] Preferably, in step S1, the influencing factors obtained for indoor temperature prediction include: outdoor temperature, outdoor relative humidity, outdoor wind speed, and solar radiation.

[0021] Preferably, in step S2, the values ​​of the influencing factors used for indoor temperature prediction are obtained; the collected values ​​are the values ​​of the influencing factors for a period of time before the prediction time; the period of time is one of 1 minute, 5 minutes, 10 minutes, and 15 minutes.

[0022] Preferably, the formula for calculating the correlation coefficient r using the product-moment method is as follows:

[0023] ;

[0024] In the formula, x and y represent the values ​​of the influencing factors and the indoor temperature, respectively. and The center point is the influencing factors and the indoor temperature value, and n is the number of samples involved in the calculation.

[0025] Preferably, the BP neural network model includes an input layer, a hidden layer, and an output layer, wherein the input layer has 4 nodes; the output layer has 1 node; and the formula for calculating the number of nodes h in the hidden layer is:

[0026] ;

[0027] In the formula, m and n are the number of nodes in the input layer and the output layer, respectively, and a is the adjustment coefficient.

[0028] Preferably, the transfer function of the BP neural network model uses the sigmoid function, and its formula is expressed as:

[0029] ;

[0030] Where K represents the input data.

[0031] Preferably, the BP neural network model is trained 50,000 times.

[0032] According to another aspect of the present invention, a control system for the indoor thermal environment of a senior care building is provided, the system employing the above-described method for controlling the indoor thermal environment of a senior care building, the system comprising:

[0033] The influencing factor acquisition module is used to acquire the influencing factors for indoor temperature prediction.

[0034] The data acquisition module is used to collect the values ​​of the influencing factors used for indoor temperature prediction;

[0035] The preprocessing module is used to perform preprocessing operations on the influencing factors used for indoor temperature prediction to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction.

[0036] The model building module is used to build models for predicting indoor temperatures.

[0037] The model training module is used to train the model for predicting indoor temperature.

[0038] The prediction module is used to input the preprocessed values ​​of influencing factors for indoor temperature prediction into the indoor temperature prediction model to obtain the indoor temperature prediction result.

[0039] The thermal environment control module is used to control the indoor thermal environment based on the indoor temperature prediction results.

[0040] The advantages and beneficial effects of this invention are as follows:

[0041] This invention first obtains the influencing factors used for indoor temperature prediction, then collects the values ​​of these influencing factors, and then preprocesses the values ​​of these influencing factors. During the preprocessing process, the correlation coefficient is used to preprocess the values ​​of the influencing factors. This allows the input data to reflect the importance of the data involved in the calculation when using a deep learning model for prediction, thereby improving the accuracy of the prediction and thus improving the accuracy of thermal environment control. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of this invention or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 A flowchart of a method for controlling the indoor thermal environment of an elderly care building, provided as an embodiment of the present invention;

[0044] Figure 2 A flowchart for preprocessing the influencing factors used for indoor temperature prediction based on the correlation coefficient magnitude, provided in an embodiment of the present invention;

[0045] Figure 3 A structural diagram of the BP neural network model provided in an embodiment of the present invention;

[0046] Figure 4 This is a structural diagram of a control system for the indoor thermal environment of an elderly care building, provided as an embodiment of the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] Indoor thermal environment refers to the thermodynamic state of an indoor space, including parameters such as temperature, humidity, air velocity, and thermal radiation. These factors collectively affect human senses and determine the thermal comfort of residents. The quality of the indoor thermal environment is influenced by various factors, including external climate conditions, building design and materials, indoor heat sources (such as electrical appliances and human bodies), and the configuration of the ventilation system. Temperature is a critical factor affecting the indoor thermal environment, directly related to energy consumption and the health of residents. Both excessively high and low temperatures can cause discomfort, while appropriate humidity can reduce the survival rate of viruses and the spread of allergens. In this embodiment, a method for controlling the indoor thermal environment of elderly care buildings is proposed to achieve dynamic and accurate adjustment of indoor temperature.

[0049] As attached Figure 1 As shown, a method for controlling the indoor thermal environment of a senior care building includes the following steps:

[0050] S1: Obtain the influencing factors used for indoor temperature prediction;

[0051] The actual heat load of a building includes internal and external disturbances. External disturbances mainly include heat transferred from the exterior building envelope, solar radiation heat obtained from exterior glass skylights and exterior curtain walls, and air heat passing through gaps in building doors and windows. The heat affecting this part is mainly related to outdoor temperature, relative humidity, wind speed, solar radiation, heat dissipation area, and the number of gaps. Internal disturbances mainly refer to the number of people and heat loss during the use of lighting and electrical equipment.

[0052] In the field of building indoor temperature prediction, the influencing factors of internal disturbances are difficult to quantify. Therefore, external disturbances are generally considered as influencing factors to achieve thermal control of the indoor environment.

[0053] In this step, the influencing factors obtained for indoor temperature prediction include: outdoor temperature, outdoor relative humidity, outdoor wind speed, and solar radiation.

[0054] S2: Collect the values ​​of the influencing factors used for indoor temperature prediction;

[0055] In this step, a small weather instrument is used to obtain the values ​​of the influencing factors used for indoor temperature prediction;

[0056] It is worth emphasizing that the collected values ​​are the values ​​of influencing factors for a period of time before the prediction time; the period of time can be 1 minute, 5 minutes, 10 minutes, or 15 minutes; in order to improve the accuracy of the prediction, the values ​​of the influencing factors in this step are selected from the period that is relatively close to the prediction time.

[0057] S3: Perform a preprocessing operation on the values ​​of the influencing factors used for indoor temperature prediction to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction.

[0058] In existing technologies, influencing factors are generally directly input into the prediction model to obtain the prediction results; this results in low prediction accuracy. This embodiment, based on the existing technical solution, performs correlation analysis on the influencing factors used for indoor temperature prediction, and then performs preprocessing operations on the influencing factors used for indoor temperature prediction according to the correlation coefficient.

[0059] Specifically, the correlation analysis of the influencing factors used for indoor temperature prediction involves:

[0060] Obtain indoor temperature, outdoor temperature, outdoor relative humidity, outdoor wind speed, and solar radiation values. Then, use the product-difference method to calculate the correlation coefficients between the outdoor temperature, outdoor relative humidity, outdoor wind speed, and solar radiation values ​​and the indoor temperature value.

[0061] The formula for calculating the correlation coefficient r using the product-moment method is as follows:

[0062] ;

[0063] In the formula, x and y represent the values ​​of the influencing factors and the indoor temperature, respectively. and The center point of the influencing factors and the indoor temperature value is n, where n is the number of samples involved in the calculation.

[0064] In this embodiment, the correlation coefficients r1, r2, r3, and r4 between the outdoor temperature value, outdoor relative humidity value, outdoor wind speed value, solar radiation value, and indoor temperature value are 0.983, 0.891, 0.704, and 0.126, respectively.

[0065] As attached Figure 2 As shown, the preprocessing operation for the influencing factors used in indoor temperature prediction based on the correlation coefficient is specifically as follows:

[0066] Sa: Normalize the values ​​of the influencing factors used for indoor temperature prediction to obtain the normalized values ​​of the influencing factors used for indoor temperature prediction;

[0067] Among them, the values ​​of the influencing factors used for indoor temperature prediction are normalized using the maximum-minimum normalization method;

[0068] Sb: The correlation coefficient between the values ​​of the influencing factors used for indoor temperature prediction and the indoor temperature value is normalized to obtain the normalized correlation coefficient value;

[0069] The correlation coefficients between the outdoor temperature, outdoor relative humidity, outdoor wind speed, and solar radiation values ​​and the indoor temperature were also normalized using the minimum-maximum normalization method, resulting in the normalized correlation coefficient value r. c1 r c2 r c3 r c4 ;

[0070] Sc: Multiply the normalized values ​​of the influencing factors used for indoor temperature prediction by the corresponding normalized correlation coefficient values ​​to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction;

[0071] In this embodiment, by using correlation coefficients to preprocess the values ​​of influencing factors, the input data can reflect the importance of the data involved in the calculation when using a deep learning model for prediction, thus improving the accuracy of the prediction.

[0072] S4: Develop a model for predicting indoor temperature;

[0073] Neural networks utilize the principles of the human brain, where neurons control the stimuli and information received from the outside world. Research shows that the human brain contains billions of different neurons, each closely connected to thousands of other neurons, forming the neural network of the human brain. When the brain receives external stimuli, neurons transmit and accumulate information according to certain rules, ultimately resulting in the brain's response to those stimuli. Using the operating principles of the human brain, a biological model is established—the neural network model. A neural network is a theory of intelligent computer science; it can perform computational functions such as learning, memory, and recognition, and can solve complex, uncertain, and nonlinear problems. The backpropagation (BP) algorithm utilizes error propagation to form complete interconnections at all levels, enabling high-precision approximation of various complex nonlinear functions with extremely low computational cost. It also possesses autonomous learning capabilities, continuously adapting to changes.

[0074] Therefore, in this embodiment, the model used to predict indoor temperature is a BP neural network model;

[0075] As attached Figure 3 As shown, the BP neural network model includes an input layer, a hidden layer, and an output layer;

[0076] The input data of the input layer is determined by various indicators generated from the analysis. In this embodiment, it is determined by the influencing factors of indoor temperature prediction. Therefore, according to the analysis results of the previous step, the number of nodes in the input layer is 4. The output layer is used to output the predicted temperature, so the number of nodes in the output layer is 1. Wherein, xi is the input indicator value, f1 is the hidden layer, f2 is the output layer, bi is the hidden layer parameter, and Bk is the output layer parameter.

[0077] The formula for calculating node h in the hidden layer is:

[0078] ;

[0079] In the formula, m and n are the number of nodes in the input layer and the output layer, respectively, and a is the adjustment coefficient;

[0080] Furthermore, the BP neural network model uses the sigmoid function as its transfer function, and its formula is as follows:

[0081] ;

[0082] Where K is the input data;

[0083] The training iterations of the BP neural network model were set to 50,000. To achieve a better fit, the number of iterations was adjusted to the maximum of 50,000. The model stopped training when the error dropped to 0.0001.

[0084] S5: Train the model for predicting indoor temperature;

[0085] The model for predicting indoor temperature was trained using MATLAB R2014a.

[0086] Using Matlab software, multiple rounds of training and learning are conducted. By adjusting factors such as weights and i, the shared value of the sample data is accurately output.

[0087] In this embodiment, the evaluation results output by the evaluation model can be measured by the mean squared error (MSE). The smaller the MSE, the better the model fits.

[0088] S6: The preprocessed values ​​of the influencing factors used for indoor temperature prediction are input into the model for predicting indoor temperature to obtain the indoor temperature prediction result;

[0089] In fact, the indoor temperature prediction result obtained in this step is the prediction result one minute after the prediction.

[0090] S7: Control the indoor thermal environment based on the indoor temperature prediction results;

[0091] The indoor temperature prediction result is input into the air conditioning control system, which then controls the indoor thermal environment based on the indoor temperature prediction result and the set target temperature.

[0092] Example 2: This example includes a control system for the indoor thermal environment of an elderly care building. The system adopts a control method for the indoor thermal environment of an elderly care building according to Example 1. The system includes:

[0093] The influencing factor acquisition module is used to acquire the influencing factors for indoor temperature prediction.

[0094] The data acquisition module is used to collect the values ​​of the influencing factors used for indoor temperature prediction;

[0095] The preprocessing module is used to perform preprocessing operations on the influencing factors used for indoor temperature prediction to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction.

[0096] The model building module is used to build models for predicting indoor temperatures.

[0097] The model training module is used to train the model for predicting indoor temperature.

[0098] The prediction module is used to input the preprocessed values ​​of influencing factors for indoor temperature prediction into the indoor temperature prediction model to obtain the indoor temperature prediction result.

[0099] The thermal environment control module is used to control the indoor thermal environment based on the indoor temperature prediction results.

[0100] Example 3: This example includes a computer-readable storage medium storing a data processing program, which is executed by a processor according to Example 1, a method for controlling the indoor thermal environment of an elderly care building.

[0101] Those skilled in the art will understand that the embodiments described herein can be provided as methods, apparatus (devices), or computer program products. Therefore, this document may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. This includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0102] This document is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments herein. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0103] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0104] The embodiments and / or implementation methods described above are merely preferred embodiments and / or implementation methods for implementing the technology of the present invention, and are not intended to limit the implementation methods of the present invention in any way. Any person skilled in the art can make some modifications or alterations to other equivalent embodiments without departing from the scope of the technical means disclosed in the present invention, but these should still be considered as technologies or embodiments substantially the same as the present invention. Note that the above are merely preferred embodiments and the technical principles applied in the present invention. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for controlling the indoor thermal environment of a senior care building, characterized in that, The method includes the following steps: S1: Obtain the influencing factors used for indoor temperature prediction; S2: Collect the values ​​of the influencing factors used for indoor temperature prediction; S3: Perform a preprocessing operation on the values ​​of the influencing factors used for indoor temperature prediction to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction. Specifically, S3 involves: performing a correlation analysis on the influencing factors used for indoor temperature prediction, wherein the correlation analysis on the influencing factors used for indoor temperature prediction specifically includes: The indoor temperature value, outdoor temperature value, outdoor relative humidity value, outdoor wind speed value, and solar radiation value are obtained. Then, the product difference method is used to calculate the correlation coefficients between the outdoor temperature value, outdoor relative humidity value, outdoor wind speed value, and solar radiation value and the indoor temperature value. The formula for calculating the correlation coefficient r using the product-moment method is as follows: ； In the formula, x and y represent the values ​​of the influencing factors and the indoor temperature, respectively. and The center point of the influencing factors and the indoor temperature value is n, where n is the number of samples involved in the calculation. Then, based on the correlation coefficient, the influencing factors used for indoor temperature prediction are preprocessed to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction. The preprocessing operation for the influencing factors used in indoor temperature prediction based on the correlation coefficient is specifically as follows: Sa: Normalize the values ​​of the influencing factors used for indoor temperature prediction to obtain the normalized values ​​of the influencing factors used for indoor temperature prediction; Sb: The correlation coefficient between the values ​​of the influencing factors used for indoor temperature prediction and the indoor temperature value is normalized to obtain the normalized correlation coefficient value; Sc: Multiply the normalized values ​​of the influencing factors used for indoor temperature prediction by the corresponding normalized correlation coefficient values ​​to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction; S4: Develop a model for predicting indoor temperature; S5: Train the model for predicting indoor temperature; S6: The preprocessed values ​​of the influencing factors used for indoor temperature prediction are input into the model for predicting indoor temperature to obtain the indoor temperature prediction result; S7: Control the indoor thermal environment based on the indoor temperature prediction results.

2. The method for controlling the indoor thermal environment of a senior care building according to claim 1, characterized in that, In step S2, the values ​​of the influencing factors used for indoor temperature prediction are obtained; the collected values ​​are the values ​​of the influencing factors for a period of time before the prediction time; the period of time is one of 1 minute, 5 minutes, 10 minutes, and 15 minutes.

3. The method for controlling the indoor thermal environment of a senior care building according to claim 1, characterized in that, The model used to predict indoor temperature is a backpropagation (BP) neural network model. This BP neural network model includes an input layer, a hidden layer, and an output layer. The input layer has 4 nodes; the output layer has 1 node; and the formula for calculating the number of nodes h in the hidden layer is: ； In the formula, m and n are the number of nodes in the input layer and the output layer, respectively, and a is the adjustment coefficient.

4. The method for controlling the indoor thermal environment of a senior care building according to claim 3, characterized in that, The BP neural network model uses the sigmoid function as its transfer function, and its formula is as follows: ； Where K is the input data; The BP neural network model was trained 50,000 times.

5. A control system for the indoor thermal environment of a senior care building, characterized in that, The system employs a method for controlling the indoor thermal environment of an elderly care building as described in any one of claims 1-4, the system comprising: The influencing factor acquisition module is used to acquire the influencing factors for indoor temperature prediction. The data acquisition module is used to collect the values ​​of the influencing factors used for indoor temperature prediction; The preprocessing module is used to perform preprocessing operations on the influencing factors used for indoor temperature prediction to obtain the preprocessed values ​​of the influencing factors used for indoor temperature prediction. The model building module is used to build models for predicting indoor temperatures. The model training module is used to train the model for predicting indoor temperature. The prediction module is used to input the preprocessed values ​​of influencing factors for indoor temperature prediction into the indoor temperature prediction model to obtain the indoor temperature prediction result. The thermal environment control module is used to control the indoor thermal environment based on the indoor temperature prediction results.

Images