Severe cold area thermal demand analysis method based on building digitization technology

Abstract

The invention discloses a severe cold area thermal demand analysis method based on a building digitization technology, and relates to the technical field of heat supply analysis. The method aims to solve the problem that an existing thermal demand analysis method is low in analysis accuracy. The method comprises the following steps: acquiring outdoor meteorological data to be analyzed at different moments; constructing an indoor BIM model to be analyzed; setting the design temperature, the personnel density and the equipment use condition of each functional area in the to-be-analyzed room; obtaining the water supply flow required by each functional area in the to-be-analyzed room; the valve opening degree corresponding to the needed water supply flow is obtained through the water supply flow needed by all functional areas in a to-be-analyzed room, the valve opening degree in the to-be-analyzed room is adjusted according to the valve opening degree, then the temperature of all the functional areas in the to-be-analyzed room is obtained through a room temperature sensor, and an abnormal value is replaced with a correction value; and obtaining the temperature of each functional area in the to-be-analyzed chamber after treatment, and regulating and controlling the opening degree of the valve again based on the temperature of each functional area in the to-be-analyzed chamber after treatment. The method is used for thermodynamic demand analysis and thermodynamic regulation and control.

Description

Technical Field

[0001] The present invention relates to the technical field of heat supply analysis, and in particular to a method for analyzing heat demand in severe cold regions based on building digitalization technology. Background Art

[0003] The traditional method for analyzing the thermal demand of heating systems adopts a static analysis method, which relies on empirical formulas, simplified physical models and previous operating experience to conduct energy consumption analysis and control operations. However, the traditional method for analyzing the thermal demand of heating systems does not consider the impact of dynamic factors such as actual indoor temperature and outdoor meteorological data (outdoor temperature, outdoor wind speed, light) on thermal demand, resulting in low accuracy of thermal demand analysis. Summary of the invention

[0004] The purpose of the present invention is to solve the problem of low analysis accuracy in existing thermal demand analysis methods, and propose a thermal demand analysis method for severe cold areas based on building digitalization technology.

[0005] A method for analyzing heat demand in severe cold regions based on building digital technology, including:

[0006] Step 1: Obtain outdoor meteorological data to be analyzed at different times in the study area;

[0007] The outdoor meteorological data to be analyzed include: outdoor temperature, outdoor pressure, and outdoor air density;

[0008] Step 2: Obtain the heat transfer coefficient of the building maintenance structure of the room to be analyzed, and use the heat transfer coefficient of the building maintenance structure of the room to be analyzed, the building shape, the building structure diagram and the building diagram to construct a BIM model of the building where the room to be analyzed is located;

[0009] Step 3: Set the design temperature, personnel density and equipment usage of each functional area in the room to be analyzed;

[0010] The functional areas include: meeting room, tea room, toilet;

[0011] Step 4: Use the BIM model of the building where the room to be analyzed is located to perform thermal demand analysis using the outdoor meteorological data to be analyzed and the design temperature, personnel density and equipment usage of each functional area in the room to be analyzed, and obtain the required water supply flow for each functional area in the room to be analyzed;

[0012] Step 5. Use the required water supply flow rate for each functional area in the room to be analyzed obtained in step 4 to obtain the valve opening corresponding to the required water supply flow rate, and adjust the valve opening of the room to be analyzed according to the valve opening, and then use the room temperature sensor to obtain the temperature of each functional area in the room to be analyzed at different times, and then obtain the abnormal values ​​in the temperature of each functional area in the room to be analyzed at different times, and replace the abnormal values ​​with corrected values ​​to obtain the processed temperature of each functional area in the room to be analyzed at different times, and adjust the valve opening again based on the processed temperature of each functional area in the room to be analyzed at different times.

[0013] Furthermore, in step 4, the BIM model of the building where the indoor room to be analyzed is used to perform thermal demand analysis using the outdoor meteorological data to be analyzed and the design temperature, personnel density and equipment usage of each functional area in the indoor room to be analyzed, and obtain the required water supply flow rate for each functional area in the indoor room to be analyzed, specifically:

[0014] Step 41: Obtain the heat load of the i-th functional area of ​​the room to be analyzed at the j-th heating moment, specifically:

[0015] Q ij =Q1 ij +Q2 ij +Q3 ij -Q4 ij

[0016] Q1 ij =αKA(t ij -t w j )

[0017] Q2 ij =0.278NVc p ρ w (t ij -t w j )

[0018] Q3 ij =Q1 ij (1+β c +β f +β q +β m )(1+β fg )(1+β j )

[0019] Q4 ij =η(zq r +W)

[0020] Among them, Q ijis the heat load of the i-th indoor functional zone at the j-th heating moment, i∈[1,m], i is the number of the indoor functional zone to be evaluated, m is the total number of indoor functional zones to be evaluated, j∈[1,n], j is the number of the heating moment, n is the total number of heating moments, Q1 ij is the basic heat consumption of the enclosure structure at the jth heating moment in the i-th functional area, Q2 ij is the heat consumption of cold air penetration in the i-th functional area at the j-th heating moment, Q3 ij is the additional heat consumption of the building at the jth heating moment in the i-th functional area, Q4 ij is the total heat dissipation of human body and equipment in the room to be analyzed at the jth heating moment in the i-th functional zone, α is the temperature difference correction coefficient, K represents the heat transfer coefficient of the building envelope, A represents the heat transfer area of ​​the building envelope, t ij represents the design temperature of the i-th functional area of ​​the room to be analyzed at the j-th heating moment, t w j represents the average outdoor temperature at the jth heating moment, N represents the number of indoor air changes, V represents the net volume of the room, c p is the specific heat capacity of outdoor air at constant pressure, ρ w represents the outdoor air density, β c represents the preset orientation correction rate, β f Indicates the preset wind correction rate, β q Indicates the preset two-wall correction rate, β m Indicates the preset window-to-wall ratio correction rate, β fg Indicates the preset room height correction rate, β j represents the preset intermittent correction rate, η represents the preset correction rate of heat dissipation of people and equipment, z represents the number of people in the room to be analyzed, and q r It represents the heat dissipation of human body, and W represents the heat dissipation of equipment.

[0021] Step 42: Use the heat load of the i-th functional area of ​​the room to be analyzed at the j-th heating moment to obtain the required water supply flow F of the i-th functional area of ​​the room to be analyzed at the j-th heating moment ij .

[0022] Furthermore, the heat load of the i-th functional zone in the room to be analyzed at the j-th heating moment is used in the step 42 to obtain the required water supply flow F for the i-th functional zone in the room to be analyzed at the j-th heating moment. ij , specifically:

[0023] F ij =Q ij / (cρΔT)

[0024] Where c represents the specific heat capacity of water, ρ represents the density of water, ΔT represents the supply and return water temperature difference, F ijIt is the water supply flow required for the jth heating moment of the i-th functional area in the room to be analyzed.

[0025] Furthermore, the step 5 uses the required water supply flow rate for each functional area of ​​the room to be analyzed obtained in step 4 to obtain the valve opening corresponding to the required water supply flow rate, specifically:

[0026] If the regulating valve has a fast-opening flow characteristic, the required water supply flow corresponds to the valve opening and can be obtained in the following way:

[0027]

[0028] Among them, F max Indicates the maximum flow rate of the valve, L ij represents the required valve opening of the i-th functional zone in the room to be analyzed at the j-th heating moment, L max Indicates the maximum opening of the valve, and R indicates the predicted adjustable ratio of the control valve;

[0029] If the regulating valve has a linear flow characteristic, the required water supply flow corresponds to the valve opening and can be obtained by:

[0030]

[0031] If the regulating valve has an equal percentage flow characteristic, the required water supply flow corresponds to the valve opening and can be obtained by:

[0032]

[0033] Furthermore, in step 5, the room temperature sensor is used to obtain the temperature of each functional area in the room to be analyzed at different times, and then the abnormal value in the temperature of each functional area in the room to be analyzed at different times is obtained, and the abnormal value is replaced by the correction value to obtain the processed temperature of each functional area in the room to be analyzed at different times, specifically:

[0034] First, obtain the historical sequence of N historical heating moments of the i-th functional zone in the room to be analyzed, input the historical sequence of N historical heating moments of the i-th functional zone in the room to be analyzed into the trained indoor temperature prediction model, and obtain the predicted indoor temperature of the i-th functional zone at the N+1 heating moment, i.e., the correction value;

[0035] The historical sequence of the N historical heating moments of the i-th functional zone includes: the indoor temperature sequence of the N historical heating moments of the i-th functional zone, the water supply temperature sequence of the N historical heating moments of the i-th functional zone, the return water temperature sequence of the N historical heating moments of the i-th functional zone, the flow sequence of the N historical heating moments of the i-th functional zone, and the outdoor temperature sequence of the N historical heating moments of the i-th functional zone;

[0036] Then, the predicted indoor temperature of the ith functional area at the N+1th heating moment is compared with the actual indoor temperature of the ith functional area at the N+1th heating moment obtained by the room temperature sensor. If the indoor predicted temperature and the actual indoor temperature are within the preset first error range, the valve opening is adjusted again based on the temperatures of each functional area in the room to be analyzed at different moments after processing; otherwise, the actual indoor temperature of the ith functional area at the N+1th heating moment is replaced by the correction value, and the valve opening is adjusted again based on the temperatures of each functional area in the room to be analyzed at different moments after processing.

[0037] Furthermore, the trained indoor temperature prediction model is obtained by:

[0038] B1. Obtain the historical sequences of M historical heating moments of the i-th functional zone of the room to be analyzed respectively, and preprocess each historical sequence, and form a training set with the preprocessed historical sequence and the indoor temperature of the i-th functional zone of the room to be analyzed at the M+1-th heating moment;

[0039] The historical sequence of the M historical heating moments of the i-th functional zone includes: the indoor temperature sequence of the M historical heating moments of the i-th functional zone, the water supply temperature sequence of the M historical heating moments of the i-th functional zone, the return water temperature sequence of the M historical heating moments of the i-th functional zone, the flow sequence of the M historical heating moments of the i-th functional zone, and the outdoor temperature sequence of the M historical heating moments of the i-th functional zone;

[0040] B2. Use the training set to train the indoor temperature prediction model to obtain a trained indoor temperature prediction model.

[0041] Furthermore, the preprocessing of each historical sequence in B1 is specifically as follows:

[0042] A1. Obtain the missing feature data position in the m'th historical sequence of the i-th functional area, and then supplement the missing feature data position with the average value of the feature data value of the previous position and the feature data value of the next position;

[0043] Wherein, m' is the historical sequence number, and m'=1, 2, 3, 4, 5 represent the indoor temperature sequence, the supply water temperature sequence, the return water temperature sequence, the flow sequence, and the outdoor temperature sequence respectively;

[0044] A2, obtain the first quartile Q1, the third quartile Q3, and the interquartile range IQR of the m'th historical sequence of the ith functional area after processing by A1;

[0045] The first quartile Q1 is the 25% quantile of the m'th historical sequence of the ith functional area;

[0046] The third quartile Q3 is the 75% quantile of the m'th historical sequence of the ith functional area;

[0047] The interquartile range (IQR) is obtained by:

[0048] IQR=Q3-Q1

[0049] A3. Use Q1, Q3 and IQR to obtain the upper and lower bounds of outliers:

[0050] Outlier lower bound = Q1-1.5×IQR

[0051] Outlier upper limit = Q3 + 1.5 × IQR

[0052] A4. In the m'th historical sequence of the i-th functional area, the characteristic data value that is not within the range from the lower bound to the upper bound of the abnormal value is the abnormal value, and then the position of the abnormal value is obtained, and the average value of the three characteristic data values ​​before the abnormal value position and the three characteristic data values ​​after the abnormal value position is replaced into the abnormal value position, and the m'th historical sequence of the i-th functional area after the abnormal value is filled is obtained;

[0053] A5. Normalize the m'th historical sequence of the ith functional area after filling the outliers to obtain the indoor temperature sequence, water supply temperature sequence, return water temperature sequence, flow sequence, and outdoor temperature sequence of the M historical heating moments of the ith functional area after preprocessing.

[0054] Furthermore, the m'th historical sequence of the ith functional area after outlier filling in A5 is normalized, specifically:

[0055]

[0056] Among them, x i,m',d is the dth characteristic data value in the m'th historical sequence of the ith functional area after outlier filling, x i ' ,m',d is the dth characteristic data value in the m'th historical sequence of the ith functional area after normalization, x i,m',min is the minimum value of the characteristic data in the m'th historical sequence of the ith functional area after outlier filling, x i,m',max It is the maximum value of the characteristic data in the m'th historical sequence of the ith functional area after outliers are filled.

[0057] Furthermore, the indoor temperature prediction model in B2 includes: an LSTM module, an efficient additive self-attention mechanism module, and an indoor temperature prediction module;

[0058] The LSTM module is an LSTM network, which is used to obtain the hidden state of the input feature vector, specifically:

[0059] h j' =O j' tanh(C j' )

[0060] O j' =σ(W o [h j'-1 ,x j' ]+b o )

[0061]

[0062] f j' =σ(W f [h j'-1 ,x j' ]+b f )

[0063] i j' =σ(W i” [h j'-1 ,x j' ]+b i” )

[0064] Among them, f j is the output of the forget gate at time step j', σ is the Sigmoid activation function, W f is the forget gate weight matrix, W i” is the input gate weight matrix, W c is the cell state update weight matrix, W o is the output gate weight matrix, h j'-1 is the hidden state of the previous time step j'-1, x j' is the input feature vector of the current time step j', b f is the forget gate bias term, b i” is the input gate bias term, b c is the cell state update bias term, b o is the output gate bias term, i j' is the output of the input gate at time step j', is the candidate cell state, tanh is the hyperbolic tangent activation function, C j' Updated cell state, C j'-1 is the cell state at the previous time step j'-1, O j' is the output of the output gate at time step j', h j' is the hidden state at time step j';

[0065] The input feature vector includes: supply water temperature, return water temperature, flow rate, indoor temperature and outdoor temperature;

[0066] The efficient additive self-attention mechanism module obtains the global context representation and c' according to the hidden state of the input feature vector:

[0067]

[0068] x' j' =Q j' +T(K j' ×q j' )

[0069] q j' =α j' Q j'

[0070]

[0071] Q j' =h j' W Q

[0072] K j' =h j' W K

[0073] Among them, x' j' is the global context representation of the j'th time step, α j' is the global attention query vector, d is the query matrix dimension, W Q , W K is the learned weight matrix, Q j' is the query vector, K j' is the key vector, W a is the preset parameter vector, q j' is a single global query vector, T is a linear transformation;

[0074] The indoor temperature prediction module represents and obtains the indoor temperature prediction value according to the hidden state and global context of the input feature vector:

[0075] y′=Wz′+b

[0076] z'=concat[h j' ,c']

[0077] Among them, W' is the preset weight matrix, b is the bias term, and z is h j' and c', y' is the predicted value of indoor temperature.

[0078] Furthermore, in step 5, the valve opening is adjusted again based on the temperature of each functional area in the room to be analyzed at different times after processing, specifically:

[0079] Determine whether the error between the temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment after processing and the design temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment is within a preset allowable second temperature error range, if within the preset allowable second temperature error range, do not adjust the valve opening, if not within the preset allowable second temperature error range, adjust the valve opening;

[0080] If it is not within the preset allowable second temperature error range, the valve opening is regulated, specifically:

[0081] Find the outdoor temperature data P closest to the j-th heating moment in the historical data, and obtain the valve opening corresponding to the outdoor temperature data P;

[0082] If the temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment after processing is higher than the design temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment, the minimum value of the valve opening corresponding to the outdoor temperature data P is used as the current valve opening;

[0083] If the temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment after processing is lower than the design temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment, the maximum value of the valve opening corresponding to the outdoor temperature data P is used as the current valve opening.

[0084] The beneficial effects of the present invention are:

[0085] The present invention proposes a thermal demand analysis method for building heating systems in severe cold regions, which can complete energy-saving control tasks. The present invention obtains multiple dynamic influencing factors of indoor temperature and outdoor meteorological data and the heat transfer coefficient of the building envelope structure to realize accurate thermal demand analysis and flow demand analysis of building heating systems in severe cold regions, thereby effectively improving the accuracy of thermal demand analysis and thus reducing building energy consumption; the present invention determines the opening of the heating water supply valve according to the required indoor temperature of the heating room, the actual indoor temperature and the outdoor meteorological data, and detects whether the actual indoor temperature of the heating room meets the preset temperature after the first regulation, and then performs secondary regulation of the heating water supply valve to improve the regulation accuracy of the indoor heating temperature, thereby meeting the heating demand while reducing energy consumption. The present invention provides real-time feedback on the actual indoor temperature after regulation and performs secondary regulation on the water supply flow, thereby improving the accuracy of the thermal demand analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0087] Specific implementation method 1: Figure 1 As shown, the specific process of the thermal demand analysis method for severe cold regions based on building digital technology in this embodiment is as follows:

[0088] Step 1: Obtain outdoor meteorological data to be analyzed at different times in severe cold regions;

[0089] The outdoor meteorological data to be analyzed include: outdoor temperature, outdoor pressure, and outdoor air density;

[0090] A small weather monitor is placed next to the building to capture outdoor weather data in real time. Compared with obtaining outdoor dynamic weather data at the building location through the weather website of the Meteorological Bureau, it is more accurate, which further makes the subsequent thermal demand analysis more accurate.

[0091] The severely cold regions meet the following conditions:

[0092] Condition 1: The number of days with daily average temperature below 5°C is greater than 145 days;

[0093] The daily average temperature is the average of the maximum and minimum temperatures of the day;

[0094] Condition 2: The lowest monthly average temperature of the current year is less than -10℃, specifically:

[0095] Get the daily average temperature of the current area, add up the daily average temperature and divide it by the number of days in the month to get the average temperature of the month; get the lowest monthly average temperature of the current year, and make sure the lowest monthly average temperature of the current year is less than -10℃.

[0096] Step 2: Obtain the heat transfer coefficient of the building maintenance structure of the room to be analyzed, and use the heat transfer coefficient of the building maintenance structure of the room to be analyzed, the building shape, the building structure diagram and the building diagram to construct the BIM model of the building where the room to be analyzed is located, specifically:

[0097] Step 21: Obtain the architectural mode of the room to be evaluated. If the architectural mode of the room to be evaluated is the drawing mode, execute step 22; if the architectural mode of the room to be evaluated is the renovation mode, execute step 23;

[0098] The building mode includes: drawing mode and transformation mode;

[0099] The drawing mode is: the material types, material thicknesses and material parameters used in BIM digital modeling are set according to the design drawings. This mode is suitable for buildings that are constructed according to the design drawings or buildings that have been renovated and the parameters after the renovation are known;

[0100] The renovation mode is: the renovation mode means that the building is to be renovated after being designed and constructed according to the drawings. This mode can be used to analyze the optimal enclosure structure parameters after renovation and provide guidance for the renovation of old communities. The material type, material thickness and parameters are set according to the analysis results and used for subsequent dynamic thermal demand analysis.

[0101] Step 22: Obtain the type and thickness of the indoor materials to be evaluated according to the design drawings, obtain the heat transfer coefficient of the building maintenance structure using the type and thickness of the indoor materials to be evaluated, and construct the BIM model of the building where the indoor room to be analyzed is located using the building shape, the heat transfer coefficient of the building maintenance structure, the building structure diagram and the building diagram;

[0102] The BIM model includes detailed information such as building form and materials;

[0103] The types and thickness of materials used in the same functional areas of the room are the same, and the heat transfer coefficients are equal.

[0104] Step 2 and 3: Use the type and thickness of the indoor materials to be evaluated after the renovation to obtain the heat transfer coefficient of the building maintenance structure, and use the heat transfer coefficient of the building maintenance structure, the building shape, the building structure diagram and the building diagram to build a BIM model;

[0105] The types and thickness of indoor materials to be evaluated after renovation are set based on experience and generally according to cost.

[0106] Step 3: Set the design temperature of each functional area in the room to be analyzed according to the heating working mode of the room to be analyzed, and set the personnel density and equipment usage of the room to be analyzed, specifically:

[0107] Step 31: Obtain the heating working mode of the room to be analyzed. If the heating working mode is the normal mode, execute step 32; if the heating working mode is the manual mode, execute step 33;

[0108] The normal mode is: the heating temperature of the room to be analyzed remains unchanged at the initial setting value, and the heating time is full-time heating;

[0109] Manual mode: the heating temperature and heating period of each functional area in the room to be analyzed are set by the user and can be changed at any time;

[0110] Step 32: Set the preset heating design temperature for each functional area of ​​the room to be analyzed:

[0111] In normal mode, the office area temperature is set at 20 degrees Celsius, the conference room temperature is set at 20 degrees Celsius, the tea room temperature is set at 18 degrees Celsius, the bathroom temperature is set at 18 degrees Celsius, and the indoor personnel density and equipment usage are set.

[0112] Step 3. Set the heating design temperature for each functional area in the room to be analyzed at each time period:

[0113] Functional areas include: office area, meeting room, tea room, toilet, etc.;

[0114] Examples of heating design temperatures for functional areas at different time periods are as follows:

[0115] In manual mode, the heating time can be set according to the working hours. The heating time of the office area is 8:00-18:00, and the heating temperature from 18:00 to 8:00 is 20 degrees Celsius and 12 degrees Celsius respectively;

[0116] The heating time of the conference room can be set after the meeting is confirmed, and the heating temperature is 20 degrees Celsius;

[0117] The heating time of the tea room is 8:00-18:00, the heating temperature is 18 degrees Celsius, and the heating temperature from 18:00 to 8:00 is 12 degrees Celsius;

[0118] The bathroom heating time is 8:00-18:00, the heating temperature is 18 degrees Celsius, and the heating temperature from 18:00 to 8:00 is 12 degrees Celsius;

[0119] Step 3 and 4: Set the indoor personnel density and equipment usage to be evaluated. If there are special circumstances, temporary settings can be made and the change time can be selected to be the same day or permanent;

[0120] The device is an electrical device, such as a lighting device.

[0121] The present invention provides a drawing mode and a renovation mode for users to choose during the BIM model establishment process. The renovation mode provides the best renovation plan for the renovation of old residential areas, and is divided into two heating modes: conventional mode and manual mode. The heating period and heating temperature are selected to meet the different needs of various users.

[0122] Step 4: Use the BIM model of the building where the indoor room to be analyzed is located to perform thermal demand analysis using the outdoor meteorological data to be analyzed and the design temperature of each functional area in the indoor room to be analyzed, and obtain the required water supply flow for each functional area in the indoor room to be analyzed, specifically:

[0123] Step 41: Obtain the heat load of the i-th functional area of ​​the room to be analyzed at the j-th heating moment:

[0124] Q ij =Q1 ij +Q2 ij +Q3 ij -Q4 ij

[0125] Q1 ij =αKA(t ij -t w j )

[0126] Q2 ij =0.278NVc p ρ w (t ij-t w j )

[0127] Q3 ij =Q1 ij (1+β c +β f +β q +β m )(1+β fg )(1+β j )

[0128] Q4 ij =η(zq r +W)

[0129] Among them, Q ij is the heat load of the i-th indoor functional zone at the j-th heating moment, i∈[1,m], i is the number of the indoor functional zone to be evaluated, m is the total number of indoor functional zones to be evaluated, j∈[1,n], j is the number of the heating moment, n is the total number of heating moments, Q1 ij is the basic heat consumption of the enclosure structure at the jth heating moment in the i-th functional area, Q2 ij is the heat consumption of cold air penetration in the i-th functional area at the j-th heating moment, Q3 ij is the additional heat consumption of the building at the jth heating moment in the i-th functional area, Q4 ij is the total heat dissipation of human body and equipment in the room to be analyzed at the jth heating moment in the i-th functional zone, α is the temperature difference correction coefficient, K represents the heat transfer coefficient of the building envelope, A represents the heat transfer area of ​​the building envelope, t ij represents the design temperature of the i-th functional area of ​​the room to be analyzed at the j-th heating moment, t w j represents the average outdoor temperature at the jth heating moment, N represents the number of indoor air changes, V represents the net volume of the room, c p is the specific heat capacity of outdoor air at constant pressure, ρ w represents the outdoor air density, β c represents the preset orientation correction rate, β f Indicates the preset wind correction rate, β q Indicates the preset two-wall correction rate, β m Indicates the preset window-to-wall ratio correction rate, β fg Indicates the preset room height correction rate, β j represents the preset intermittent correction rate, η represents the preset correction rate of heat dissipation of people and equipment, z represents the number of people in the room, and q r It represents the heat dissipation of human body, and W represents the heat dissipation of equipment.

[0130] The correction rate of heat dissipation of people and equipment is obtained by looking up in the "Design Specifications for Heating, Ventilation and Air Conditioning of Civil Buildings";

[0131] Correction rate β for the indoor orientation to be evaluated, i.e., north, northeast, or northwest c Take the value between 0 and 10%; the correction rate of the east or west orientation of the room to be evaluated β c Take -5% as the correction rate β for the southeast or southwest orientation of the room to be evaluated c Take the value between -10% and -15%; the correction rate of the indoor south orientation to be evaluated is β c Take between -15% and -30%;

[0132] The indoor buildings to be evaluated are those located in high places without wind shelter, on rivers, coasts, in the wilderness, and buildings in towns that are obviously higher than other surrounding buildings. The wind correction rate β f The value range is between 5% and 10%;

[0133] Correction rate of two exterior walls β q Set to 5%;

[0134] Correction rate of excessive window-to-wall ratio β m Set to 10%;

[0135] Room height correction rate β fg The value is set to 2(H-4)%, and β fg When it exceeds 15%, fg Set to 15%;

[0136] When the room to be evaluated is only used during the day, the intermittent correction rate β j Set to 20%; if the room to be evaluated is not frequently used, the intermittent correction rate β j Set to 30%;

[0137] Indoor spaces to be evaluated that are used only during the day include: offices, schools, and shops;

[0138] Infrequently used indoor areas to be evaluated are buildings that are only used for events, meetings or certain seasons;

[0139] Indoor occupancy density and equipment usage will affect heating energy consumption, so when calculating the heating heat load, people and equipment are taken into account and the heat they generate is recorded as Q4. ij , the total heat dissipation of indoor personnel is recorded as zq r The total heat dissipation of indoor equipment is recorded as W, and η is used to correct the heat dissipation of personnel and equipment to ensure that the calculated heat load is more accurate.

[0140] Step 42: Use the heat load of the i-th functional area of ​​the room to be analyzed at the j-th heating moment to obtain the required water supply flow F of the i-th functional area of ​​the room to be analyzed at the j-th heating moment ij :

[0141] F ij =Q ij / (cρΔT)

[0142] Where c represents the specific heat capacity of water, ρ represents the density of water, and ΔT represents the supply and return water temperature difference.

[0143] The present invention obtains multiple dynamic influencing factors of indoor temperature and outdoor meteorological data, as well as the heat transfer coefficient of the building envelope structure to realize accurate thermal demand analysis and flow demand analysis of the heating system of buildings in severe cold areas, thereby effectively reducing the energy consumption of buildings.

[0144] Step 5: Use the required water supply flow rate for each functional area of ​​the room to be analyzed obtained in step 4 to obtain the valve opening corresponding to the required water supply flow rate, and adjust the valve opening of the room to be analyzed according to the valve opening, and then use the room temperature sensor to obtain the temperature of each functional area in the room to be analyzed at different times, obtain the abnormal value in the temperature of each functional area in the room to be analyzed at different times, and replace the abnormal value with the correction value to obtain the temperature of each functional area in the room to be analyzed at different times after processing, and adjust the valve opening again based on the temperature of each functional area in the room to be analyzed at different times after processing, specifically:

[0145] Step 5. Use the required water supply flow for each functional area of ​​the room to be analyzed obtained in step 4 to obtain the valve opening corresponding to the required water supply flow:

[0146] If the regulating valve has a quick-opening flow characteristic, the valve opening L is calculated using the water supply flow required for each functional area in the room to be analyzed and the quick-opening flow characteristic opening formula, specifically:

[0147]

[0148] Among them, F max Indicates the maximum flow rate of the valve, L ij represents the required valve opening of the i-th functional zone in the room to be analyzed at the j-th heating moment, L max Indicates the maximum opening of the valve, and R indicates the adjustable ratio of the control valve;

[0149] If the regulating valve has a linear flow characteristic, the valve opening is calculated using the water supply flow required for each functional area in the room to be analyzed and the linear flow characteristic opening formula, specifically:

[0150]

[0151] If the regulating valve has a parabolic flow characteristic, the valve opening is calculated using the water supply flow required for each functional area in the room to be analyzed and the parabolic flow characteristic opening formula, specifically:

[0152]

[0153] If the regulating valve has an equal percentage flow characteristic, the valve opening is calculated using the water supply flow required for each functional area in the room to be analyzed and the equal percentage flow characteristic opening formula, specifically;

[0154]

[0155] Step 52: adjust the valve opening of the room to be analyzed according to the valve opening corresponding to the required water supply flow, and then use the room temperature sensor to obtain the temperature of each functional area in the room to be analyzed at different times, and then obtain the abnormal value of the temperature of each functional area in the room to be analyzed at different times, and replace the abnormal value with the correction value to obtain the processed temperature of each functional area in the room to be analyzed at different times;

[0156] The abnormal values ​​in the temperature of each functional zone in the room to be analyzed at different times are obtained, and the abnormal values ​​are replaced by correction values ​​to obtain the processed temperature of each functional zone in the room to be analyzed at different times, which is obtained by the following method:

[0157] Step 521: Obtain the historical sequence of N historical heating moments of the i-th functional zone of the room to be analyzed, input the historical sequence of N historical heating moments of the i-th functional zone of the room to be analyzed into the trained indoor temperature prediction model, and obtain the predicted indoor temperature of the i-th functional zone at the N+1-th heating moment, i.e., the correction value;

[0158] The historical sequence of N historical heating moments of the i-th functional zone includes: the indoor temperature sequence, the water supply temperature sequence, the return water temperature sequence, the flow sequence, and the outdoor temperature sequence of the i-th functional zone at N historical moments;

[0159] The trained indoor temperature prediction model is obtained by:

[0160] B1. Obtain the historical sequences of M historical moments of the i-th functional zone of the room to be analyzed respectively, and preprocess each historical sequence, and form a training set with the preprocessed historical sequence and the historical temperature of the i-th functional zone of the room to be analyzed at the M+1th moment;

[0161] The preprocessing of each historical sequence is specifically as follows:

[0162] A1. Obtain the missing feature data position in the m'th historical sequence of the i-th functional area, and then supplement the missing feature data position with the average value of the feature data value of the previous position and the feature data value of the next position;

[0163] Wherein, m' is the historical sequence number, m'=1, 2, 3, 4, 5 represent the indoor temperature sequence, the supply water temperature sequence, the return water temperature sequence, the flow sequence, and the outdoor temperature sequence respectively;

[0164] A2. Get the first quartile Q1, median Q2, third quartile Q3, and interquartile range IQR of the m'th historical sequence of the ith functional area after processing by A1:

[0165] The first quartile Q1 is the 25% quantile of the m'th historical sequence of the ith functional area;

[0166] The third quartile Q3 is the 75% quantile of the m'th historical sequence of the ith functional area;

[0167] The interquartile range (IQR) is obtained by:

[0168] IQR=Q3-Q1

[0169] A3. Use Q1, Q2, Q3 and IQR to obtain the upper and lower bounds of outliers:

[0170] Outlier lower bound = Q1-1.5×IQR

[0171] Outlier upper limit = Q3 + 1.5 × IQR

[0172] A4. In the m'th historical sequence of the i-th functional area, the characteristic data value that is not within the range from the lower bound to the upper bound of the abnormal value is the abnormal value, and then the position of the abnormal value is obtained, and the average value of the three characteristic data values ​​before the abnormal value position and the three characteristic data values ​​after the abnormal value position is replaced into the abnormal value position, and the m'th historical sequence of the i-th functional area after the abnormal value is filled is obtained;

[0173] A5. Normalize the m'th historical sequence of the ith functional area after filling the abnormal values, and obtain the indoor temperature sequence, water supply temperature sequence, return water temperature sequence, flow sequence, and outdoor temperature sequence of the M historical heating moments of the ith functional area after preprocessing:

[0174]

[0175] Among them, x i,m',d is the dth characteristic data value in the m'th historical sequence of the ith functional area after outlier filling, x i ' ,m',d is the dth characteristic data value in the m'th historical sequence of the ith functional area after normalization, x i,m',min is the minimum value of the characteristic data in the m'th historical sequence of the ith functional area after outlier filling, x i,m',max It is the maximum value of the characteristic data in the m'th historical sequence of the ith functional area after outliers are filled.

[0176] B2. Use the training set to train the indoor temperature prediction model to obtain a trained indoor temperature prediction model;

[0177] The indoor temperature prediction model includes: an LSTM module, an efficient additive self-attention mechanism module, and an indoor temperature prediction module;

[0178] The LSTM module is an LSTM network, which is used to obtain the hidden state of the input feature vector:

[0179] h j' =O j' tanh(C j' )

[0180] O j' =σ(W o [h j'-1 ,x j' ]+b o )

[0181]

[0182] f j' =σ(W f [h j'-1 ,x j' ]+b f )

[0183] i j' =σ(W i” [h j'-1 ,x j' ]+b i” )

[0184] Among them, f j is the output of the forget gate at time step j', σ is the Sigmoid activation function, W f , W i” , W c , W o are the weight matrices of the forget gate, input gate, cell state update, and output gate, respectively. j'-1 is the hidden state of the previous time step j'-1, x j' is the input feature vector of the current time step j, which includes supply water temperature, return water temperature, flow rate, indoor temperature, outdoor temperature, b f , b i” , b c , b o are the bias terms of the forget gate, input gate, cell state update and output gate, respectively, i j' is the output of the input gate at time step j', is the candidate cell state, tanh is the hyperbolic tangent activation function, C j' Updated cell state, C j'-1 is the cell state at the previous time step j'-1, O j'is the output of the output gate at time step j', h j' is the hidden state at time step j';

[0185] The efficient additive self-attention mechanism module obtains the global context representation and c' according to the hidden state of the input feature vector:

[0186]

[0187] x' j' =Q j' +T(K j' ×q j' )

[0188] q j' =α j' Q j'

[0189]

[0190] Q j' =h j' W Q

[0191] K j' =h j' W K

[0192] Among them, x' j' is the global context representation of the j'th time step, N is the total number of time steps, α j' is the global attention query vector, d is the query matrix dimension, W Q , W K is the learned weight matrix, Q j' is the query vector, K j' is the key vector, W a is the learnable parameter vector, q j' is a single global query vector, T is a linear transformation;

[0193] The indoor temperature prediction module represents and obtains the indoor temperature prediction value according to the hidden state and global context of the input feature vector:

[0194] y′=W'z'+b

[0195] z'=concat[h j' ,c']

[0196] Where W' is the learnable weight matrix, b is the bias term, and z' is h j' and the concatenated vector of c'.

[0197] Step 522: Compare the predicted indoor temperature of the ith functional area at the N+1th heating moment with the actual indoor temperature of the ith functional area at the N+1th heating moment obtained by the room temperature sensor. If the predicted indoor temperature and the actual indoor temperature are within the preset first error range, execute step 53; otherwise, it indicates that the actual indoor temperature of the ith functional area at the N+1 moment is an abnormal value. Replace the actual indoor temperature of the ith functional area at the N+1 moment with the corrected value, and then execute step 53.

[0198] Step 53: Based on the temperature of each functional area in the room to be analyzed at different times after processing, the opening of the heating water supply valve is adjusted again:

[0199] Determine whether the error between the temperature of each functional area in the room to be analyzed and the design temperature at different times after processing is within the preset allowable second temperature error range, if it is within the preset allowable second temperature error range, do not adjust the valve opening, if not, adjust the valve opening;

[0200] The preset allowable second temperature error is ±1 degree Celsius;

[0201] If it is not within the preset allowable second temperature error range, the valve opening is regulated, specifically:

[0202] Find the outdoor temperature data P closest to the j-th heating moment in the historical data, and obtain the valve opening corresponding to the outdoor temperature data P;

[0203] If the temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment after processing is higher than the design temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment, the minimum value of the valve opening corresponding to the outdoor temperature data P is used as the current valve opening;

[0204] If the temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment after processing is lower than the design temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment, the maximum value of the valve opening corresponding to the outdoor temperature data P is used as the current valve opening.

[0205] The present invention obtains multiple dynamic influencing factors such as indoor temperature, outdoor meteorological data, population density, etc., to realize accurate dynamic thermal demand analysis and dynamic control of the building. After dynamic control, the actual indoor heating temperature is detected for secondary regulation, thereby effectively reducing the energy consumption of the building while improving the user comfort. The BIM model can be established by referring to the drawings, and can also be used for the renovation of old communities and then established with reference to the optimal renovation plan after analysis. At the same time, two heating modes are provided for users to choose from, thereby meeting the usage needs of different users from multiple aspects.

Claims

1. A method for analyzing thermal demand in severe cold regions based on building digital technology, characterized in that The specific process of the method is: Step 1: Obtain outdoor meteorological data to be analyzed at different times in the study area; The outdoor meteorological data to be analyzed include: outdoor temperature, outdoor pressure, and outdoor air density; Step 2: Obtain the heat transfer coefficient of the building maintenance structure of the room to be analyzed, and use the heat transfer coefficient of the building maintenance structure of the room to be analyzed, the building shape, the building structure diagram and the building diagram to construct a BIM model of the building where the room to be analyzed is located; Step 3: Set the design temperature, personnel density and equipment usage of each functional area in the room to be analyzed; The functional areas include: office area, meeting room, pantry, and toilet; Step 4: Use the BIM model of the building where the room to be analyzed is located to perform thermal demand analysis using the outdoor meteorological data to be analyzed and the design temperature, personnel density and equipment usage of each functional area in the room to be analyzed, and obtain the required water supply flow for each functional area in the room to be analyzed; Step 5. Use the required water supply flow rate for each functional area in the room to be analyzed obtained in step 4 to obtain the valve opening corresponding to the required water supply flow rate, and adjust the valve opening of the room to be analyzed according to the valve opening, and then use the room temperature sensor to obtain the temperature of each functional area in the room to be analyzed at different times, and then obtain the abnormal values ​​in the temperature of each functional area in the room to be analyzed at different times, and replace the abnormal values ​​with corrected values ​​to obtain the processed temperature of each functional area in the room to be analyzed at different times, and adjust the valve opening again based on the processed temperature of each functional area in the room to be analyzed at different times.

2. According to claim 1, a method for analyzing thermal demand in severe cold regions based on building digitalization technology is characterized by: In step 4, the BIM model of the building where the indoor room to be analyzed is used to perform thermal demand analysis using the outdoor meteorological data to be analyzed and the design temperature, personnel density and equipment usage of each functional area in the indoor room to be analyzed, and the required water supply flow rate of each functional area in the indoor room to be analyzed is obtained, specifically: Step 41: Obtain the heat load of the i-th functional area of ​​the room to be analyzed at the j-th heating moment, specifically: <h2 style=";text-align:left;direction:ltr">Q<h2 style=";text-align:left;direction:ltr"> ij <h2 style=";text-align:left;direction:ltr"> =Q1<h2 style=";text-align:left;direction:ltr"> ij <h2 style=";text-align:left;direction:ltr"> +Q2<h2 style=";text-align:left;direction:ltr"> ij <h2 style=";text-align:left;direction:ltr"> +Q3<h2 style=";text-align:left;direction:ltr"> ij <h2 style=";text-align:left;direction:ltr"> -Q4<h2 style=";text-align:left;direction:ltr"> ij Q1 ij =αKA(t ij -t w j ) Q2 ij =0.278NVc p ρ w (t ij -t w j ) Q3 ij =Q1 ij (1+b c +b f +b q +b m )(1+b fg )(1+b j ) Q4 ij =η(zq r +W) Among them, Q ij is the heat load of the i-th indoor functional zone at the j-th heating moment, i∈[1,m], i is the number of the indoor functional zone to be evaluated, m is the total number of indoor functional zones to be evaluated, j∈[1,n], j is the number of the heating moment, n is the total number of heating moments, Q1 ij is the basic heat consumption of the enclosure structure at the jth heating moment in the i-th functional area, Q2 ij is the heat consumption of cold air penetration in the i-th functional area at the j-th heating moment, Q3 ij is the additional heat consumption of the building at the jth heating moment in the i-th functional area, Q4 ij is the total heat dissipation of human body and equipment in the room to be analyzed at the jth heating moment in the i-th functional zone, α is the temperature difference correction coefficient, K represents the heat transfer coefficient of the building envelope, A represents the heat transfer area of ​​the building envelope, t ij represents the design temperature of the i-th functional area of ​​the room to be analyzed at the j-th heating moment, t w j represents the average outdoor temperature at the jth heating moment, N represents the number of indoor air changes, V represents the net volume of the room, c p is the specific heat capacity of outdoor air at constant pressure, ρ w represents the outdoor air density, β c represents the preset orientation correction rate, β f Indicates the preset wind correction rate, β q Indicates the preset two-wall correction rate, β m Indicates the preset window-to-wall ratio correction rate, β fg Indicates the preset room height correction rate, β j represents the preset intermittent correction rate, η represents the preset correction rate of heat dissipation of people and equipment, z represents the number of people in the room to be analyzed, and q r It represents the heat dissipation of human body, and W represents the heat dissipation of equipment. Step 42: Use the heat load of the i-th functional area of ​​the room to be analyzed at the j-th heating moment to obtain the required water supply flow F of the i-th functional area of ​​the room to be analyzed at the j-th heating moment ij .

3. According to claim 2, a method for analyzing thermal demand in severe cold regions based on building digitalization technology is characterized by: The step 42 uses the heat load of the i-th functional zone in the room to be analyzed at the j-th heating moment to obtain the water supply flow rate F required for the i-th functional zone in the room to be analyzed at the j-th heating moment ij , specifically: F ij =Q ij / (cρΔT) Where c represents the specific heat capacity of water, ρ represents the density of water, ΔT represents the supply and return water temperature difference, F ij It is the water supply flow required for the jth heating moment of the i-th functional area in the room to be analyzed.

4. The method for analyzing thermal demand in severe cold regions based on building digitalization technology according to claim 3 is characterized by: The step 5 uses the required water supply flow rate for each functional area of ​​the room to be analyzed obtained in step 4 to obtain the valve opening corresponding to the required water supply flow rate, specifically: If the regulating valve has a fast-opening flow characteristic, the required water supply flow corresponds to the valve opening and can be obtained in the following way: Among them, F max Indicates the maximum flow rate of the valve, L ij represents the required valve opening of the i-th functional zone in the room to be analyzed at the j-th heating moment, L max Indicates the maximum opening of the valve, and R indicates the predicted adjustable ratio of the control valve; If the regulating valve has a linear flow characteristic, the required water supply flow corresponds to the valve opening and can be obtained by: If the regulating valve has an equal percentage flow characteristic, the required water supply flow corresponds to the valve opening and can be obtained by:

5. The method for analyzing thermal demand in severe cold regions based on building digitalization technology according to claim 4 is characterized by: In step 5, the room temperature sensor is used to obtain the temperature of each functional area in the room to be analyzed at different times, and then the abnormal values ​​in the temperature of each functional area in the room to be analyzed at different times are obtained, and the abnormal values ​​are replaced with the correction values ​​to obtain the processed temperature of each functional area in the room to be analyzed at different times, specifically: First, obtain the historical sequence of N historical heating moments of the i-th functional zone in the room to be analyzed, input the historical sequence of N historical heating moments of the i-th functional zone in the room to be analyzed into the trained indoor temperature prediction model, and obtain the predicted indoor temperature of the i-th functional zone at the N+1 heating moment, i.e., the correction value; The historical sequence of the N historical heating moments of the i-th functional zone includes: the indoor temperature sequence of the N historical heating moments of the i-th functional zone, the water supply temperature sequence of the N historical heating moments of the i-th functional zone, the return water temperature sequence of the N historical heating moments of the i-th functional zone, the flow sequence of the N historical heating moments of the i-th functional zone, and the outdoor temperature sequence of the N historical heating moments of the i-th functional zone; Then, the predicted indoor temperature of the ith functional area at the N+1th heating moment is compared with the actual indoor temperature of the ith functional area at the N+1th heating moment obtained by the room temperature sensor. If the indoor predicted temperature and the actual indoor temperature are within the preset first error range, the valve opening is adjusted again based on the temperatures of each functional area in the room to be analyzed at different moments after processing; otherwise, the actual indoor temperature of the ith functional area at the N+1th heating moment is replaced by the correction value, and the valve opening is adjusted again based on the temperatures of each functional area in the room to be analyzed at different moments after processing.

6. The method for analyzing thermal demand in severe cold regions based on building digitalization technology according to claim 5 is characterized by: The trained indoor temperature prediction model is obtained by: B1. Obtain the historical sequences of M historical heating moments of the i-th functional zone of the room to be analyzed respectively, and preprocess each historical sequence, and form a training set with the preprocessed historical sequence and the indoor temperature of the i-th functional zone of the room to be analyzed at the M+1-th heating moment; The historical sequence of the M historical heating moments of the i-th functional zone includes: the indoor temperature sequence of the M historical heating moments of the i-th functional zone, the water supply temperature sequence of the M historical heating moments of the i-th functional zone, the return water temperature sequence of the M historical heating moments of the i-th functional zone, the flow sequence of the M historical heating moments of the i-th functional zone, and the outdoor temperature sequence of the M historical heating moments of the i-th functional zone; B2. Use the training set to train the indoor temperature prediction model to obtain a trained indoor temperature prediction model.

7. The method for analyzing thermal demand in severe cold regions based on building digitalization technology according to claim 6 is characterized by: The preprocessing of each historical sequence in B1 is specifically as follows: A1. Obtain the missing feature data position in the m'th historical sequence of the i-th functional area, and then supplement the missing feature data position with the average value of the feature data value of the previous position and the feature data value of the next position; Wherein, m' is the historical sequence number, and m'=1, 2, 3, 4, 5 represent the indoor temperature sequence, the supply water temperature sequence, the return water temperature sequence, the flow sequence, and the outdoor temperature sequence respectively; A2, obtain the first quartile Q1, the third quartile Q3, and the interquartile range IQR of the m'th historical sequence of the i-th functional area after processing by A1; The first quartile Q1 is the 25% quantile of the m'th historical sequence of the ith functional area; The third quartile Q3 is the 75% quantile of the m'th historical sequence of the ith functional area; The interquartile range (IQR) is obtained by: IQR=Q3-Q1 A3. Use Q1, Q3 and IQR to obtain the upper and lower bounds of outliers: Outlier lower bound = Q1-1.5×IQR Outlier upper limit = Q3 + 1.5 × IQR A4. In the m'th historical sequence of the i-th functional area, the characteristic data value that is not within the range from the lower bound to the upper bound of the abnormal value is the abnormal value, and then the position of the abnormal value is obtained, and the average value of the three characteristic data values ​​before the abnormal value position and the three characteristic data values ​​after the abnormal value position is replaced into the abnormal value position, and the m'th historical sequence of the i-th functional area after the abnormal value is filled is obtained; A5. Normalize the m'th historical sequence of the ith functional area after filling the outliers to obtain the indoor temperature sequence, water supply temperature sequence, return water temperature sequence, flow sequence, and outdoor temperature sequence of the M historical heating moments of the ith functional area after preprocessing.

8. The method for analyzing thermal demand in severe cold regions based on building digitalization technology according to claim 7 is characterized by: The normalization process of the m'th historical sequence of the ith functional area after outlier filling in A5 is specifically as follows: Among them, x i,m',d is the dth characteristic data value in the m'th historical sequence of the ith functional area after outlier filling, x i ' ,m',d is the dth characteristic data value in the m'th historical sequence of the ith functional area after normalization, x i,m',min is the minimum value of the characteristic data in the m'th historical sequence of the ith functional area after outlier filling, x i,m',max It is the maximum value of the characteristic data in the m'th historical sequence of the ith functional area after outliers are filled.

9. The method for analyzing thermal demand in severe cold regions based on building digitalization technology according to claim 8 is characterized by: The indoor temperature prediction model in B2 includes: an LSTM module, an efficient additive self-attention mechanism module, and an indoor temperature prediction module; The LSTM module is an LSTM network, which is used to obtain the hidden state of the input feature vector, specifically: h j' =O j' fishy(C) j' ) The j' =σ(W o [h j'-1 ,x j' ]+b o ) f j' =σ(W f [h j'-1 ,x j' ]+b f ) i j' =σ(W i” [h j'-1 ,x j' ]+b i” ) Among them, f j is the output of the forget gate at time step j', σ is the Sigmoid activation function, W f is the forget gate weight matrix, W i” is the input gate weight matrix, W c is the cell state update weight matrix, W o is the output gate weight matrix, h j'-1 is the hidden state of the previous time step j'-1, x j' is the input feature vector of the current time step j', b f is the forget gate bias term, b i” is the input gate bias term, b c is the cell state update bias term, b o is the output gate bias term, i j' is the output of the input gate at time step j', is the candidate cell state, tanh is the hyperbolic tangent activation function, C j' Updated cell state, C j'-1 is the cell state at the previous time step j'-1, O j' is the output of the output gate at time step j', h j' is the hidden state at time step j'; The input feature vector includes: supply water temperature, return water temperature, flow rate, indoor temperature and outdoor temperature; The efficient additive self-attention mechanism module obtains the global context representation and c' according to the hidden state of the input feature vector: x' j' =Q j' +T(K j' ×q j' ) q j' =α j' Q j' Q j' =h j' W Q K j' =h j' W K Among them, x' j' is the global context representation of the j'th time step, α j' is the global attention query vector, d is the query matrix dimension, W Q , W K is the learned weight matrix, Q j' is the query vector, K j' is the key vector, W a is the preset parameter vector, q j' is a single global query vector, T is a linear transformation; The indoor temperature prediction module represents and obtains the indoor temperature prediction value according to the hidden state and global context of the input feature vector: y′=Wz′+b z'=concat[h j' ,c'] Among them, W' is the preset weight matrix, b is the bias term, and z is h j' and c', y' is the predicted value of indoor temperature.

10. The method for analyzing thermal demand in severe cold regions based on building digitalization technology according to claim 9 is characterized in that: The valve opening is adjusted again based on the temperature of each functional area in the room to be analyzed at different times after processing in step 5, specifically: Determine whether the error between the temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment after processing and the design temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment is within a preset allowable second temperature error range, if within the preset allowable second temperature error range, do not adjust the valve opening, if not within the preset allowable second temperature error range, adjust the valve opening; If it is not within the preset allowable second temperature error range, the valve opening is regulated, specifically: Find the outdoor temperature data P closest to the j-th heating moment in the historical data, and obtain the valve opening corresponding to the outdoor temperature data P; If the temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment after processing is higher than the design temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment, the minimum value of the valve opening corresponding to the outdoor temperature data P is used as the current valve opening; If the temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment after processing is lower than the design temperature of the i-th functional zone in the room to be analyzed at the j-th heating moment, the maximum value of the valve opening corresponding to the outdoor temperature data P is used as the current valve opening.

Images