Fabricated residence information processing system based on BIM

Abstract

The invention provides a BIM-based fabricated residence information processing system, and relates to the technical field of residence environment control, and the system comprises a data pre-collection module, a model training module, a data preprocessing module, a residence heat preservation model obtaining module, and a heat preservation adjustment module. The temperature control module is used for simulating the corresponding indoor temperature change and power consumption, calculating the predicted temperature difference and adjusting the real-time power of the temperature control equipment, and the humidity control module is used for adjusting the humidity in time according to the temperature difference data obtained by the heat preservation adjusting module. And meanwhile, preparation and control in advance are achieved according to the external changing environment, accurate and advanced adjustment of the humidity is achieved through temperature changes again, and energy consumption is accurately controlled while it is guaranteed that the environment is suitable.

Description

Technical Field

[0001] The present invention relates to the technical field of residential environment control, and specifically to an information processing system for prefabricated residences based on BIM. Background Art

[0002] Currently, with the continuous development of construction technology, prefabricated residences have received increasing attention due to advantages such as fast construction speed and controllable quality. However, the environmental control systems of prefabricated residences, such as temperature and humidity regulation, still face many challenges. Traditional residential environment regulation systems mostly rely on fixed temperature control and humidity control parameters, making it difficult to respond in real time to changes in the external environment and the comfort requirements of indoor occupants, resulting in excessive energy consumption or poor indoor comfort. In addition, due to the structural characteristics of prefabricated residences, their heat conduction and humidity regulation behaviors are significantly different from those of traditional buildings, and a more intelligent system is needed to accurately simulate and control the internal environmental conditions.

[0003] In the prior art, the publication number CN202410829262.2 discloses a method and system for energy consumption control of intelligent buildings based on BIM. Based on a building structure data set, a building model is constructed using BIM technology, and the physical structure, geographical location, and equipment parameters of the building are analyzed, including the window position, thermal performance of wall materials, and air conditioning configuration parameters, to generate building parameter analysis results; based on the building parameter analysis results, energy efficiency simulations are performed on multiple building designs, the energy consumption data of multiple building designs are analyzed and compared to obtain energy consumption optimization design parameters; based on the energy consumption optimization design parameters, by analyzing historical energy consumption data and real-time input data, energy consumption patterns are predicted and identified, the energy usage trend is evaluated to obtain energy consumption prediction information; based on the energy consumption prediction information, the energy usage situation is monitored in real time, compared with a preset energy consumption threshold, and a warning is issued for energy consumption data outside the normal range to generate real-time energy monitoring data; based on the real-time energy monitoring data, combined with real-time meteorological information, user behavior patterns, and energy supply information, the impact of meteorological changes on the energy consumption trend and pattern is analyzed to obtain environmental impact analysis data; based on the environmental impact analysis data, the operating parameters of the air conditioner and lighting are adjusted in real time by monitoring the indoor temperature and lighting level to generate building energy consumption control parameters.

[0004] Although the above information disclosed in the background art realizes the control of internal environmental factors of residences, it fails to achieve the effect of making preparations in advance for environmental changes, lacks specific implementation methods, and the environmental regulation inside the residence is not timely when dealing with environmental changes. Summary of the Invention

[0005] The purpose of the present invention is to provide an information processing system for prefabricated residences based on BIM to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A BIM-based information processing system for prefabricated houses, comprising:

[0008] A temperature data pre-collection module for real-time monitoring of the temperature in the house to determine whether the preset comfortable temperature T is reached 0 , if the temperature does not meet the requirements, the temperature control device will start to adjust at the maximum power. At the same time, the BIM system simulates the change of indoor temperature and the corresponding power consumption, generates a data set at equal time intervals, and adds a timestamp to each data point to ensure temporal consistency;

[0009] A model training module for preprocessing and normalizing the collected data, extracting the indoor temperature difference feature and the outdoor real temperature difference feature, which respectively represent the difference between the real indoor temperature and the simulated indoor temperature, and the difference between the real indoor temperature and the outdoor temperature, and inputting the features into a linear regression model for training, updating the parameters by the gradient descent method, and obtaining a house insulation model;

[0010] A heat preservation adjustment module for, after the temperature control device adjusts the indoor temperature to a suitable state, the BIM system obtains the predicted outdoor temperature data for the next hour from the weather station through the network, simulates the corresponding indoor temperature change and power consumption in the simulation, calculates the predicted temperature difference, and adjusts the real-time power of the temperature control device based on this;

[0011] A humidity control module for controlling the indoor humidity. The BIM system obtains the residential space volume data and obtains the air humidity data through the network, judges the real temperature change situation inside the house based on the temperature difference data obtained by the heat preservation model and the simulated indoor temperature data, and adjusts the indoor humidity situation in real time according to the air humidity change at different temperatures.

[0012] Further, the data pre-collection module monitors the temperature in the house in real time, detects whether the indoor temperature is the human comfort temperature T 0 , if it is not the human comfort temperature, the temperature control device is controlled to adjust at the maximum power, the inside of the house is simulated in the BIM system simulation, and the simulated indoor temperature growth data and the simulated power consumption data are obtained. The simulated indoor temperature growth data and the simulated power consumption data form a data set at equal time intervals and are added with timestamps, and the timestamps of the simulated indoor temperature growth data set are aligned with the timestamps of the simulated power consumption data set:

[0013] MNSNT = {MTn t1 , MTn t2 , MTn t3 , …, MTn ti , …, MTn tn}

[0014] MNHDL = {Qm t1 , Qm t2 , Qm t3 , …, Qm ti , …, Qm tn}

[0015] Among them, MNSNT is the indoor temperature simulated growth data set, MTn ti is the simulated indoor temperature at time point ti, MNHDL is the power consumption simulated data set, Qm ti is the simulated power consumption at time point ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0016] When the temperature control device starts to adjust the indoor temperature, collect outdoor temperature data at equal time intervals, add time stamps, and the time interval of the outdoor temperature data is the same as that of the indoor temperature simulated growth data and is time stamp aligned to form the outdoor temperature data set SWT:

[0017] SWT = {Tw t1 , Tw t2 , Tw t3 , …, Tw ti , …, Tw tn}

[0018] Among them, Tw ti, is the outdoor temperature value at time point ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0019] Continuously collect temperature data, collect real indoor temperature data at equal time intervals, add time stamps, and the time interval for collecting real indoor temperature data is the same as that for collecting outdoor temperature data and is time stamp aligned to form the real indoor temperature data set SNT:

[0020] SNT = {Tn t1 , Tn t2 , Tn t3 , …, Tn ti , …, Tn tn}

[0021] Among them, Tn ti, is the indoor temperature value at time point ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n.

[0022] Further, the model training module collects a dataset for model training, preprocesses and normalizes the data, and extracts features, including indoor temperature difference features and outdoor true temperature difference features, to form an indoor temperature difference feature set NWC. The formula is as follows:

[0023] ΔTn ti =Tn ti -MTn ti

[0024] NWC={ΔTn t1 ,ΔTn t2 ,ΔTn t3 ,…,ΔTn ti ,…,ΔTn tn}

[0025] Where ΔTn ti is the difference between the indoor true temperature and the indoor simulated temperature at time ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0026] Obtain an outdoor true temperature difference feature set ZWC. The formula is as follows:

[0027] ΔT ti =Tn ti -Tw ti

[0028] ZWC={ΔT t1 ,ΔT t2 ,ΔT t3 ,…,ΔT ti ,…,ΔT tn}

[0029] Where ΔT ti is the difference between the indoor true temperature and the outdoor temperature at time point ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0030] Take 80% of all datasets as the training set and 20% as the test set. Select the indoor temperature difference feature as the target variable and use a linear regression model. The formula is as follows

[0031] ΔTy ti =β 0 +β 1 ΔT ti +β 2 (ΔT ti ) 2

[0032] Where ΔTy ti is the predicted value of the model for the indoor temperature difference, β 0, β 1 , β 2 are model coefficients, preset to 1.

[0033] Furthermore, a loss function is set, and the formula is as follows:

[0034]

[0035] Among them, J(β) is the loss function of the model coefficients, n is the number of samples, i is the retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0036] The model parameters are updated by the gradient descent method, and the formula is as follows:

[0037]

[0038] Among them, is the gradient of the loss function with respect to the parameter β j , j is the retrieval variable of the model coefficients, j ∈ Z, 0 ≤ j ≤ 2, and α is the learning rate;

[0039] Set the loss function threshold. When the loss function value is less than the loss function threshold for 10 consecutive times, it is judged that the model tends to be stable, otherwise continue to train in the training set;

[0040] The model that has completed training and passed the test set is calibrated as the residential insulation model.

[0041] Furthermore, after the temperature control device controls the indoor temperature to a comfortable state for the human body, the BIM system obtains the time series of the outdoor temperature in the next hour in this area from the weather station through the network and forms a data set SWTT:

[0042] SWTT = {TTw t1 , TTw t2 , TTw t3 , …, TTw ti , …, TTw tn}

[0043] Among them, TTw ti, is the outdoor temperature value at the ti time point, ti is the i-th time point, and i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0044] The BIM system simulates the time series of the indoor simulated temperature in the insulation state under the operation of the temperature control device in the next hour and forms a data set MNSNTT:

[0045] MNSNTT = {MTTn t1 , MTTn t2 , MTTn t3 , …, MTTn ti, …, MTTn tn}

[0046] MTTn ti is the simulated indoor temperature at time point ti, where ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0047] Generate a time series of simulated power consumption data for the temperature control device for the next hour and generate a data set MNHDLL:

[0048] MNHDLL = {QLm t1 , QLm t2 , QLm t3 , …, QLm ti , …, QLm tn}

[0049] where QLm ti is the simulated power consumption at time point ti, where ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0050] The outdoor temperature data set SWTT, the indoor simulated temperature data set MNSNTT, and the simulated power consumption data set MNHDLL are aligned in time and input into the residential insulation model to obtain the temperature difference data set NWCC:

[0051] NWCC = {ΔTTn t1 , ΔTTn t2 , ΔTTn t3 , …, ΔTTn ti , …, ΔTTn tn}

[0052] where ΔTTn ti is the difference between the indoor actual temperature and the indoor simulated temperature at time ti, where ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0053] The power of the temperature control device is corrected by the indoor predicted temperature difference to obtain the actual power of the temperature control device, and the basis formula is as follows:

[0054]

[0055] where P ti is the actual power of the temperature control device, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n, η is the efficiency of the temperature control device, and k is the proportionality coefficient;

[0056] The insulation adjustment module performs temperature control according to the actual power of the temperature control device.

[0057] Further, the BIM system calculates the volume of the space inside the residence, obtains air humidity data from the cyber space. The air humidity data includes the saturated water vapor pressure and the human comfort water vapor pressure data at various temperatures. The humidity control module collects the relative humidity inside the residence in real time, controls the air moisture by the humidity control device according to the temperature change, and obtains the water vapor pressure at each temperature. The formula is as follows:

[0058]

[0059] Wherein, is MTTn ti +ΔTTn ti The water vapor pressure at the temperature, is MTTn ti +ΔTTn ti The relative humidity at the temperature, e s (MTTn ti +ΔTTn ti ) is the saturated water vapor pressure at the temperature of MTTn ti +ΔTTn ti ;

[0060]

[0061] Wherein, is the amount of water needed for humidification at the temperature of MTTn ti +ΔTTn ti . When W≤0, is the amount of water needed for dehumidification. V is the volume of the residence, is the human comfort water vapor pressure at the temperature of MTTn ti +ΔTTn ti . R is the water vapor constant;

[0062] The humidity control module controls the humidity according to the data.

[0063] Compared with the prior art, the beneficial effects of the present invention are:

[0064] By judging the heat preservation effect inside the residence at different temperatures during the temperature control process, the present invention can better control the internal temperature, and at the same time, make preparations and control in advance according to the external changing environment. By using the temperature change again, it can achieve precise and pre-adjusted humidity regulation, ensuring a suitable environment while precisely controlling energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 is a schematic structural diagram of the system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0066] To make the objectives, technical solutions, and advantages of the present invention more clear and understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0067] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meaning understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0068] Embodiment:

[0069] Please refer to Figure 1 , the present invention provides a technical solution:

[0070] A BIM-based information processing system for prefabricated houses, specifically including:

[0071] A data pre-collection module, used to monitor the temperature in the house in real time to determine whether it reaches the preset comfortable temperature T 0 , if the temperature does not meet the requirements, the temperature control device will start to adjust at the maximum power. At the same time, the BIM system simulates the change of indoor temperature and the corresponding power consumption, generates a data set at equal time intervals, and adds a timestamp to each data point to ensure temporal consistency;

[0072] A model training module, used to preprocess and normalize the collected data, extract the indoor temperature difference feature and the outdoor real temperature difference feature, which respectively represent the difference between the real indoor temperature and the simulated indoor temperature, and the difference between the real indoor temperature and the outdoor temperature, and input the features into a linear regression model for training, update the parameters through the gradient descent method, and obtain a house insulation model;

[0073] An insulation adjustment module, used to when the temperature control device adjusts the indoor temperature to an appropriate state, the BIM system obtains the predicted outdoor temperature data for the next hour from the weather station through the network, simulates the corresponding indoor temperature change and power consumption in the simulation, calculates the predicted temperature difference, and adjusts the real-time power of the temperature control device based on this;

[0074] The humidity control module is used to control the indoor humidity. The BIM system obtains the residential space volume data and the air humidity data through the network, and judges the real temperature change situation inside the residence based on the temperature difference data obtained through the thermal insulation model and the simulated indoor temperature data, and adjusts the indoor humidity situation in real time according to the air humidity change at different temperatures.

[0075] Step 1: The data pre-collection module monitors the temperature inside the residence in real time and detects whether the indoor temperature is the human comfort temperature T 0 , if it is not the human comfort temperature, then control the temperature control device to adjust at the maximum power, simulate the inside of the residence in the BIM system simulation, and obtain the simulated indoor temperature growth data and the simulated power consumption data. The simulated indoor temperature growth data and the simulated power consumption data form an equal-time interval data set and add time stamps, and the time stamps of the simulated indoor temperature growth data set are aligned with the time stamps of the simulated power consumption data set:

[0076] MNSNT = {MTn t1 , MTn t2 , MTn t3 , …, MTn ti , …, MTn tn}

[0077] MNHDL = {Qm t1 , Qm t2 , Qm t3 , …, Qm ti , …, Qm tn}

[0078] Among them, MNSNT is the simulated indoor temperature growth data set, MTn ti is the simulated indoor temperature at the ti time point, MNHDL is the simulated power consumption data set, Qm ti is the simulated power consumption at the ti time point, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0079] When the temperature control device starts to adjust the indoor temperature, collect the outdoor temperature data at equal time intervals, add time stamps, and the time interval of the outdoor temperature data is the same as that of the simulated indoor temperature growth data and the time stamps are aligned to form the outdoor temperature data set SWT:

[0080] SWT = {Tw t1 , Tw t2 , Tw t3 , …, Tw ti , …, Tw tn}

[0081] Among them, Tw ti,The outdoor temperature value at time point ti, where ti is the i-th time point, i is the time point retrieval variable, i ∈ N, and 1 ≤ i ≤ n;

[0082] Continuously collect temperature data, collect real indoor temperature data at equal time intervals, add time stamps, and ensure that the time interval for collecting real indoor temperature data is the same as that for collecting outdoor temperature data and the time stamps are aligned, forming a real indoor temperature data set SNT:

[0083] SNT = {Tn t1 , Tn t2 , Tn t3 , …, Tn ti , …, Tn tn}

[0084] where Tn ti, is the indoor temperature value at time point ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, and 1 ≤ i ≤ n.

[0085] Collecting and aligning the house temperature data is conducive to the establishment of the model, and through the simulation of the BIM system, the differences between the system recognition situation and the actual situation can be intuitively obtained, and a more perfect information management system can be further established based on the differences.

[0086] Step 2: The model training module collects the data set for model training, preprocesses and normalizes the data, and extracts features. The features include indoor temperature difference features and outdoor real temperature difference features, forming an indoor temperature difference feature set NWC. The formula is as follows:

[0087] ΔTn ti = Tn ti - MTn ti

[0088] NWC = {ΔTn t1 , ΔTn t2 , ΔTn t3 , …, ΔTn ti , …, ΔTn tn}

[0089] where ΔTn ti is the difference between the real indoor temperature and the simulated indoor temperature at time point ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, and 1 ≤ i ≤ n;

[0090] Obtain an outdoor real temperature difference feature set ZWC. The formula is as follows:

[0091] ΔT ti = Tn ti - Tw ti

[0092] ZWC = {ΔT t1 , ΔT t2 , ΔT t3 , …, ΔT ti , …, ΔT tn}

[0093] Among them, ΔT ti is the difference between the indoor actual temperature and the outdoor temperature at the time point ti, where ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0094] Take 80% of all data sets as the training set and 20% as the test set. Select the indoor temperature difference feature as the target variable and use the linear regression model. The formula is as follows

[0095] ΔTy ti = β 0 + β 1 ΔT ti + β 2 (ΔT ti ) 2

[0096] Among them, ΔTy ti is the predicted value of the model for the indoor temperature difference, and β 0 , β 1 , β 2 are the model coefficients, preset to 1.

[0097] Step 3: Set the loss function. The formula is as follows:

[0098]

[0099] Among them, J(β) is the loss function of the model coefficients, n is the number of samples, i is the retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0100] Update the model parameters by the gradient descent method. The formula is as follows:

[0101]

[0102] Among them, is the gradient of the loss function with respect to the parameter β j , j is the retrieval variable of the model coefficients, j ∈ Z, 0 ≤ j ≤ 2, and α is the learning rate;

[0103] Set the loss function threshold. When the loss function value is less than the loss function threshold for 10 consecutive times, it is judged that the model tends to be stable, otherwise continue to train in the training set;

[0104] Calibrate the model that has completed training and passed the test set as the residential insulation model.

[0105] By training the model with data in the initial stage of temperature control, a model with a small amount of data and simple application can be quickly obtained and deployed. Importantly, a model adapted to each residence can be individually formed, achieving precise control while realizing personalization.

[0106] Step 4: After the temperature control device controls the indoor temperature to a comfortable state for the human body, the BIM system obtains the time series of the outdoor temperature in the next hour in this area from the weather station through the network and forms a data set SWTT:

[0107] SWTT = {TTw t1 ,TTw t2 ,TTw t3 ,…,TTw ti ,…,TTw tn}

[0108] where TTw ti, is the outdoor temperature value at time point ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0109] The BIM system simulates the time series of the indoor simulated temperature in the heat preservation state under the operation of the temperature control device in the next hour and forms a data set MNSNTT:

[0110] MNSNTT = {MTTn t1 ,MTTn t2 ,MTTn t3 ,…,MTTn ti ,…,MTTn tn}

[0111] MTTn ti is the simulated indoor temperature at time point ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0112] Generate the time series of the simulated power consumption data of the temperature control device in the next hour and generate a data set MNHDLL:

[0113] MNHDLL = {QLm t1 ,QLm t2 ,QLm t3 ,…,QLm ti ,…,QLm tn}

[0114] where QLm ti is the simulated power consumption at time point ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0115] The outdoor temperature dataset SWTT, the indoor simulated temperature dataset MNSNTT, and the simulated power consumption dataset MNHDLL are aligned at time points and input into the residential insulation model to obtain the temperature difference dataset NWCC:

[0116] NWCC = {ΔTTn t1 , ΔTTn t2 , ΔTTn t3 , …, ΔTTn ti , …, ΔTTn tn}

[0117] Among them, ΔTTn ti is the difference between the indoor actual temperature and the indoor simulated temperature at time ti, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n;

[0118] The power of the temperature control device is corrected by the indoor predicted temperature difference to obtain the actual power of the temperature control device. The formula is as follows:

[0119]

[0120] Among them, P ti is the real-time power of the temperature control device, ti is the i-th time point, i is the time point retrieval variable, i ∈ N, 1 ≤ i ≤ n, η is the efficiency of the temperature control device, obtained through the specification, and k is the proportionality coefficient, determined by personnel;

[0121] The power of the temperature control device predicted by the BIM system is the ratio of the power consumption per unit time to the product of the efficiency and time. However, due to the difference in the insulation performance of the house, the power of the temperature control device needs to be adjusted according to the actual situation. By dividing the temperature difference at a specific temperature by the coefficient, the power of the temperature control device can be adjusted by the influence of the insulation performance, and early control can be achieved by collecting data from the weather station.

[0122] The insulation adjustment module controls the temperature according to the real-time power of the temperature control device.

[0123] Step 5: The BIM system calculates the volume of the space in the residence and obtains the air humidity data from the network space. The air humidity data includes the saturated water vapor pressure and the human comfort water vapor pressure data at each temperature. The humidity control module collects the relative humidity in the residence in real time and controls the air moisture by the humidity control device as the temperature changes to obtain the water vapor pressure at each temperature. The formula is as follows:

[0124]

[0125] Among them, is MTTn ti +ΔTTn tiVapor pressure of water at a temperature is MTTn ti + ΔTTn ti Relative humidity at a temperature, e s (MTTn ti + ΔTTn ti ) is MTTn ti + ΔTTn ti Saturated water vapor pressure at a temperature;

[0126]

[0127] wherein, is the amount of water needed for humidification at MTTn ti + ΔTTn ti temperature. When W ≤ 0, is the amount of water needed for dehumidification. V is the volume of the residence, is the comfortable water vapor pressure of the human body at MTTn ti + ΔTTn ti temperature, and R is the water vapor constant;

[0128] The humidity control module performs humidity control according to data.

[0129] Through the real-time control of temperature by the residential insulation model and the BIM system, and by obtaining in advance the indoor temperature change situation, the humidity is controlled according to the specific temperature at each time point, so that the humidity inside the residence can always be in the most suitable stage whether the residence is in the temperature adjustment stage or the temperature stable stage.

[0130] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0131] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0132] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, and it may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] As described above, the specific implementation manners of the present application are only provided, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. The BIM-based prefabricated housing information processing system is characterized by: include: The data pre-collection module is used to monitor the temperature in the residence in real time to determine whether the preset comfort temperature T0 is reached. If the temperature does not meet the requirements, the temperature control device will start to adjust at maximum power. At the same time, the BIM system simulates the changes in indoor temperature and the corresponding power consumption, generates data sets with equal time intervals, and adds a timestamp to each data point to ensure temporal consistency; The model training module is used to pre-process and normalize the collected data, extract the indoor temperature difference feature and the outdoor real temperature difference feature, which respectively represent the difference between the real indoor temperature and the simulated indoor temperature, and the difference between the real indoor temperature and the outdoor temperature, and input the features into the linear regression model for training, update the parameters through the gradient descent method, and obtain the residential insulation model; The insulation adjustment module is used to obtain the outdoor temperature forecast data for the next hour from the weather station through the network after the temperature control device adjusts the indoor temperature to a suitable state, simulate the corresponding indoor temperature changes and power consumption in the simulation, calculate the predicted temperature difference, and adjust the real-time power of the temperature control device based on this; The humidity control module is used to control the indoor humidity. The BIM system obtains the residential space volume data and the air humidity data through the network. The temperature difference data obtained by the insulation model and the simulated indoor temperature data are used to determine the actual temperature changes inside the residence. The indoor humidity is adjusted in real time according to the changes in air humidity at different temperatures.

2. The BIM-based prefabricated housing information processing system according to claim 1, characterized in that: The data pre-collection module monitors the temperature in the residence in real time, detects whether the indoor temperature is the human body comfortable temperature T0, and controls the temperature control device to adjust at maximum power if it is not the human body comfortable temperature. The interior of the residence is simulated in the BIM system simulation, and indoor temperature simulation growth data and power consumption simulation data are obtained. The indoor temperature simulation growth data and power consumption simulation data form equal time interval data sets and add timestamps. The timestamp of the indoor temperature simulation growth data set is aligned with the timestamp of the power consumption simulation data set: MNSNT={MTn t1 ,MTn t2 ,MTn t3 ,…,MTn ti ,…,MTn tn } MNHDL={Qm t1 ,Qm t2 ,Qm t3 ,…,Qm ti ,…,Qm tn } Among them, MNSNT is the indoor temperature simulation growth data set, MTn ti is the simulated indoor temperature at time point ti, MNHDL is the power consumption simulation data set, Qm ti is the simulated power consumption at time point ti, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n; When the temperature control device starts to adjust the indoor temperature, it collects outdoor temperature data at equal time intervals and adds timestamps. The time interval of the outdoor temperature data is the same as the time interval of the indoor temperature simulation growth data and the timestamps are aligned to form the outdoor temperature data set SWT: SWT={Tw t1 ,Tw t2 ,Tw t3 ,…,Tw ti ,…,Tw tn } Among them, Tw ti, is the outdoor temperature value at time point ti, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n; Continuously collect temperature data, collect real indoor temperature data at equal time intervals, add timestamps, and make the time interval for collecting real indoor temperature data the same as the time interval for collecting outdoor temperature data and align the timestamps to form a real indoor temperature data set SNT: SNT={Tn t1 ,Tn t2 ,Tn t3 ,…,Tn ti ,…,Tn tn } Among them, Tn ti, is the indoor temperature value at time point ti, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n.

3. The BIM-based prefabricated housing information processing system according to claim 1, characterized in that: The model training module collects data sets for model training, preprocesses and normalizes the data, and extracts features, including indoor temperature difference features and outdoor real temperature difference features, to form an indoor temperature difference feature set NWC, based on the following formula: ΔTn ti =Tn ti -MTn ti NWC={ΔTn t1 ,ΔTn t2 ,ΔTn t3 ,…,ΔTn ti ,…,ΔTn tn } Among them, ΔTn ti is the difference between the real indoor temperature and the simulated indoor temperature at time ti, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n; The outdoor real temperature difference feature set ZWC is obtained based on the following formula: ΔT ti =Tn ti -Tw ti ZWC={ΔT t1 ,ΔT t2 ,ΔT t3 ,…,ΔT ti ,…,ΔT tn } Where, ΔT ti is the difference between the real indoor temperature and the outdoor temperature at time point ti, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n; 80% of all data sets are used as training sets and 20% as test sets. The indoor temperature difference feature is selected as the target variable. The linear regression model is used. The formula is as follows: ΔTy ti =β0+β1ΔT ti +β2(ΔT ti ) 2 Among them, ΔTy ti is the model's predicted value for the indoor temperature difference, β0, β1, and β2 are model coefficients, which are preset to 1.

4. The BIM-based prefabricated housing information processing system according to claim 3 is characterized by: The loss function is set based on the following formula: Among them, J(β) is the loss function of the model coefficient, n is the number of samples, i is the retrieval variable, i∈N, 1≤i≤n; The model parameters are updated by the gradient descent method, based on the following formula: in, is the loss function for the parameter β j The gradient of , j is the retrieval variable of the model coefficient, j∈Z, 0≤j≤2, α is the learning rate; Set the loss function threshold. When the loss function value is less than the loss function threshold for 10 consecutive times, the model is considered to be stable. Otherwise, continue training in the training set. The model that has completed training and passed the test set is calibrated as the residential insulation model.

5. The BIM-based prefabricated housing information processing system according to claim 4 is characterized in that: After the temperature control device controls the indoor temperature to a state suitable for human body, the BIM system obtains the time series of outdoor temperature in the next hour from the weather station through the network and forms the data set SWTT: <h2 style=";text-align:left;direction:ltr">SWTT = {TTw<h2 style=";text-align:left;direction:ltr"> t1 <h2 style=";text-align:left;direction:ltr"> TTw<h2 style=";text-align:left;direction:ltr"> t2 <h2 style=";text-align:left;direction:ltr"> TTw<h2 style=";text-align:left;direction:ltr"> t3 <h2 style=";text-align:left;direction:ltr"> ,…,TTw<h2 style=";text-align:left;direction:ltr"> ti <h2 style=";text-align:left;direction:ltr"> ,…,TTw<h2 style=";text-align:left;direction:ltr"> tn <h2 style=";text-align:left;direction:ltr">} Among them, TTw ti, is the outdoor temperature value at time point ti, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n; The BIM system simulates the time series of the indoor simulated temperature in the insulation state under the operation of the temperature control equipment in the next hour and forms the data set MNSNTT: MNSNTT={MTTn t1 ,MTTn t2 ,MTTn t3 ,…,MTTn ti ,…,MTTn tn } MTTn ti is the simulated indoor temperature at time point ti, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n; Generate a time series of simulated data on the power consumption of the temperature control equipment for the next hour and generate the data set MNHDLL: MNHDLL={QLm t1 ,QLm t2 ,QLm t3 ,…,QLm ti ,…,QLm tn } Among them, QLm ti is the simulated power consumption at time point ti, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n; The outdoor temperature dataset SWTT, the indoor simulated temperature dataset MNSNTT, and the simulated power consumption dataset MNHDLL are aligned at the time point and input into the residential insulation model to obtain the temperature difference dataset NWCC: NWCC={ΔTTn t1 ,ΔTTn t2 ,ΔTTn t3 ,…,ΔTTn ti ,…,ΔTTn tn } Among them, ΔTTn ti is the difference between the real indoor temperature and the simulated indoor temperature at time ti, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n; The power of the temperature control equipment is corrected by the predicted indoor temperature difference to obtain the implemented power of the temperature control equipment. The formula is as follows: Among them, P ti is the real-time power of the temperature control device, ti is the i-th time point, i is the time point retrieval variable, i∈N, 1≤i≤n, η is the efficiency of the temperature control device, and k is the proportional coefficient; The insulation adjustment module performs temperature control according to the real-time power of the temperature control equipment.

6. The BIM-based prefabricated housing information processing system according to claim 5 is characterized in that: The BIM system counts the volume of the residential space and obtains air humidity data from the network space. The air humidity data includes the saturated water vapor pressure at each temperature and the human body comfort water vapor pressure data. The humidity control module collects the relative humidity in the house in real time, controls the humidity control device to control the air moisture as the temperature changes, and obtains the water vapor pressure at each temperature. The formula is as follows: in, MTTn ti +ΔTTn ti Water vapor pressure at temperature, MTTn ti +ΔTTn ti Relative humidity at temperature, e s (MTTn ti +ΔTTn ti ) is MTTn ti +ΔTTn ti Saturated water vapor pressure at temperature; in, For MTTn ti +ΔTTn ti The amount of water required for humidification when the temperature is W≤0, is the amount of water to be dehumidified, V is the volume of the house, For MTTn ti +ΔTTn ti The comfortable water vapor pressure for the human body at temperature, R is the water vapor constant; Humidity control module according to Data for humidity control.

Images