Intelligent building environment comfort level optimization system and method based on Internet of Things

Abstract

The invention discloses an intelligent building environment comfort degree optimization system and method based on the Internet of Things, relates to the technical field of intelligent buildings, and solves the technical problem that the experience feeling of a user in a building environment is poor due to the lack of consideration on dynamic response capability and personalized comfort degree of environment change in the prior art. Predicting an indoor person existence moment through a time prediction model; calculating an indoor comfort index through the indoor environment data; calculating equipment adjustment parameters according to the indoor comfort index and the indoor environment data; when a person exists in the indoor environment, calculating a person influence coefficient according to the indoor person data; according to the personnel influence coefficient and the indoor environment data, the equipment adjustment parameter is dynamically calculated, the time when the user arrives at the interior of the building is predicted, the indoor environment is adjusted to be in the state of the optimal environment comfort degree in advance, when the number of people in the room is large, the comfort degree index is dynamically adjusted, the influence of the number of people on equipment adjustment is considered, and the user experience is improved.

Description

Technical Field

[0001] The present application belongs to the field of intelligent building technology, and specifically to an intelligent building environment comfort optimization system and method based on the Internet of Things. Background Art

[0002] Intelligent buildings are buildings that use buildings as platforms and are based on the comprehensive application of various intelligent information. They integrate architecture, systems, applications, management and optimization. They have the comprehensive wisdom of perception, transmission, memory, reasoning, judgment and decision-making, forming an integrated body that coordinates people, buildings and the environment, and provide people with a safe, efficient, convenient and sustainable functional environment. Environmental comfort refers to whether people feel comfortable in the natural environment and the degree to which they feel comfortable without taking any special measures to keep warm or cool. It has an important impact on people's quality of life, work efficiency and health. Optimizing comfort can not only enhance people's sense of happiness, but also help improve work efficiency and reduce the occurrence of diseases.

[0003] With the rapid development of Internet of Things technology, smart buildings have become an important direction for improving the quality of urban life. However, most of the existing smart building environmental control systems rely on manual settings or simple preset rules for regulation, lacking the ability to dynamically respond to environmental changes and personalized comfort considerations, resulting in poor user experience in the building environment; therefore, the smart building environmental comfort optimization system still needs further improvement. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes an intelligent building environment comfort optimization system and method based on the Internet of Things, which is used to solve the technical problem that the prior art lacks the ability to dynamically respond to environmental changes and personalized comfort considerations, resulting in a poor user experience in the building environment.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides an intelligent building environment comfort optimization system based on the Internet of Things, comprising: a data acquisition module, a data analysis module, a control module, an early warning module and a database;

[0006] The data acquisition module is used to acquire indoor environment data and indoor personnel data through data acquisition equipment;

[0007] The data analysis module: predicts the time when people are present indoors through a time prediction model, wherein the time prediction model is constructed through an LSTM model; calculates an indoor comfort index through indoor environmental data; calculates equipment adjustment parameters based on the indoor comfort index and indoor environmental data; calculates a personnel influence coefficient based on indoor personnel data when there are people in the indoor environment; dynamically calculates equipment adjustment parameters based on the personnel influence coefficient and indoor environmental data; and generates an alarm signal based on the indoor comfort index;

[0008] The control module: assigns the device adjustment parameters to the corresponding device parameters;

[0009] The early warning module: makes prompts according to the alarm signal and contacts the management personnel.

[0010] The present application predicts the time when people are present indoors through a time prediction model; calculates an indoor comfort index through indoor environmental data; calculates equipment adjustment parameters based on the indoor comfort index and indoor environmental data; when there are people in the indoor environment, calculates the personnel impact coefficient based on the indoor personnel data; dynamically calculates equipment adjustment parameters based on the personnel impact coefficient and indoor environmental data; generates an alarm signal based on the indoor comfort index, predicts the time when the user arrives in the building, adjusts the indoor environment to the state of optimal environmental comfort in advance, and dynamically adjusts the comfort index when there are a large number of people indoors, taking into account the impact of the number of people on equipment adjustment, thereby improving the user experience.

[0011] Furthermore, the time prediction model is constructed by using an LSTM model, including:

[0012] Obtain some historical outdoor environment data, time characteristics and time tags;

[0013] Performing data preprocessing on a number of historical outdoor environment data, time features, and time tags to obtain a number of preprocessed historical outdoor environment data, time features, and time tags;

[0014] Integrate historical outdoor environment data and time features with the same time tags into a time vector;

[0015] Integrate each time vector into several prediction sequences according to the order of time labels;

[0016] Divide several prediction sequences into training set, test set and validation set according to the order of time labels;

[0017] Select the LSTM model as the base model;

[0018] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0019] By verifying the pre-trained model on the test set, we finally obtain a time prediction model whose input is outdoor environment data and time features and whose output is time labels.

[0020] Furthermore, the indoor comfort index is calculated using indoor environment data, including:

[0021] Obtain the interior temperature NW, interior light intensity NGQ and interior sound level NSB in the indoor environment data and their corresponding optimum interior temperature SNW, optimum interior light intensity SNGQ and optimum interior sound level SNSB, as well as the indoor environment data priority;

[0022] When the internal sound barrier is less than the optimum internal sound barrier, the internal sound barrier impact value NSBY=0; otherwise, the internal sound barrier impact value is the absolute value of the difference between the internal sound barrier and the optimum internal sound barrier;

[0023] By formula Calculate the indoor comfort index NSZ; wherein α1, α2 and α3 are weight coefficients, α1, α2 and α3∈(0,1), and the weight coefficients are calculated according to the priority of indoor environment data; DW is unit temperature, DGQ is unit light intensity, and DSB is unit sound bezel.

[0024] The present application calculates the indoor comfort index by using the internal temperature, internal light intensity and internal sound level in the indoor environment data, calculates the indoor comfort index with multi-source data and uses it to measure the user experience, and can dynamically adjust the equipment with more accurate indicators, thereby improving the accuracy of the dynamic adjustment of the equipment.

[0025] Furthermore, the weight coefficient is calculated according to the priority of the indoor environment data, including:

[0026] Obtaining the internal temperature NW, internal light intensity NGQ and internal sound shell NSB in the indoor environment data and their corresponding internal temperature priority NWYJ, internal light intensity priority NGQYJ and internal sound shell priority NSBYJ; the indoor environment priority is custom constructed by user preference;

[0027] The weight coefficient α1 corresponding to the internal temperature is calculated by the formula α1=NWYJ / (NWYJ+NGQYJ+NSBYJ);

[0028] The weight coefficient α2 corresponding to the internal illumination intensity is calculated by the formula α2=NGQYJ / (NWYJ+NWYJ+NSBYJ);

[0029] The weight coefficient α3 corresponding to the inner sound shell is calculated by the formula α3=NSBYJ / (NWYJ+NWYJ+NGQYJ).

[0030] Furthermore, the step of calculating the equipment adjustment parameters according to the indoor comfort index and the indoor environment data includes:

[0031] Obtain indoor comfort index NSZ, indoor environment data and indoor environment data priority;

[0032] When the indoor comfort index is greater than the comfort threshold, no action is taken;

[0033] Otherwise, the internal temperature influence coefficient NWYX, the internal light intensity influence coefficient NGQYX and the internal sound shell influence coefficient NSBYX are calculated according to the indoor environment data priority and the indoor environment data;

[0034] Get the maximum values ​​of NWYX, NGQYX and NSBYX in sequence;

[0035] When the maximum value is NSBYX, determine whether the window state is closed; if yes, generate an indoor noise source alarm signal; if no, set the window state to closed and calculate the indoor comfort index again; when the indoor comfort index is less than the comfort threshold, generate an indoor noise source alarm signal; otherwise, do nothing;

[0036] When the maximum value is NWYX, the output temperature of the temperature control device is set to SNW; and the indoor comfort index is calculated again. When the indoor comfort index is greater than the comfort threshold, no operation is performed;

[0037] When the maximum value is NGQYX, the output light intensity of the light intensity control device is set to SNGQ; and the indoor comfort index is calculated again. When the indoor comfort index is greater than the comfort threshold, no operation is performed.

[0038] Further, the calculation of the internal temperature influence coefficient NWYX, the internal light intensity influence coefficient NGQYX and the internal sound wave influence coefficient NSBYX according to the indoor environment data priority and the indoor environment data includes:

[0039] Obtain the internal temperature NW, internal light intensity NGQ and internal sound shell NSB in the indoor environment data and their corresponding internal temperature priority NWYJ, internal light intensity priority NGQYJ and internal sound shell priority NSBYJ;

[0040] By formula Calculate the internal temperature influence coefficient NWYX;

[0041] By formula Calculate the internal light intensity influence coefficient NGQYX;

[0042] By formula Calculate the internal sound shell influence coefficient NSBYX; where α4 and α5 are weight coefficients, α4 and α5∈(0, 1).

[0043] Further, the calculating of the personnel influence coefficient according to the indoor personnel data includes:

[0044] Get the number of people in the room NRS in real time;

[0045] When NRS is less than the number threshold RY, the personnel influence coefficient RYX=0;

[0046] Otherwise, by formula Calculate the personnel influence coefficient; where α6 is the proportional coefficient, α6>0; DR is the number of people per unit.

[0047] Furthermore, the dynamically calculating the equipment adjustment parameters according to the personnel influence coefficient and the indoor environment data includes:

[0048] Obtain the personnel influence coefficient RYX and indoor environment data;

[0049] When the personnel influence coefficient is 0, no operation is performed;

[0050] Otherwise, the optimum internal temperature TSNW is calculated and adjusted by the formula TSNW=SNW-WFF×RYX;

[0051] The optimum internal light intensity TSNGQ is calculated and adjusted by the formula TSNGQ=SNGQ+GQFF×RYX;

[0052] The optimal internal sound shell TSNSB is calculated and adjusted by the formula TSNSB=SNSB+SBFF×RYX; wherein WFF, GQFF and SBFF are the temperature floating range, the light intensity floating range and the sound shell floating range;

[0053] When the internal sound level is less than the optimal internal sound level, the adjusted internal sound level influence value TNSBY=0; otherwise, the adjusted internal sound level influence value is the absolute value of the difference between the internal sound level and the optimal internal sound level;

[0054] According to the formula Calculate and adjust the indoor comfort index TNSZ;

[0055] When the adjusted indoor comfort index is greater than the comfort threshold, no operation is performed;

[0056] Otherwise, the indoor temperature influence coefficient TNWYX, the indoor light intensity influence coefficient TNGQYX and the indoor sound shell influence coefficient TNSBYX are calculated and adjusted according to the indoor environment data priority and the indoor environment data;

[0057] Get the maximum values ​​of TNWYX, TNGQYX and TNSBYX in sequence;

[0058] When the maximum value is TNSBYX, determine whether the window state is closed; if yes, generate an indoor noise source alarm signal; if no, set the window state to closed, and recalculate and adjust the indoor comfort index; when the adjusted indoor comfort index is less than the comfort threshold, generate an indoor noise source alarm signal; otherwise, do nothing;

[0059] When the maximum value is TNWYX, the output temperature of the temperature control device is set to TSNW; and the indoor comfort index is calculated and adjusted again. When the adjusted indoor comfort index is greater than the comfort threshold, no operation is performed;

[0060] When the maximum value is TNGQYX, the output light intensity of the light intensity control device is set to TSNGQ; and the indoor comfort index is calculated and adjusted again. When the adjusted indoor comfort index is greater than the comfort threshold, no operation is performed.

[0061] This application takes into account the influence of the number of people indoors, calculates the indoor comfort index according to the changes in the number of people, and dynamically adjusts the optimal values ​​corresponding to the environmental parameters in the indoor environment according to the changes in the number of people, and adjusts the corresponding equipment so that the comfort of the indoor environment meets user requirements, thereby improving the user experience.

[0062] Further, generating an alarm signal according to the indoor comfort index includes:

[0063] Obtaining the indoor comfort index after dynamic adjustment and adjusting the indoor comfort index;

[0064] When the indoor comfort index is less than the comfort threshold, a fault alarm signal of the control device is generated; otherwise, no operation is performed;

[0065] When the adjusted indoor comfort index is less than the comfort threshold, a fault alarm signal of the control device is generated; otherwise, no operation is performed.

[0066] Another aspect of the present invention provides a method for optimizing the comfort level of an intelligent building environment based on the Internet of Things, comprising:

[0067] S0: Acquire indoor environment data and indoor personnel data;

[0068] S1: Predict the time when people are present indoors through a time prediction model, and the time prediction model is constructed by an LSTM model at the same time; calculate the indoor comfort index through indoor environment data;

[0069] S2: Calculate the equipment adjustment parameters according to the indoor comfort index and the indoor environment data; assign the equipment adjustment parameters to the corresponding equipment parameters;

[0070] S3: When there are people in the indoor environment, calculate the people influence coefficient according to the indoor people data; dynamically calculate the equipment adjustment parameters according to the people influence coefficient and the indoor environment data; assign the equipment adjustment parameters to the corresponding equipment parameters;

[0071] S4: generating an alarm signal according to the indoor comfort index;

[0072] S5: Provide prompts based on the alarm signal and contact management.

[0073] Compared with the prior art, the beneficial effects of this application are:

[0074] 1. The present application predicts the time when people are present indoors through a time prediction model; calculates the indoor comfort index through indoor environmental data; calculates equipment adjustment parameters based on the indoor comfort index and indoor environmental data; when there are people in the indoor environment, calculates the personnel impact coefficient based on the indoor personnel data; dynamically calculates equipment adjustment parameters based on the personnel impact coefficient and indoor environmental data; generates an alarm signal based on the indoor comfort index, predicts the time when the user arrives in the building, adjusts the indoor environment to the state of optimal environmental comfort in advance, and dynamically adjusts the comfort index when there are a large number of people indoors, taking into account the impact of the number of people on equipment adjustment, thereby improving the user experience.

[0075] 2. This application calculates the indoor comfort index by using the internal temperature, internal light intensity and internal sound level in the indoor environment data, calculates the indoor comfort index with multi-source data and uses it to measure the user's experience. It can dynamically adjust the equipment with more accurate indicators, thereby improving the accuracy of dynamic adjustment of the equipment.

[0076] 3. This application takes into account the influence of the number of people indoors, calculates the indoor comfort index according to the changes in the number of people, and dynamically adjusts the optimal values ​​corresponding to the environmental parameters in the indoor environment according to the changes in the number of people, and adjusts the corresponding equipment so that the comfort of the indoor environment meets the user requirements, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0078] Figure 1 This is a schematic diagram of the principle of the IoT-based intelligent building environment comfort optimization system of this application;

[0079] Figure 2This is a flow chart of the method for optimizing the environmental comfort of smart buildings based on the Internet of Things in this application. DETAILED DESCRIPTION

[0080] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0081] See also Figure 1 , the first embodiment of the present application provides an intelligent building environment comfort optimization system based on the Internet of Things, including: a data acquisition module, a data analysis module, a control module, an early warning module and a database;

[0082] Data acquisition module: obtain indoor environment data and indoor personnel data through data acquisition equipment; data acquisition equipment includes various sensors, etc.;

[0083] Data analysis module: predict the time when people are present indoors through the time prediction model, which is constructed through the LSTM model; calculate the indoor comfort index through indoor environmental data, which refers to the degree of comfort of the indoor environment for users; calculate the equipment adjustment parameters based on the indoor comfort index and indoor environmental data; when there are people in the indoor environment, calculate the personnel impact coefficient based on the indoor personnel data, which refers to the impact coefficient of the number of people in the room; dynamically calculate the equipment adjustment parameters based on the personnel impact coefficient and indoor environmental data; generate an alarm signal based on the indoor comfort index;

[0084] Control module: assign device adjustment parameters to corresponding device parameters;

[0085] Early warning module: Prompts are given based on alarm signals and management personnel are contacted. Alarm signals include fault alarm signals of control equipment and noise source alarm signals in the room.

[0086] This embodiment predicts the time when people are present indoors through a time prediction model; calculates an indoor comfort index through indoor environmental data; calculates equipment adjustment parameters based on the indoor comfort index and indoor environmental data; when there are people in the indoor environment, calculates the personnel impact coefficient based on the indoor personnel data; dynamically calculates equipment adjustment parameters based on the personnel impact coefficient and indoor environmental data; generates an alarm signal based on the indoor comfort index, predicts the time when the user arrives in the building, adjusts the indoor environment to the state of optimal environmental comfort in advance, and when there are a large number of people indoors, dynamically adjusts the comfort index, considers the impact of the number of people on equipment adjustment, and improves the user experience.

[0087] The time prediction model in this embodiment is constructed by using an LSTM model, including:

[0088] Obtain some historical outdoor environment data, time features and time tags; outdoor environment data includes outdoor temperature, outdoor weather, etc.; time features include whether it is a working day;

[0089] Performing data preprocessing on a number of historical outdoor environment data, time features, and time tags to obtain a number of preprocessed historical outdoor environment data, time features, and time tags;

[0090] Integrate historical outdoor environment data and time features with the same time tags into a time vector;

[0091] Integrate each time vector into several prediction sequences according to the order of time labels;

[0092] Divide several prediction sequences into training set, test set and validation set according to the order of time labels; the ratio between training set, test set and validation set is 7:2:1;

[0093] Select the LSTM model as the base model;

[0094] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0095] By verifying the pre-trained model on the test set, we finally obtain a time prediction model whose input is outdoor environment data and time features and whose output is time labels.

[0096] In this embodiment, the indoor comfort index is calculated using indoor environment data, including:

[0097] Obtain the interior temperature NW, interior light intensity NGQ and interior sound level NSB in the indoor environment data and their corresponding optimum interior temperature SNW, optimum interior light intensity SNGQ and optimum interior sound level SNSB, as well as the indoor environment data priority;

[0098] When the internal sound barrier is less than the optimum internal sound barrier, the internal sound barrier impact value NSBY=0; otherwise, the internal sound barrier impact value is the absolute value of the difference between the internal sound barrier and the optimum internal sound barrier;

[0099] By formula Calculate the indoor comfort index NSZ; wherein α1, α2 and α3 are weight coefficients, α1, α2 and α3∈(0,1), the weight coefficients are calculated according to the priority of the indoor environment data, and the specific values ​​are set according to experience; DW is the unit temperature, DGQ is the unit light intensity, and DSB is the unit sound shell. The specific values ​​are set according to experience. In this embodiment, DW is set to 1°C, DGQ is set to 1lx, and DSB is set to 1dB; the more the temperature and light intensity in the indoor environment data deviate from their corresponding optimal values, the larger the sound shell, indicating that the comfort of the indoor environment will become worse; therefore, the indoor comfort index will decrease accordingly.

[0100] This embodiment calculates the indoor comfort index by using the indoor temperature, indoor light intensity and indoor sound level in the indoor environment data. The indoor comfort index is calculated with multi-source data and is used to measure the user experience. It can dynamically adjust the equipment with more accurate indicators, thereby improving the accuracy of dynamic adjustment of the equipment.

[0101] The weight coefficient in this embodiment is calculated according to the indoor environment data priority, including:

[0102] Obtain the interior temperature NW, interior light intensity NGQ and interior sound shell NSB in the indoor environment data and their corresponding interior temperature priority NWYJ, interior light intensity priority NGQYJ and interior sound shell priority NSBYJ; the indoor environment data priority is custom constructed by user preference;

[0103] The weight coefficient α1 corresponding to the internal temperature is calculated by the formula α1=NWYJ / (NWYJ+NGQYJ+NSBYJ);

[0104] The weight coefficient α2 corresponding to the internal illumination intensity is calculated by the formula α2=NGQYJ / (NWYJ+NWYJ+NSBYJ);

[0105] The weight coefficient α3 corresponding to the internal sound shell is calculated by the formula α3=NSBYJ / (NWYJ+NWYJ+NGQYJ); the values ​​of α1, α2 and α3 are calculated by the proportion of the corresponding environmental data priority.

[0106] In this embodiment, the device adjustment parameters are calculated according to the indoor comfort index and the indoor environment data, including:

[0107] Obtain indoor comfort index NSZ, indoor environment data and indoor environment data priority;

[0108] When the indoor comfort index is greater than the comfort threshold, no action is taken; the comfort threshold is set based on experience;

[0109] Otherwise, the internal temperature influence coefficient NWYX, the internal light intensity influence coefficient NGQYX and the internal sound shell influence coefficient NSBYX are calculated according to the indoor environment data priority and the indoor environment data;

[0110] Get the maximum values ​​of NWYX, NGQYX and NSBYX in sequence;

[0111] When the maximum value is NSBYX, determine whether the window state is closed; if yes, generate an indoor noise source alarm signal; if no, set the window state to closed and calculate the indoor comfort index again; when the indoor comfort index is less than the comfort threshold, generate an indoor noise source alarm signal; otherwise, do nothing;

[0112] When the maximum value is NWYX, the output temperature of the temperature control device is set to SNW; and the indoor comfort index is calculated again. When the indoor comfort index is greater than the comfort threshold, no operation is performed;

[0113] When the maximum value is NGQYX, the output light intensity of the light intensity control device is set to SNGQ; and the indoor comfort index is calculated again. When the indoor comfort index is greater than the comfort threshold, no operation is performed.

[0114] In this embodiment, the calculation of the internal temperature influence coefficient NWYX, the internal light intensity influence coefficient NGQYX and the internal sound shell influence coefficient NSBYX according to the indoor environment data priority and the indoor environment data includes:

[0115] Obtain the internal temperature NW, internal light intensity NGQ and internal sound shell NSB in the indoor environment data and their corresponding internal temperature priority NWYJ, internal light intensity priority NGQYJ and internal sound shell priority NSBYJ;

[0116] By formula Calculate the internal temperature influence coefficient NWYX; the more the internal temperature deviates from the optimal internal temperature, and the higher its priority, the greater the impact of temperature on the user's environmental comfort, so the internal temperature influence coefficient increases accordingly;

[0117] By formula Calculate the internal light intensity influence coefficient NGQYX; the more the internal light intensity deviates from the optimal internal light intensity, and the higher its priority, the greater the impact of light intensity on the user's environmental comfort, so the internal light intensity influence coefficient increases accordingly;

[0118] By formula Calculate the internal sound barrier influence coefficient NSBYX; where α4 and α5 are weight coefficients, α4 and α5∈(0,1), and the specific values ​​are set based on experience; the more the internal sound barrier deviates from the optimal internal sound barrier and the higher its priority, the greater the impact of the sound barrier on the user's environmental comfort, and therefore, the internal influence coefficient increases accordingly.

[0119] This embodiment calculates the influence coefficient of each environmental parameter in the environmental data through indoor environmental data and its corresponding environmental data priority, and gives priority to adjusting the equipment corresponding to the maximum influence coefficient, so that the indoor environmental comfort meets user needs and improves the user experience.

[0120] In this embodiment, calculating the personnel influence coefficient according to the indoor personnel data includes:

[0121] Get the number of people in the room NRS in real time;

[0122] When NRS is less than the number threshold RY, the personnel influence coefficient RYX=0; the number threshold is set based on experience;

[0123] Otherwise, by formula Calculate the personnel impact coefficient; wherein, α6 is the proportional coefficient, α6>0, and the specific value is set according to experience; DR is the number of people per unit, and the specific value is set according to experience. In this embodiment, DR is set to 1 person; the more people there are, the greater the impact on the comfort of the indoor environment, so the personnel impact coefficient increases with the increase in the number of people.

[0124] In this embodiment, the device adjustment parameters are dynamically calculated based on the personnel influence coefficient and the indoor environment data, including:

[0125] Obtain the personnel influence coefficient RYX and indoor environment data;

[0126] When the personnel influence coefficient is 0, no operation is performed;

[0127] Otherwise, the optimum internal temperature TSNW is calculated and adjusted by the formula TSNW=SNW-WFF×RYX; when the optimum internal temperature is determined, the greater the personnel influence coefficient is, the more the temperature needs to be lowered to eliminate the influence of human body heat brought by the number of people; therefore, the optimum internal temperature is adjusted to be lowered accordingly;

[0128] The optimum interior light intensity TSNGQ is calculated and adjusted by the formula TSNGQ=SNGQ+GQFF×RYX; when the optimum interior light intensity is determined, the greater the personnel influence coefficient, the greater the adjustment of the optimum interior light intensity;

[0129] The optimal internal sound shell TSNSB is calculated and adjusted by the formula TSNSB=SNSB+SBFF×RYX; wherein WFF, GQFF and SBFF are the temperature floating range, the light intensity floating range and the sound shell floating range, and the specific values ​​are set according to experience; when the optimal internal sound shell is determined, the greater the personnel influence coefficient, the more sound shells need to be added to eliminate the impact of the increase in the number of people on the sound shell; therefore, the optimal internal sound shell is adjusted to increase accordingly;

[0130] When the internal sound level is less than the optimal internal sound level, the adjusted internal sound level influence value TNSBY=0; otherwise, the adjusted internal sound level influence value is the absolute value of the difference between the internal sound level and the optimal internal sound level;

[0131] According to the formula Calculate and adjust the indoor comfort index TNSZ; adjust the indoor comfort index to be consistent with the calculation method and formula principle of the indoor comfort index;

[0132] When the adjusted indoor comfort index is greater than the comfort threshold, no operation is performed;

[0133] Otherwise, the adjusted internal temperature influence coefficient TNWYX, the adjusted internal light intensity influence coefficient TNGQYX and the adjusted internal sound shell influence coefficient TNSBYX are calculated according to the indoor environment data priority and the indoor environment data; the calculation method and formula principle of the adjusted internal temperature influence coefficient TNWYX, the adjusted internal light intensity influence coefficient TNGQYX and the adjusted internal sound shell influence coefficient TNSBYX are consistent with the internal temperature influence coefficient NWYX, the internal light intensity influence coefficient NGQYX and the internal sound shell influence coefficient NSBYX;

[0134] Get the maximum values ​​of TNWYX, TNGQYX and TNSBYX in sequence;

[0135] When the maximum value is TNSBYX, determine whether the window state is closed; if yes, generate an indoor noise source alarm signal; if no, set the window state to closed, and recalculate and adjust the indoor comfort index; when the adjusted indoor comfort index is less than the comfort threshold, generate an indoor noise source alarm signal; otherwise, do nothing;

[0136] When the maximum value is TNWYX, the output temperature of the temperature control device is set to TSNW; and the indoor comfort index is calculated and adjusted again. When the adjusted indoor comfort index is greater than the comfort threshold, no operation is performed;

[0137] When the maximum value is TNGQYX, the output light intensity of the light intensity control device is set to TSNGQ; and the indoor comfort index is calculated and adjusted again. When the adjusted indoor comfort index is greater than the comfort threshold, no operation is performed.

[0138] This embodiment takes the influence of the number of people indoors into consideration, calculates the indoor comfort index according to the change in the number of people, and dynamically adjusts the optimal values ​​corresponding to the environmental parameters in the indoor environment according to the change in the number of people, and adjusts the corresponding equipment accordingly so that the comfort of the indoor environment meets the user requirements, thereby improving the user experience.

[0139] In this embodiment, generating an alarm signal according to the indoor comfort index includes:

[0140] Obtaining the indoor comfort index after dynamic adjustment and adjusting the indoor comfort index;

[0141] When the indoor comfort index is less than the comfort threshold, a fault alarm signal of the control device is generated; otherwise, no operation is performed;

[0142] When the adjusted indoor comfort index is less than the comfort threshold, a fault alarm signal of the control device is generated; otherwise, no operation is performed.

[0143] See also Figure 2 Another aspect of the present application provides a method for optimizing the comfort level of an intelligent building environment based on the Internet of Things, comprising:

[0144] S0: Acquire indoor environment data and indoor personnel data;

[0145] S1: Predict the time when people are present indoors through the time prediction model, and build the LSTM model at the same time; calculate the indoor comfort index through indoor environment data;

[0146] S2: Calculate the equipment adjustment parameters according to the indoor comfort index and the indoor environment data; assign the equipment adjustment parameters to the corresponding equipment parameters;

[0147] S3: When there are people in the indoor environment, calculate the people influence coefficient according to the indoor people data; dynamically calculate the equipment adjustment parameters according to the people influence coefficient and the indoor environment data; assign the equipment adjustment parameters to the corresponding equipment parameters;

[0148] S4: generating an alarm signal according to the indoor comfort index;

[0149] S5: Provide prompts based on the alarm signal and contact management.

[0150] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0151] The working principle of the present application is as follows: by acquiring indoor environment data and indoor personnel data; predicting the time when indoor personnel exist through a time prediction model; calculating the indoor comfort index through indoor environment data; calculating the equipment adjustment parameters according to the indoor comfort index and indoor environment data; when there are personnel in the indoor environment, calculating the personnel impact coefficient according to the indoor personnel data; dynamically calculating the equipment adjustment parameters according to the personnel impact coefficient and indoor environment data; assigning the equipment adjustment parameters to the corresponding equipment parameters; generating an alarm signal according to the indoor comfort index; making a prompt according to the alarm signal and contacting the management personnel, predicting the time when the user arrives in the building, adjusting the indoor environment to the state of optimal environmental comfort in advance, and when there are a large number of people indoors, dynamically adjusting the comfort index, considering the impact of the number of people on the equipment adjustment, thereby improving the user experience and avoiding the problem that the existing technology lacks the ability to dynamically respond to environmental changes and personalized comfort considerations, resulting in a poor user experience in the building environment.

[0152] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. The intelligent building environment comfort optimization system based on the Internet of Things is characterized by: include: Data acquisition module, data analysis module, control module, early warning module and database; The data acquisition module is used to acquire indoor environment data and indoor personnel data through data acquisition equipment; The data analysis module: predicts the time when people are present indoors through a time prediction model, wherein the time prediction model is constructed through an LSTM model; calculates an indoor comfort index through indoor environmental data; calculates equipment adjustment parameters based on the indoor comfort index and indoor environmental data; calculates a personnel influence coefficient based on indoor personnel data when there are people in the indoor environment; dynamically calculates equipment adjustment parameters based on the personnel influence coefficient and indoor environmental data; and generates an alarm signal based on the indoor comfort index; The control module assigns the device adjustment parameters to the corresponding device parameters.

2. The IoT-based intelligent building environment comfort optimization system according to claim 1 is characterized in that: The time prediction model is constructed by using the LSTM model, including: Obtain some historical outdoor environment data, time characteristics and time tags; Performing data preprocessing on a number of historical outdoor environment data, time features, and time tags to obtain a number of preprocessed historical outdoor environment data, time features, and time tags; Integrate historical outdoor environment data and time features with the same time tags into a time vector; Integrate each time vector into several prediction sequences according to the order of time labels; Divide several prediction sequences into training set, test set and validation set according to the order of time labels; Select the LSTM model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtain a time prediction model whose input is outdoor environment data and time features and whose output is time labels.

3. The IoT-based intelligent building environment comfort optimization system according to claim 1 is characterized in that: The calculating of the indoor comfort index by indoor environment data includes: Obtain the interior temperature NW, interior light intensity NGQ and interior sound level NSB in the indoor environment data and their corresponding optimum interior temperature SNW, optimum interior light intensity SNGQ and optimum interior sound level SNSB, as well as the indoor environment data priority; When the internal sound barrier is less than the optimum internal sound barrier, the internal sound barrier impact value NSBY=0; otherwise, the internal sound barrier impact value is the absolute value of the difference between the internal sound barrier and the optimum internal sound barrier; By formula Calculate the indoor comfort index NSZ; wherein α1, α2 and α3 are weight coefficients, α1, α2 and α3∈(0,1), and the weight coefficients are calculated according to the priority of indoor environment data; DW is unit temperature, DGQ is unit light intensity, and DSB is unit sound bezel.

4. The IoT-based intelligent building environment comfort optimization system according to claim 3 is characterized in that: The weight coefficient is calculated according to the indoor environment data priority, including: Obtaining the internal temperature NW, the internal light intensity NGQ and the internal sound shell NSB in the indoor environment data and their corresponding internal temperature priority NWYJ, internal light intensity priority NGQYJ and internal sound shell priority NSBYJ; the indoor environment priority is custom constructed by user preference; The weight coefficient α1 corresponding to the internal temperature is calculated by the formula α1=NWYJ / (NWYJ+NGQYJ+NSBYJ); The weight coefficient α2 corresponding to the internal illumination intensity is calculated by the formula α2=NGQYJ / (NWYJ+NWYJ+NSBYJ); The weight coefficient α3 corresponding to the inner sound shell is calculated by the formula α3=NSBYJ / (NWYJ+NWYJ+NGQYJ).

5. The IoT-based intelligent building environment comfort optimization system according to claim 1 is characterized in that: The calculating of equipment adjustment parameters according to the indoor comfort index and indoor environment data includes: Obtain indoor comfort index NSZ, indoor environment data and indoor environment data priority; When the indoor comfort index is greater than the comfort threshold, no action is taken; Otherwise, the internal temperature influence coefficient NWYX, the internal light intensity influence coefficient NGQYX and the internal sound shell influence coefficient NSBYX are calculated according to the indoor environment data priority and the indoor environment data; Get the maximum values ​​of NWYX, NGQYX and NSBYX in sequence; When the maximum value is NSBYX, determine whether the window state is closed; if yes, generate an indoor noise source alarm signal; if no, set the window state to closed and calculate the indoor comfort index again; when the indoor comfort index is less than the comfort threshold, generate an indoor noise source alarm signal; otherwise, do nothing; When the maximum value is NWYX, the output temperature of the temperature control device is set to SNW; and the indoor comfort index is calculated again. When the indoor comfort index is greater than the comfort threshold, no operation is performed; When the maximum value is NGQYX, the output light intensity of the light intensity control device is set to SNGQ; and the indoor comfort index is calculated again. When the indoor comfort index is greater than the comfort threshold, no operation is performed.

6. The IoT-based intelligent building environment comfort optimization system according to claim 5 is characterized in that: The method of calculating the internal temperature influence coefficient NWYX, the internal light intensity influence coefficient NGQYX and the internal sound wave influence coefficient NSBYX according to the indoor environment data priority and the indoor environment data includes: Obtain the internal temperature NW, internal light intensity NGQ and internal sound shell NSB in the indoor environment data and their corresponding internal temperature priority NWYJ, internal light intensity priority NGQYJ and internal sound shell priority NSBYJ; By formula Calculate the internal temperature influence coefficient NWYX; By formula Calculate the internal light intensity influence coefficient NGQYX; By formula Calculate the internal sound shell influence coefficient NSBYX; where α4 and α5 are weight coefficients, α4 and α5∈(0, 1).

7. The IoT-based intelligent building environment comfort optimization system according to claim 1 is characterized in that: The calculating of the personnel influence coefficient according to the indoor personnel data includes: Get the number of people in the room NRS in real time; When NRS is less than the number threshold RY, the personnel influence coefficient RYX=0; Otherwise, by formula Calculate the personnel influence coefficient; where α6 is the proportional coefficient, α6>0; DR is the number of people per unit.

8. The IoT-based intelligent building environment comfort optimization system according to claim 1 is characterized in that: The dynamically calculating the equipment adjustment parameters according to the personnel influence coefficient and the indoor environment data includes: Obtain the personnel influence coefficient RYX and indoor environment data; When the personnel influence coefficient is 0, no operation is performed; Otherwise, the optimum internal temperature TSNW is calculated and adjusted by the formula TSNW=SNW-WFF×RYX; The optimum internal light intensity TSNGQ is calculated and adjusted by the formula TSNGQ=SNGQ+GQFF×RYX; The optimal internal sound shell TSNSB is calculated and adjusted by the formula TSNSB=SNSB+SBFF×RYX; wherein WFF, GQFF and SBFF are the temperature floating range, the light intensity floating range and the sound shell floating range; When the internal sound level is less than the optimal internal sound level, the adjusted internal sound level influence value TNSBY=0; otherwise, the adjusted internal sound level influence value is the absolute value of the difference between the internal sound level and the optimal internal sound level; According to the formula Calculate and adjust the indoor comfort index TNSZ; When the adjusted indoor comfort index is greater than the comfort threshold, no operation is performed; Otherwise, the indoor temperature influence coefficient TNWYX, the indoor light intensity influence coefficient TNGQYX and the indoor sound shell influence coefficient TNSBYX are calculated and adjusted according to the indoor environment data priority and the indoor environment data; Get the maximum values ​​of TNWYX, TNGQYX and TNSBYX in sequence; When the maximum value is TNSBYX, determine whether the window state is closed; if yes, generate an indoor noise source alarm signal; if no, set the window state to closed, and recalculate and adjust the indoor comfort index; when the adjusted indoor comfort index is less than the comfort threshold, generate an indoor noise source alarm signal; otherwise, do nothing; When the maximum value is TNWYX, the output temperature of the temperature control device is set to TSNW; and the indoor comfort index is calculated and adjusted again. When the adjusted indoor comfort index is greater than the comfort threshold, no operation is performed; When the maximum value is TNGQYX, the output light intensity of the light intensity control device is set to TSNGQ; and the indoor comfort index is calculated and adjusted again. When the adjusted indoor comfort index is greater than the comfort threshold, no operation is performed.

9. The IoT-based intelligent building environment comfort optimization system according to claim 1, characterized in that: The step of generating an alarm signal according to the indoor comfort index comprises: Obtaining the indoor comfort index after dynamic adjustment and adjusting the indoor comfort index; When the indoor comfort index is less than the comfort threshold, a fault alarm signal of the control device is generated; otherwise, no operation is performed; When the adjusted indoor comfort index is less than the comfort threshold, a fault alarm signal of the control device is generated; otherwise, no operation is performed.

10. A method for optimizing the environmental comfort of an intelligent building based on the Internet of Things, applied to the system for optimizing the environmental comfort of an intelligent building based on the Internet of Things as claimed in any one of claims 1 to 9, characterized in that: include: S0: Acquire indoor environment data and indoor personnel data; S1: Predict the time when people are present indoors through a time prediction model, and the time prediction model is constructed by an LSTM model at the same time; calculate the indoor comfort index through indoor environment data; S2: Calculate the equipment adjustment parameters according to the indoor comfort index and the indoor environment data; assign the equipment adjustment parameters to the corresponding equipment parameters; S3: When there are people in the indoor environment, calculate the people influence coefficient according to the indoor people data; dynamically calculate the equipment adjustment parameters according to the people influence coefficient and the indoor environment data; assign the equipment adjustment parameters to the corresponding equipment parameters; S4: Generate an alarm signal according to the indoor comfort index.

Images