Sensor analysis-based decorative space energy-saving analysis method and system

Abstract

This invention discloses a sensor-based energy-saving analysis method and system for decorative spaces, relating to the field of indoor environmental control. The method includes: deploying a sensor network within the decorative space to collect multi-source sensor datasets; performing surface characteristic inversion modeling of decorative materials based on optical, thermal, and equipment operation auxiliary data to obtain a decorative light-heat coupling feature vector; establishing the coupling relationship between optical and thermal behavior to obtain a light-heat coupling energy consumption function model; performing multi-dimensional energy consumption contribution decomposition on the decorative space; conducting energy consumption impact sensitivity analysis according to the obtained multi-dimensional energy consumption contribution indicators; generating a multi-dimensional collaborative optimization strategy based on the analysis results; and issuing and executing energy-saving feedback control. This application addresses the problem that existing decorative space energy consumption optimization strategies lack scientific basis and are difficult to achieve refined and intelligent management, thus providing a scientific basis for decorative space energy consumption optimization and achieving refined and intelligent energy consumption management.

Description

Technical Field

[0001] This application relates to the field of indoor environmental control, and in particular to a sensor-based method and system for energy-saving analysis of decorative spaces. Background Technology

[0002] Energy consumption optimization in decorative spaces is a crucial research area in building energy conservation, directly impacting energy efficiency, cost reduction, and the implementation of green and low-carbon principles, thus significantly contributing to the sustainable development of the construction industry. Currently, the mainstream technical approach for optimizing energy consumption in decorative spaces combines manual experience-based control with conventional energy monitoring. This involves manually observing lighting and temperature conditions, adjusting operating parameters of lighting, air conditioning, and other equipment, and recording energy consumption data using simple meters. Based on historical data, the direction for energy optimization is determined. However, existing methods rely excessively on manual experience and employ rudimentary monitoring techniques, resulting in inaccurate energy monitoring, incomplete analysis of energy-influencing factors, and a lack of scientific basis for optimization strategies. This leads to an inability to accurately pinpoint energy waste, poor optimization results, and difficulty in achieving refined and intelligent control of energy consumption in decorative spaces. Furthermore, manual control is inefficient and costly, failing to meet the dynamic energy optimization needs of different usage scenarios.

[0003] At present, the optimization of energy consumption in decorative spaces faces technical challenges, such as a lack of scientific basis for optimization strategies and difficulty in achieving refined and intelligent management. Summary of the Invention

[0004] This application provides a sensor-based energy-saving analysis method and system for decorative spaces. By deploying a sensor network within the decorative space, it collects multi-source sensor data related to optics, thermal dynamics, and equipment operation. Based on this data, it performs inversion modeling of the surface characteristics of decorative materials, obtaining a light-heat coupling feature vector. Based on this feature vector, it establishes the coupling relationship between optical and thermal behaviors. By fusing models of the impact of light on lighting energy consumption and light on heat load, it obtains a light-heat coupling energy consumption function model. Based on this model, it performs multi-dimensional energy consumption contribution decomposition and energy consumption impact sensitivity analysis, generating multi-dimensional collaborative optimization strategies and issuing and executing energy-saving feedback control for the decorative space. This solves the technical problem of existing decorative space energy consumption optimization strategies lacking scientific basis and making it difficult to achieve refined and intelligent management. It achieves the technical effect of providing a scientific basis for decorative space energy consumption optimization and realizing refined and intelligent energy consumption management.

[0005] This application provides a sensor-based energy-saving analysis method for decorative spaces, comprising: deploying a sensor network within the decorative space to collect multi-source sensor datasets, including optical related data, thermal related data, and equipment operation auxiliary data; performing surface characteristic inversion modeling of decorative materials based on the optical related data, thermal related data, and equipment operation auxiliary data to obtain a decorative light-heat coupling feature vector; establishing a coupling relationship between optical behavior and thermal behavior based on the decorative light-heat coupling feature vector to obtain a light-heat coupling energy consumption function model, wherein the light-heat coupling energy consumption function model is obtained by fusing a light-to-lighting energy consumption influence model and a light-to-heat load influence model; performing multi-dimensional energy consumption contribution decomposition on the decorative space based on the light-heat coupling energy consumption function model; performing energy consumption impact sensitivity analysis according to the multi-dimensional energy consumption contribution index obtained from the decomposition; generating a multi-dimensional collaborative optimization strategy based on the energy consumption impact sensitivity analysis results; and issuing the multi-dimensional collaborative optimization strategy to execute energy-saving feedback control of the decorative space.

[0006] In a possible implementation, the surface properties of the decorative material are inverted and modeled based on the optically relevant data, thermally relevant data, and equipment operation auxiliary data. The following processing is performed: multi-source time-series alignment is applied to the optically relevant data, thermally relevant data, and equipment operation auxiliary data to obtain a regional-level time-series data set; optical characteristic parameters are inverted based on the regional-level time-series data set, including reflectivity estimation, absorptivity estimation, and light utilization efficiency parameters, to obtain an optical feature vector; thermal characteristic parameters are inverted based on the regional-level time-series data set, including thermal time constant estimation, equivalent heat capacity estimation, and thermal conductivity estimation, to obtain a thermal feature vector; photothermal effect coupling modeling is performed based on the optical feature vector and the thermal feature vector, and a decorative light-heat coupling feature vector is obtained based on the constructed photothermal effect coupling model.

[0007] In a possible implementation, a decorative light-heat coupling feature vector is obtained based on the constructed photothermal effect coupling model, and the following processing is performed: the device coupling influence vector is extracted based on the constructed photothermal effect coupling model, including the lighting coupling coefficient characterizing the influence of light reflection on lighting demand, and the air conditioning coupling coefficient characterizing the influence of surface temperature on cooling load; the device coupling influence vector, optical feature vector and thermal feature vector are fused to obtain the decorative light-heat coupling feature vector.

[0008] In a possible implementation, the coupling relationship between optical and thermal behaviors is established based on the decorative light-heat coupling feature vector to obtain a light-heat coupling energy consumption function model. The following processing is then performed: A variable mapping relationship is established analytically based on the decorative light-heat coupling feature vector to obtain a set of model input variables, including optical control variables, thermal control variables, and equipment response variables; the optical control variables are used as input to calculate effective illuminance, and a lighting demand function is introduced to respond to the effective illuminance based on the target illuminance demand, constructing a light-on-lighting energy consumption impact model; the thermal control variables are used as input to calculate surface temperature rise, and an air conditioning load function is introduced to respond to the surface temperature rise load, constructing a light-on-heat load impact model; the light-on-lighting energy consumption impact model and the light-on-heat load impact model are fused to obtain the light-heat coupling energy consumption function model.

[0009] In a possible implementation, the light-to-lighting energy consumption influence model and the light-to-heat load influence model are fused to obtain a light-heat coupled energy consumption function model. The following processing is then performed: obtaining the lighting energy consumption response value output by the light-to-lighting energy consumption influence model and the load energy consumption response value output by the light-to-heat load influence model; assigning weights to the lighting energy consumption response value and the load energy consumption response value, wherein the weights are analyzed based on energy consumption sensitivity; and fusing the normalized response values ​​of the lighting energy consumption response value and the load energy consumption response value according to the weights to obtain the light-heat coupled energy consumption function model.

[0010] In a possible implementation, the decorative space is decomposed into multidimensional energy consumption contributions based on the light-heat coupling energy consumption function model, and the following processing is performed: a baseline operating condition is set, and the baseline total energy consumption output by the light-heat coupling energy consumption function model is obtained under the baseline operating condition; a single-dimensional control variable is perturbed through the baseline operating condition to obtain the perturbed total energy consumption of the single-dimensional control variable; the multidimensional energy consumption contribution is quantified sequentially according to the perturbed total energy consumption of the single-dimensional control variable to obtain a multidimensional energy consumption contribution index.

[0011] In a possible implementation, an energy consumption impact sensitivity analysis is performed based on the multidimensional energy consumption contribution indicators obtained from the decomposition, and the following processing is performed: based on each energy consumption contribution indicator in the multidimensional energy consumption contribution indicators, Monte Carlo sampling is used to calculate the sensitivity indicators affecting the overall energy consumption change; the sensitivity indicators are sorted according to obtain the energy consumption impact sensitivity analysis results corresponding to the multidimensional energy consumption contribution indicators, and the energy consumption impact sensitivity analysis results include optimization priority identifiers based on the sorting configuration.

[0012] In a possible implementation, a multidimensional collaborative optimization strategy is generated based on the results of the energy consumption impact sensitivity analysis, and the following processes are performed: defining an optimization objective and a search step size that minimizes total energy consumption; based on the optimization priority identifier of the energy consumption impact sensitivity analysis results and the search step size, performing a priority queue sequential search under the optimization objective until the convergence condition of the optimization objective is met, thereby generating a multidimensional collaborative optimization strategy.

[0013] In a possible implementation, the following processing is performed: Monte Carlo sampling is used to calculate sensitivity indices affecting changes in overall energy consumption, including a first-order sensitivity index and a total-order sensitivity index; the first-order sensitivity index is used to quantify the contribution of a single variable itself to the variance of total energy consumption, and the total-order sensitivity index is used to quantify the contribution of a single variable and its interaction with other variables to the variance of total energy consumption.

[0014] This application also provides a sensor-based energy-saving analysis system for decorative spaces, comprising: a multi-source sensor data acquisition module for deploying a sensor network within the decorative space to acquire multi-source sensor datasets, including optical-related data, thermal-related data, and equipment operation auxiliary data; a decorative light-heat coupling feature vector generation module for performing surface characteristic inversion modeling of decorative materials based on the optical-related data, thermal-related data, and equipment operation auxiliary data to obtain decorative light-heat coupling feature vectors; a light-heat coupling energy consumption function model construction module for establishing the coupling relationship between optical behavior and thermal behavior based on the decorative light-heat coupling feature vectors to obtain a light-heat coupling energy consumption function model, wherein the light-heat coupling energy consumption function model is obtained by fusing a light-to-lighting energy consumption influence model and a light-to-heat load influence model; and an energy-saving feedback control module for performing multi-dimensional energy consumption contribution decomposition of the decorative space based on the light-heat coupling energy consumption function model, performing energy consumption impact sensitivity analysis according to the multi-dimensional energy consumption contribution index obtained from the decomposition, generating a multi-dimensional collaborative optimization strategy based on the energy consumption impact sensitivity analysis results, and issuing the multi-dimensional collaborative optimization strategy to execute energy-saving feedback control of the decorative space.

[0015] The proposed sensor-based energy-saving analysis method and system for decorative spaces first deploys a sensor network within the decorative space to collect multi-source sensor datasets, including optical, thermal, and equipment operation auxiliary data. Next, based on these data, the surface characteristics of the decorative materials are inverted and modeled to obtain a decorative light-heat coupling feature vector. Then, based on this feature vector, a coupling relationship between optical and thermal behaviors is established, resulting in a light-heat coupling energy consumption function model. This model is obtained by fusing models of light's impact on lighting energy consumption and light's impact on heat load. Finally, based on this model, a multi-dimensional energy consumption contribution decomposition is performed on the decorative space. Energy consumption impact sensitivity analysis is conducted according to the decomposed multi-dimensional energy consumption contribution indicators. Based on the results of this analysis, a multi-dimensional collaborative optimization strategy is generated, and this strategy is then deployed to implement energy-saving feedback control of the decorative space. Through this process, the proposed method and system provide a scientific basis for optimizing energy consumption in decorative spaces and achieve refined and intelligent energy consumption management. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 This is a flowchart illustrating the energy-saving analysis method for decorative spaces based on sensor analysis provided in this application embodiment.

[0018] Figure 2 This is a schematic diagram of the structure of a sensor-based energy-saving analysis system for decorative spaces provided in an embodiment of this application.

[0019] Figure labeling: Multi-source sensor data acquisition module 10, decorative light-heat coupling feature vector generation module 20, light-heat coupling energy consumption function model construction module 30, energy-saving feedback control module 40. Detailed Implementation

[0020] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0021] This application provides a sensor-based energy-saving analysis method for decorative spaces, such as... Figure 1 As shown, the method includes: Step S100: Deploy a sensor network within the decorative space to collect multi-source sensor datasets, including optical data, thermal data, and equipment operation auxiliary data.

[0022] Specifically, the decorative space is divided into zones based on its actual layout, forming multiple equal monitoring areas, each serving as an independent sensing and monitoring unit. A sensor network is deployed, with optical and thermal sensors installed in each monitoring area. Operating status sensors are installed on the lighting and air conditioning equipment within the decorative space. The sensor network communicates with the data acquisition terminal via a wired connection, using a transmission control protocol to ensure stable data transmission. Specifically, the optical sensor is a BH1750 illuminance sensor, the thermal sensor is a DS18B20 temperature sensor, and the equipment operating status sensor is an ACS712 current and voltage sensor. Sensor acquisition frequency and range parameters are set, and the sensor network is activated for data acquisition. Optical data acquired by the optical sensors includes real-time illuminance and illumination duration for each monitoring area; thermal data acquired by the thermal sensors includes real-time ambient temperature and decorative material surface temperature for each monitoring area; and equipment operating auxiliary data includes real-time operating current, voltage, and operating time for lighting equipment, and real-time operating current, voltage, operating mode (cooling, heating, standby), and set temperature for air conditioning equipment. All data collected by the sensors are transmitted to the data acquisition terminal, which performs preliminary noise reduction on the data. The moving average filtering method is used, and five consecutive data points are selected as a filtering window. The average value of the data within the window is calculated as the denoised data. The denoised data are then aggregated to form a multi-source sensor dataset, which is stored in the local database of the data acquisition terminal. The database uses a structured query language database.

[0023] Step S200: Based on the optical related data, thermal related data and equipment operation auxiliary data, perform surface characteristic inversion modeling of decorative materials to obtain decorative light-heat coupling feature vector.

[0024] Specifically, the multi-source sensor dataset acquired and denoised in step S100 is retrieved from the local database of the data acquisition terminal. Data preprocessing is performed to unify the format of the multi-source sensor dataset, converting all data to the same format, such as CSV, to ensure data compatibility. Then, through time-series alignment, step-by-step inversion of optical and thermal parameters, coupled modeling, and fusion of device influence parameters, a decorative light-thermal coupling feature vector is finally obtained. Each monitoring area corresponds to a set of decorative light-thermal coupling feature vectors. The feature vectors from all areas are then aggregated and stored in the database.

[0025] In one possible implementation, the surface characteristics of the decorative material are inverted and modeled based on the optical, thermal, and equipment operation auxiliary data. Step S200 further includes step S210, which performs multi-source temporal alignment processing on the optical, thermal, and equipment operation auxiliary data to obtain a regional-level temporal data set. Specifically, the denoised multi-source sensor dataset from step S100 is called, where each data point corresponds to a unique acquisition time. A temporal alignment tool, such as the Pandas library in Python, is used to perform temporal alignment processing on the three types of data based on the acquisition timestamp. Specifically, data points with completely consistent acquisition timestamps are first selected. For data points with timestamp discrepancies, linear interpolation is used to supplement them, ensuring that each timestamp corresponds to a complete set of optical, thermal, and equipment operation auxiliary data. According to the monitoring areas defined in step S100, the aligned multi-source data is grouped by area, with each area corresponding to a set of time-series data. The time span of the time-series data is set to 24 hours, meaning that the time-series data for each area includes optical correlation data, thermal correlation data, and equipment operation auxiliary data for each minute within 24 hours. The time-series data for each area are integrated into regional-level time-series data, and the regional-level time-series data for all areas are summarized to form a regional-level time-series data set, which is then stored in the database.

[0026] Step S220 involves inverting optical characteristic parameters based on the regional time-series data set, including reflectance estimation, absorptivity estimation, and light utilization efficiency parameters, to obtain an optical feature vector. Specifically, the regional time-series data set obtained in step S210 is retrieved from the database. For each monitoring area, optical-related data and lighting equipment operation parameters from the time-series data and equipment operation auxiliary data of that area are extracted. A fitting calculation model is constructed using the least squares method, with the reflectance, absorptivity, and light utilization efficiency of the decorative material surface as the fitting targets. Iterative fitting calculations are performed by combining illuminance, illumination duration, and lighting equipment operation parameters, limiting the reasonable range of optical characteristic parameters during the fitting process. During the fitting process, the actual light output capability is calculated by combining the electrical operation parameters of the lighting equipment, the incident light related values ​​on the material surface are calculated by combining the spatial dimensions and illumination data, the reflectance value is derived through the fitting model, the absorptivity value is determined based on the reflectance value, and the effective light utilization is calculated by combining the spatial target illuminance and operating duration, thereby obtaining the light utilization efficiency value. The reflectance, absorptivity, and light utilization efficiency obtained from the inversion of each monitoring area are arranged in order to form the optical feature vector of that area. The optical feature vectors of all areas are then aggregated and stored in the database. A specific example of the optical characteristic parameter inversion is as follows: For reflectance, using time-aligned real-time illuminance, light output of lighting equipment, spatial dimensions, and light-receiving area of ​​the material as inputs, a correspondence is established between the measured effective light received in the space and the amount of light incident on the material surface. Reflectance is used as the parameter to be determined, and iterative fitting using the least squares method is employed to minimize the error between the calculated and measured light amounts. When the iteration error meets the preset convergence condition, the reflectance obtained from this fitting is output. For absorptivity, taking opaque decorative materials as an example, light incident on the material surface does not exist... In the transmission component, there are only reflected light components and absorbed light components. According to the law of conservation of light energy, the sum of reflectivity and absorptivity is 1. Therefore, absorptivity is uniquely determined by reflectivity, that is: absorptivity = 1 − reflectivity. As for light utilization efficiency, the target illuminance preset in the space, the real-time illuminance obtained by monitoring, and the operating time of the lighting equipment are used as the basis for calculation. Under the same operating time conditions, the real-time illuminance is compared with the target illuminance, and the proportion that the real-time illuminance can reach the target illuminance is calculated. This proportion is the light utilization efficiency, which is used to characterize the degree to which the light in the space is effectively utilized.

[0027] Step S230 involves inverting thermal characteristic parameters based on the regional time-series data set, including estimation of the thermal time constant, equivalent heat capacity, and thermal conductivity, to obtain a thermal feature vector. Specifically, the regional time-series data set obtained in step S210 is retrieved from the database. For each monitoring area, thermally relevant data and air conditioning equipment operating parameters from the equipment operation auxiliary data are extracted from the time-series data of that area. An iterative solution model for thermal parameters is constructed using the Newton-Raphson iteration method, with the thermal time constant, equivalent heat capacity, and thermal conductivity as the solution objectives. Ambient temperature, surface temperature, and air conditioning equipment operating parameters are input, limiting the reasonable range of values ​​for the thermal characteristic parameters. During the iterative solution process, the cooling and heating output capacity of the equipment is calculated by combining the air conditioning electrical parameters, and the heat transfer rate of the material is calculated by combining the temperature time-series changes. The iterative model gradually approximates the true values ​​of thermal conductivity and equivalent heat capacity, and then the thermal time constant is solved based on the aforementioned parameters. The three parameters obtained from the inversion of thermal characteristic parameters for each monitoring area—thermal time constant, equivalent heat capacity, and thermal conductivity—are arranged in sequence to form the thermal characteristic vector of that area. The thermal characteristic vectors of all areas are then aggregated and stored in the database. Specific examples of thermal characteristic parameter inversion are as follows: For thermal conductivity, based on the temporal changes in ambient temperature and surface temperature, and the air conditioning's heating and cooling output capacity, Newton's iterative method is used to successively correct the calculation, ensuring that the calculated heat transfer rate matches the measured heat transfer rate. After iterative convergence, the thermal conductivity is obtained. For equivalent heat capacity, based on the air conditioning's heating and cooling output power, operating time, and measured temperature changes, Newton's iterative method is used to iteratively correct the calculation, ensuring that the calculated thermal response matches the measured thermal response. After iterative convergence, the equivalent heat capacity is obtained. For the thermal time constant, based on the obtained thermal conductivity and equivalent heat capacity, combined with the decay trend of the material's surface temperature over time, Newton's iterative method is used for further convergence calculation, and the thermal time constant is obtained after iterative convergence.

[0028] Step S240: A photothermal effect coupling model is performed based on the optical and thermal feature vectors. The decorative light-heat coupling feature vector is obtained from the constructed model. Specifically, the optical feature vector obtained in step S220 and the thermal feature vector obtained in step S230 are retrieved from the database to ensure a one-to-one correspondence between the optical and thermal feature vectors for each monitoring area. The photothermal effect coupling model is constructed using reflectivity, absorptivity, and light utilization efficiency from the optical feature vectors as optical input parameters, and thermal time constant, equivalent heat capacity, and thermal conductivity from the thermal feature vectors as thermal input parameters. The photothermal conversion efficiency of the decorative material surface is used as the coupling core to establish the correlation between optical and thermal parameters, i.e., the photothermal effect coupling model, which quantifies the process of light energy conversion into heat energy and the laws governing heat transfer. Based on the constructed photothermal effect coupling model, key parameters characterizing the photo-thermal synergistic effect are extracted. Using a serial fusion approach, the parameters in the optical and thermal feature vectors are sequentially arranged with the key parameters output by the coupling model to form the decorative photothermal coupling feature vector for that region. All decorative photothermal coupling feature vectors from all regions are then aggregated and stored in a database. A specific implementation example is as follows: First, reflectivity, absorptivity, and light utilization efficiency from the optical feature vector are used as inputs. The absorptivity determines the proportion of incident light absorbed and converted into heat energy. Then, the equivalent heat capacity, thermal time constant, and thermal conductivity from the thermal feature vector are used as inputs. The equivalent heat capacity determines the surface temperature rise corresponding to the photothermal energy. The thermal time constant and thermal conductivity determine the temperature rise over time and the heat transfer rate. The entire process of light energy absorption, heat energy generation, temperature change, and heat transfer is integrated into a continuous calculation relationship, thus constructing the photothermal effect coupling model.

[0029] In one possible implementation, a decorative light-heat coupling feature vector is obtained based on the constructed photothermal effect coupling model. Step S240 further includes step S241, which extracts the device coupling influence vector based on the constructed photothermal effect coupling model. This includes an lighting coupling coefficient characterizing the influence of light reflection on lighting demand, and an air conditioning coupling coefficient characterizing the influence of surface temperature on cooling load. Specifically, the photothermal effect coupling model is invoked to extract the lighting coupling coefficient. The lighting coupling coefficient characterizes the influence of the light reflection characteristics of the decorative material on lighting demand. The calculation process involves first determining the target illuminance of the decorative space, then calculating the light power required by the lighting equipment under different reflectivities based on the reflectivity obtained in step S220, and finally calculating the ratio of the actual required light output to the light output under ideal reflection conditions to obtain the lighting coupling coefficient. The air conditioning coupling coefficient is then extracted. The air conditioning coupling coefficient characterizes the influence of the surface temperature of the decorative material on the air conditioning cooling load. The calculation process involves first determining the target set temperature of the air conditioner, then calculating the actual cooling load of the air conditioner under different surface temperatures based on the surface temperature change data output by the photothermal effect coupling model in step S240, and finally calculating the ratio of the actual cooling load to the cooling load under ideal temperature conditions to obtain the air conditioning coupling coefficient. The lighting coupling coefficient and air conditioning coupling coefficient of each monitoring area are arranged in order to form the equipment coupling influence vector of that area, and stored in the database.

[0030] Step S242 involves fusing the device coupling influence vector, optical feature vector, and thermal feature vector to obtain a decorative light-thermal coupling feature vector. Specifically, the device coupling influence vector obtained in step S241, the optical feature vector obtained in step S220, and the thermal feature vector obtained in step S230 are retrieved from the database, ensuring that the three vectors correspond to the same monitoring area. Vector fusion is completed using a serial splicing method, with the splicing order being all parameters of the optical feature vector, all parameters of the thermal feature vector, and all parameters of the device coupling influence vector, forming the decorative light-thermal coupling feature vector after splicing.

[0031] Step S300: Establish the coupling relationship between optical behavior and thermal behavior based on the decorative light-heat coupling feature vector to obtain the light-heat coupling energy consumption function model. The light-heat coupling energy consumption function model is obtained by fusing the light-to-lighting energy consumption influence model and the light-to-heat load influence model.

[0032] Specifically, the optical behavior in the decorative light-heat coupling feature vector includes light reflection, absorption, and light utilization processes, while the thermal behavior includes temperature changes and heat transfer processes. A coupling relationship model is constructed, using the decorative light-heat coupling feature vector as the core input, to link the mutual influence between optical and thermal behaviors. That is, changes in light energy generated by optical behavior affect the heat energy distribution of thermal behavior, and temperature changes in thermal behavior indirectly affect the light utilization efficiency of optical behavior. Two models are constructed: one for the influence of light on lighting energy consumption, and another for the influence of light on heat load. These two models correspond to the effects of optical behavior on the energy consumption of different devices. A model fusion strategy is then used to integrate the outputs of the two models, eliminating parameter conflicts between them. Finally, a light-heat coupling energy consumption function model that characterizes the total energy consumption variation of the decorative space is obtained. This model can output the corresponding total energy consumption value based on the input optical and thermal parameters. The model parameters for all monitoring areas are summarized and stored in a database. The specific implementation example is as follows: Taking the decorative light-heat coupling feature vector as input, the optical control variables are substituted into the calculation of effective illuminance. The effective illuminance is compared with the target illuminance to obtain the power adjustment amount of the lighting equipment, and a model of the influence of light on lighting energy consumption is constructed. The thermal control variables are substituted into the calculation of surface temperature rise. The surface temperature rise is compared with the reference temperature rise to obtain the air conditioning load adjustment amount, and a model of the influence of light on heat load is constructed. The outputs of the two models are weighted according to energy consumption sensitivity and then fused to obtain a light-heat coupling energy consumption function model that can output the total energy consumption.

[0033] In one possible implementation, a coupling relationship between optical and thermal behaviors is established based on the decorative light-heat coupling feature vector to obtain a light-heat coupling energy consumption function model. Step S300 further includes step S310, where a variable mapping relationship is established analytically based on the decorative light-heat coupling feature vector to obtain a set of model input variables, including optical control variables, thermal control variables, and equipment response variables. Specifically, variable mapping rules are established to map parameters directly related to optical behavior in the decorative light-heat coupling feature vector, including reflectivity, absorptivity, and light utilization efficiency, to optical control variables. These variables can be manually controlled by adjusting the surface treatment method and material type of the decorative material. Parameters directly related to thermal behavior in the decorative light-heat coupling feature vector, including thermal time constant, equivalent heat capacity, and thermal conductivity, are mapped to thermal control variables. These variables can be adjusted by adjusting the thickness and material of the decorative material. Parameters related to equipment operation in the decorative light-heat coupling feature vector, including lighting coupling coefficient and air conditioning coupling coefficient, are mapped to equipment response variables. These variables can be adjusted responsively by adjusting the operating parameters of the lighting and air conditioning equipment. All variables obtained from the mapping are summarized to form a set of model input variables, which are then stored in the database.

[0034] Step S320: The effective illuminance is calculated using the optical control variables as input. A lighting demand function is introduced to respond to the effective illuminance based on the target illuminance, constructing a light-on-light energy consumption impact model. Specifically, the effective illuminance within the decorative space is calculated by combining the reflectance and light utilization efficiency parameters in the optical control variables, as well as the rated operating parameters of the lighting equipment. Effective illuminance is the actual usable light intensity within the space that meets usage requirements. A lighting demand function is introduced to characterize the response relationship between the target illuminance and the effective illuminance. Target illuminance is set for different usage scenarios in the decorative space. The difference between the effective illuminance and the target illuminance is compared using the lighting demand function. When the effective illuminance is lower than the target illuminance, the output power adjustment coefficient that the lighting equipment needs to increase is output; when the effective illuminance is higher than the target illuminance, the output power adjustment coefficient that the lighting equipment needs to decrease is output. Based on the above process, a light-on-light energy consumption impact model is constructed. This model uses the optical control variables as input and lighting energy consumption as output. It can output corresponding lighting energy consumption values ​​based on changes in optical parameters. After the model is constructed, it is stored in a database. A specific implementation example is as follows: Multiply the real-time illuminance by the reflectance, and then by the light utilization efficiency to obtain the illuminance that can be actually used in the space and meets the usage requirements; this is the effective illuminance. Using the effective illuminance as the first input and the target illuminance as the second input, a comparison and judgment relationship is established. When the effective illuminance is less than the target illuminance, an instruction to increase the lighting power is output; when the effective illuminance is greater than or equal to the target illuminance, an instruction to decrease or maintain the lighting power is output. This comparison and judgment relationship is the lighting demand function. Dividing the target illuminance by the effective illuminance yields the lighting power adjustment coefficient. Multiplying the current output power of the lighting equipment by the lighting power adjustment coefficient gives the adjusted output power. Controlling the operation of the lighting equipment according to this output power achieves lighting regulation.

[0035] Step S330: The thermal control variables are used as input to calculate the surface temperature rise. An air conditioning load function is introduced to respond to the surface temperature rise, constructing a light-on-heat load influence model. Specifically, the surface temperature rise of the decorative material is calculated by combining the thermal time constant, equivalent heat capacity, and thermal conductivity parameters in the thermal control variables. The surface temperature rise is the difference between the surface temperature of the decorative material and the ambient temperature. An air conditioning load function is introduced to characterize the response relationship between the surface temperature rise and the air conditioning load. A target set temperature for the air conditioner is set. The difference between the surface temperature rise and the reference temperature rise (i.e., the temperature rise when the surface temperature equals the target set temperature) is compared using the air conditioning load function. When the surface temperature rise is higher than the reference temperature rise, the adjustment coefficient for increasing the cooling load of the air conditioner is output; when the surface temperature rise is lower than the reference temperature rise, the adjustment coefficient for decreasing the cooling load of the air conditioner is output. Based on the above process, a light-on-heat load influence model is constructed. This model takes the thermal control variables as input and the air conditioning heat load (cooling or heating load) as output. It can output the corresponding air conditioning load value according to the change of thermal parameters. After the model is constructed, it is stored in the database. A specific implementation example is as follows: Dividing the photothermal energy by the equivalent heat capacity yields the surface temperature rise of the decorative material due to light absorption, which is the surface temperature rise. Using the surface temperature rise as the first input and the reference temperature rise as the second input, a comparison relationship is established. When the surface temperature rise is greater than the reference temperature rise, an instruction to increase the air conditioning cooling load is output; when the surface temperature rise is less than or equal to the reference temperature rise, an instruction to reduce or maintain the cooling load is output. This comparison relationship is the air conditioning load function. Dividing the surface temperature rise by the reference temperature rise yields the air conditioning load adjustment coefficient. Multiplying the reference cooling load by this adjustment coefficient gives the adjusted cooling load. Controlling the air conditioning operation according to this load achieves the adjustment of the air conditioning load.

[0036] Step S340: The light-on-lighting energy consumption model and the light-on-heat load model are fused to obtain a light-heat coupled energy consumption function model. Specifically, a fusion framework is constructed, using the set of model input variables obtained in step S310 as a unified input. The outputs of the two models (lighting energy consumption and air conditioning heat load) are used as the fusion objects. During the fusion process, the focus is on the intrinsic relationship between the two models, i.e., the light energy generated by the operation of lighting equipment will affect the surface temperature rise of decorative materials, thereby affecting the air conditioning load. The fusion strategy eliminates the model error caused by this mutual influence, and integrates the outputs of the two models into an output value that can characterize the total energy consumption of the decorative space, ultimately forming a light-heat coupled energy consumption function model. The constructed model is verified by using historical energy consumption data collected in step S100, substituting the historical input parameters into the model, and comparing the total energy consumption output by the model with the actual historical energy consumption. If the error is controlled within a reasonable range, the model is qualified; otherwise, the fusion strategy is adjusted until the model is qualified. Qualified models are stored in the database. A specific implementation example is as follows: The lighting energy consumption response value and the air conditioning load energy consumption response value are calculated separately. Weights are assigned based on the proportion of lighting and air conditioning energy consumption in the total energy consumption, and the sum of the two weights is 1. The lighting energy consumption response value is multiplied by its corresponding weight, and the air conditioning load energy consumption response value is multiplied by its corresponding weight. The two products are then added together to obtain the total energy consumption value. Through this weighted summation method, the lighting energy consumption model and the air conditioning load model are integrated into a unified light-heat coupled energy consumption function model.

[0037] In one possible implementation, the light-on-lighting energy consumption influence model and the light-on-heat load influence model are fused to obtain a light-heat coupled energy consumption function model. Step S340 further includes step S341, obtaining the lighting energy consumption response value output by the light-on-lighting energy consumption influence model and the load energy consumption response value output by the light-on-heat load influence model. Specifically, the light-on-lighting energy consumption influence model constructed in step S320 and the light-on-heat load influence model constructed in step S330 are started, and the set of model input variables obtained in step S310 is retrieved from the database. Optical control variables are input into the light-on-lighting energy consumption influence model. The model calculates and outputs the corresponding lighting energy consumption response value based on its internal calculation logic and the input parameters. This response value is the lighting energy consumption value per unit time, which can reflect the impact of changes in optical control variables on lighting energy consumption. Thermal control variables are input into the light-on-heat load influence model. The model calculates and outputs the corresponding load energy consumption response value based on its internal calculation logic and the input parameters. This response value is the air conditioning heat load value per unit time, which can reflect the impact of changes in thermal control variables on air conditioning load. The lighting energy consumption response value and load energy consumption response value corresponding to each set of input variables are associated and stored to ensure that the input variables and response values ​​correspond one-to-one and are stored in the database.

[0038] Step S342 involves assigning weights to the lighting energy consumption response values ​​and load energy consumption response values, based on energy consumption sensitivity analysis. Specifically, historical energy consumption data of the decorative space collected in step S100 is retrieved from the database for energy consumption sensitivity analysis. During the analysis, the lighting energy consumption response values ​​and load energy consumption response values ​​are used as the analysis objects. Small disturbances are applied to both response values, and the change in total energy consumption of the decorative space after each disturbance is recorded. The energy consumption sensitivity coefficient of the two response values ​​is calculated by the ratio of the change in total energy consumption to the disturbance amplitude of the response values. The larger the sensitivity coefficient, the greater the impact of the response value on the total energy consumption. Weights are assigned based on the calculated energy consumption sensitivity coefficients, with the principle that the larger the sensitivity coefficient, the higher the weight of the corresponding response value, and the sum of the weights of all response values ​​is 1. The assigned weights are then associated with and stored in the database, specifying the weight coefficient for each response value.

[0039] Step S343: The lighting energy consumption response value and the load energy consumption response value are normalized and fused according to the weights to obtain a light-heat coupled energy consumption function model. Specifically, the two response values ​​are normalized to eliminate fusion errors caused by differences in units and value ranges. During the normalization process, the value of each response value is adjusted to the range of 0 to 1. Specifically, each response value is subtracted from the minimum value of that type of response value and then divided by the difference between the maximum and minimum values ​​of that type of response value. After normalization, the two normalized response values ​​are weighted and summed according to the assigned weight coefficients to obtain the normalized total energy consumption response value. Then, combined with the maximum and minimum values ​​of historical energy consumption data, the normalized total energy consumption response value is converted into the actual total energy consumption value. The operational relationship between the input variables and the converted actual total energy consumption value is solidified to form the light-heat coupled energy consumption function model. The model is validated to ensure that the error between the model's output total energy consumption and the actual energy consumption is within a reasonable range. After successful validation, the model is stored in the database.

[0040] Step S400: Based on the light-heat coupling energy consumption function model, perform multidimensional energy consumption contribution decomposition on the decorative space, conduct energy consumption impact sensitivity analysis according to the multidimensional energy consumption contribution index obtained from the decomposition, generate a multidimensional collaborative optimization strategy based on the energy consumption impact sensitivity analysis results, and issue the multidimensional collaborative optimization strategy to execute energy-saving feedback control of the decorative space.

[0041] Specifically, the dimensions of the multidimensional energy consumption contribution decomposition correspond to the classification of input variables in the light-heat coupled energy consumption function model, namely, the dimensions of optical control variables, thermal control variables, and equipment response variables. Each dimension corresponds to several specific energy consumption contribution indicators. Based on the light-heat coupled energy consumption function model, by setting a baseline operating condition and perturbation control variables, the contribution of each dimension and each variable to the total energy consumption is quantified, resulting in multidimensional energy consumption contribution indicators. Based on these indicators, the impact of each indicator on the change in total energy consumption is calculated, yielding a sensitivity index. The optimization priority of each indicator is determined based on the sensitivity index ranking. Based on the optimization priority, an optimization objective of minimizing total energy consumption and a reasonable search step size are defined. An optimization algorithm is used to search for the optimal parameter combination in priority order under the optimization objective, generating a multidimensional collaborative optimization strategy that includes measures such as adjusting decorative materials and adjusting equipment operating parameters. The generated optimization strategy is then distributed to the equipment control terminal in the decorated space. The control terminal adjusts the operating parameters of lighting and air conditioning equipment, as well as the relevant characteristics of decorative materials, according to the optimization strategy, executing energy-saving feedback control. Simultaneously, real-time energy consumption data after control is collected and fed back to the light-heat coupled energy consumption function model for iterative optimization, ensuring continuous and stable energy-saving effects.

[0042] In one possible implementation, the decorative space is decomposed into a multidimensional energy consumption contribution based on the light-heat coupled energy consumption function model. Step S400 further includes step S410, setting a baseline operating condition and obtaining the baseline total energy consumption output by the light-heat coupled energy consumption function model under the baseline operating condition. Specifically, the setting criteria for the baseline operating condition are determined based on the conventional usage scenarios of the decorative space. Conventional usage scenarios are determined according to the purpose of the decorative space, such as a home living scenario or an office scenario. The equipment operating parameters, environmental parameters, and usage duration under the baseline operating condition are clarified. Based on the baseline operating condition, the baseline values ​​of the model input variables are determined, that is, the conventional and reasonable values ​​of each variable in the model input variable set obtained in step S310. For example, the optical control variable takes the typical parameters of conventional decorative materials, the thermal control variable takes the thermal parameters of conventional decorative materials, and the equipment response variable takes the parameters under normal operating conditions of the equipment. The baseline values ​​are substituted into the light-heat coupled energy consumption function model to calculate the total energy consumption value output by the model. This value is the baseline total energy consumption, which is used as a baseline reference for subsequent energy consumption contribution decomposition. The baseline operating condition settings, baseline values ​​of input variables, and baseline total energy consumption are associated and stored in the database.

[0043] Step S420: A single-dimensional control variable is perturbed using the baseline operating condition to obtain the total energy consumption of the single-dimensional control variable. Specifically, the baseline operating condition parameters, baseline values ​​of the input variables, and baseline total energy consumption set in step S410 are retrieved from the database. A single-dimensional control variable perturbation rule is formulated. The perturbation rule is as follows: only one control variable is perturbed at a time, while the baseline values ​​of other control variables remain unchanged to avoid the inability to distinguish the cause of energy consumption changes due to simultaneous perturbation of multiple variables. The perturbation amplitude is set to ±10%, which can be adjusted according to actual engineering needs. Each control variable is subjected to positive perturbation (value increases by 10%) and negative perturbation (value decreases by 10%). According to the perturbation rule, each control variable is perturbed sequentially. The value of the control variable after each perturbation is substituted into the light-heat coupling energy consumption function model to calculate the total energy consumption value output by the model. This value is the total energy consumption of the single-dimensional control variable under the perturbation direction. Each single-dimensional control variable corresponds to two sets of total disturbance energy consumption, namely positive disturbance and negative disturbance. The disturbance direction, post-disturbance value, and corresponding total disturbance energy consumption of each control variable are associated and stored in the database.

[0044] Step S430: The multi-dimensional energy consumption contribution of each control variable is quantified sequentially according to the total energy consumption of the disturbance, yielding a multi-dimensional energy consumption contribution index. Specifically, the calculation logic for energy consumption contribution quantification is to quantify the contribution of each control variable to the total energy consumption by comparing the difference between the total disturbance energy consumption and the baseline total energy consumption. Specifically: the difference between each total disturbance energy consumption and the baseline total energy consumption is calculated. This difference represents the energy consumption contribution of the corresponding control variable in that disturbance direction. If the difference is positive, it indicates that the disturbance of this variable leads to an increase in total energy consumption; if the difference is negative, it indicates that the disturbance of this variable leads to a decrease in total energy consumption. Then, the energy consumption contribution ratio is calculated, which is the ratio of the absolute value of the energy consumption contribution to the baseline total energy consumption, used to characterize the proportion of the variable's influence on the total energy consumption. The energy consumption contribution and contribution ratio of the control variables for each dimension are summarized, and the total energy consumption contribution (the sum of the energy consumption contributions of all control variables under that dimension) and the total energy consumption contribution ratio (the ratio of the absolute value of the total energy consumption contribution of that dimension to the sum of the total energy consumption contributions of all dimensions) for each dimension are calculated. The total energy consumption contribution and total energy consumption contribution ratio of each dimension, as well as the energy consumption contribution and energy consumption contribution ratio of each control variable, are summarized to form a multidimensional energy consumption contribution index, which is then stored in the database according to the dimensions.

[0045] In one possible implementation, energy consumption impact sensitivity analysis is performed according to the multidimensional energy consumption contribution indicators obtained from the decomposition. Step S400 further includes step S440, whereby, based on each dimension of the multidimensional energy consumption contribution indicators, Monte Carlo sampling is used to calculate the sensitivity indicators affecting the overall energy consumption change, including a first-order sensitivity index and a total-order sensitivity index. The first-order sensitivity index is used to quantify the contribution of a single variable itself to the total energy consumption variance, and the total-order sensitivity index is used to quantify the contribution of a single variable and its interaction with other variables to the total energy consumption variance. Specifically, a Monte Carlo sampling tool is used, and sampling parameters are set, such as setting the number of samplings to 10,000, setting the sampling range of each variable to ±20% of its baseline value, and using a uniform sampling distribution to ensure that the sampled data can cover the reasonable value range of the variables. The sampling tool is started, and 10,000 sets of input variable values ​​are randomly generated according to the sampling range of each variable. Each set of values ​​includes the specific values ​​of all control variables, and each set of values ​​conforms to the reasonable value range of the variables. Substituting the sampled input variable values ​​into the light-heat coupled energy consumption function model, the total energy consumption output value for each group was calculated, resulting in 10,000 sets of total energy consumption data. Based on the sampled input variable data and total energy consumption data, the Sobel method was used to calculate sensitivity indices. During the calculation, the variance of total energy consumption was decomposed into the variance of the contribution of each individual variable and the variance of the contribution of interactions between variables. The first-order sensitivity index was obtained by dividing the variance of the contribution of each individual variable by the total variance of total energy consumption, used to quantify the influence of an individual variable on changes in total energy consumption. The total-order sensitivity index was obtained by summing the variance of the contribution of each individual variable and the variance of the contribution of that variable to all other variables, then dividing by the total variance of total energy consumption, used to quantify the combined influence of an individual variable and its interactions with other variables on changes in total energy consumption. The first-order sensitivity index and the total-order sensitivity index of each control variable were recorded, categorized and summarized by dimension to form a set of sensitivity indices, which were then stored in a database.

[0046] Step S450: The energy consumption impact sensitivity analysis results are obtained by sorting the variables according to the sensitivity indices and corresponding to the multidimensional energy consumption contribution indices. These results include optimization priority identifiers configured based on the sorting order. Specifically, the overall sensitivity index is used as the primary sorting criterion, and the first-order sensitivity index as a secondary sorting criterion. A sorting rule is established: the larger the overall sensitivity index, the higher the optimization priority of the variable; if two variables have the same overall sensitivity index, the larger the first-order sensitivity index, the higher the optimization priority. All control variables are sorted according to this rule to obtain a variable optimization priority sequence. Variables ranked higher in the priority sequence have a greater comprehensive impact on the change in total energy consumption and require priority optimization. Based on the sorting results, a corresponding optimization priority identifier is configured for each control variable. For example, the top 3 variables are configured with first-level priority (highest priority), variables ranked 4th to 6th with second-level priority, and the remaining variables with third-level priority. The priority identifier clarifies the execution order of the optimization strategy. The sorted variable sequence, the sensitivity index of each variable, and the corresponding optimization priority identifier are summarized to form the energy consumption impact sensitivity analysis results, which are then stored in the database.

[0047] In one possible implementation, a multi-dimensional collaborative optimization strategy is generated based on the results of energy consumption impact sensitivity analysis. Step S400 further includes step S460, defining the optimization objective and search step size for minimizing total energy consumption. Specifically, the optimization objective is to minimize the total energy consumption of the decorative space. Constraints include a reasonable range of values ​​for control variables, a safe operating range for equipment, and a practically adjustable range for decorative materials, ensuring the feasibility of the optimization strategy. A reasonable search step size is set based on the accuracy of the control variable values ​​and optimization efficiency. The search step size is the adjustment range of the control variables in each optimization. The step size setting needs to balance optimization accuracy and optimization speed. An excessively large step size may prevent finding the optimal solution, while an excessively small step size will increase optimization time. For example, the search step size for all control variables can be set to 5% of their baseline values. The step size can be adjusted according to the sensitivity of the variables; the step size for highly sensitive variables can be appropriately reduced to improve optimization accuracy. The optimization objective, optimization constraints, and search step size are recorded and stored in a database.

[0048] Step S470: Based on the optimization priority identifiers from the energy consumption impact sensitivity analysis and the search step size, a priority queue sequential search is performed under the optimization objective until the convergence condition of the optimization objective is met, generating a multi-dimensional collaborative optimization strategy. Specifically, a particle swarm optimization algorithm is used to construct a priority queue sequential search framework. The search process follows the order of the optimization priority identifiers, i.e., first, the first-level priority variables are optimized, then the second-level priority variables are optimized, and finally the third-level priority variables are optimized, ensuring that the variables with the greatest impact on total energy consumption are optimized first. During the search process, with the goal of minimizing total energy consumption, the values ​​of each control variable are gradually adjusted according to the set search step size. After each adjustment, the adjusted variable values ​​are substituted into the light-heat coupling energy consumption function model to calculate the corresponding total energy consumption value. The change in total energy consumption before and after the adjustment is compared, and the variable values ​​that can reduce total energy consumption are retained. At the same time, it is determined in real time whether the convergence condition is met. The convergence condition is set as follows: after multiple consecutive adjustments of variable values, the change in total energy consumption is less than a preset threshold, and the total energy consumption at this time is close to or reaches the theoretical minimum energy consumption value. When the convergence condition is met, the search stops. The optimal values ​​of all control variables, adjustment schemes for equipment operating parameters, and suggestions for adjusting decorative materials are then summarized to form a multi-dimensional collaborative optimization strategy. This strategy is stored in a database and sent to the equipment control terminal for execution of energy-saving feedback control of the decorative space.

[0049] This application embodiment deploys a sensor network within the decorative space to collect multi-source sensor data related to optics, thermal dynamics, and equipment operation assistance. Based on this data, it performs inversion modeling of the surface characteristics of decorative materials to obtain a decorative light-heat coupling feature vector. Based on this feature vector, it establishes a coupling relationship between optical and thermal behaviors. By fusing models of the impact of light on lighting energy consumption and light on heat load, it obtains a light-heat coupling energy consumption function model. Based on this model, it performs multi-dimensional energy consumption contribution decomposition and energy consumption impact sensitivity analysis, generates multi-dimensional collaborative optimization strategies, and issues and executes energy-saving feedback control for the decorative space. This solves the technical problem that existing decorative space energy consumption optimization strategies lack scientific basis and are difficult to achieve refined and intelligent management. It achieves the technical effect of providing a scientific basis for decorative space energy consumption optimization and realizing refined and intelligent energy consumption management.

[0050] In the above text, refer to Figure 1 A sensor-based energy-saving analysis method for decorative spaces according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 2 A sensor-based energy-saving analysis system for decorative spaces according to an embodiment of the present invention is described.

[0051] The energy-saving analysis system for decorative spaces based on sensor analysis according to embodiments of the present invention addresses the technical problem that existing optimization strategies for decorative spaces lack scientific basis, making it difficult to achieve refined and intelligent control. It aims to provide a scientific basis for energy consumption optimization in decorative spaces and achieve the technical effect of refined and intelligent energy consumption control. The energy-saving analysis system for decorative spaces based on sensor analysis includes: a multi-source sensor data acquisition module 10, a decorative light-heat coupling feature vector generation module 20, a light-heat coupling energy consumption function model construction module 30, and an energy-saving feedback control module 40.

[0052] The multi-source sensor data acquisition module 10 is used to deploy a sensor network within the decorative space to collect multi-source sensor datasets, including optical related data, thermal related data, and equipment operation auxiliary data. The decorative light-heat coupling feature vector generation module 20 is used to perform surface characteristic inversion modeling of decorative materials based on the optical related data, thermal related data, and equipment operation auxiliary data to obtain decorative light-heat coupling feature vectors. The light-heat coupling energy consumption function model construction module 30 is used to establish the coupling relationship between optical behavior and thermal behavior based on the decorative light-heat coupling feature vectors to obtain a light-heat coupling energy consumption function model, which is obtained by fusing the light-to-lighting energy consumption influence model and the light-to-heat load influence model. The energy-saving feedback control module 40 is used to perform multi-dimensional energy consumption contribution decomposition of the decorative space based on the light-heat coupling energy consumption function model, perform energy consumption impact sensitivity analysis according to the multi-dimensional energy consumption contribution index obtained by decomposition, generate a multi-dimensional collaborative optimization strategy based on the energy consumption impact sensitivity analysis results, and issue the multi-dimensional collaborative optimization strategy to execute the energy-saving feedback control of the decorative space.

[0053] The specific configuration of the decorative light-heat coupling feature vector generation module 20 is described in detail below: As mentioned above, the decorative light-heat coupling feature vector generation module 20 can further include: a multi-source time-series alignment processing unit for performing multi-source time-series alignment processing on the optical related data, thermal related data, and equipment operation auxiliary data to obtain a regional-level time-series data set; an optical characteristic parameter inversion unit for performing optical characteristic parameter inversion based on the regional-level time-series data set, including reflectivity estimation, absorptivity estimation, and light utilization efficiency parameters, to obtain an optical feature vector; a thermal characteristic parameter inversion unit for performing thermal characteristic parameter inversion based on the regional-level time-series data set, including thermal time constant estimation, equivalent heat capacity estimation, and thermal conductivity estimation, to obtain a thermal feature vector; and a photothermal effect coupling modeling unit for performing photothermal effect coupling modeling based on the optical feature vector and the thermal feature vector, and obtaining the decorative light-heat coupling feature vector based on the constructed photothermal effect coupling model.

[0054] Specifically, the decorative light-heat coupling feature vector is obtained based on the constructed photothermal effect coupling model. The photothermal effect coupling modeling unit may further include: a device coupling influence vector extraction subunit for extracting device coupling influence vectors based on the constructed photothermal effect coupling model, including the lighting coupling coefficient characterizing the influence of light reflection on lighting demand, and the air conditioning coupling coefficient characterizing the influence of surface temperature on cooling load; and a vector fusion subunit for fusing the device coupling influence vector, optical feature vector, and thermal feature vector to obtain the decorative light-heat coupling feature vector.

[0055] The detailed description of the specific configuration of the light-heat coupling energy consumption function model construction module 30 is as follows: As mentioned above, the coupling relationship between optical behavior and thermal behavior is established based on the decorative light-heat coupling feature vector to obtain the light-heat coupling energy consumption function model. The light-heat coupling energy consumption function model construction module 30 may further include: a variable mapping relationship establishment unit for analyzing and establishing variable mapping relationships based on the decorative light-heat coupling feature vector to obtain a set of model input variables, including optical control variables, thermal control variables, and equipment response variables; a light-to-lighting energy consumption influence model construction unit for using the optical control variables as input to calculate effective illuminance, introducing a lighting demand function to perform a demand response based on target illuminance for the effective illuminance, and constructing a light-to-lighting energy consumption influence model; a light-to-heat load influence model construction unit for using the thermal control variables as input to calculate surface temperature rise, introducing an air conditioning load function to perform a load response for the surface temperature rise, and constructing a light-to-heat load influence model; and a model fusion unit for fusing the light-to-lighting energy consumption influence model and the light-to-heat load influence model to obtain the light-heat coupling energy consumption function model.

[0056] The model integrates the light-to-lighting energy consumption influence model and the light-to-heat load influence model to obtain a light-heat coupled energy consumption function model. The model fusion unit may further include: a response value acquisition subunit for acquiring the lighting energy consumption response value output by the light-to-lighting energy consumption influence model and the load energy consumption response value output by the light-to-heat load influence model; a weight allocation subunit for allocating weights to the lighting energy consumption response value and the load energy consumption response value, the weights being analyzed based on energy consumption sensitivity; and a normalized response value fusion subunit for fusing the lighting energy consumption response value and the load energy consumption response value according to the weights to obtain the light-heat coupled energy consumption function model.

[0057] The detailed description of the specific configuration of the energy-saving feedback control module 40 is explained as follows: As mentioned above, based on the light-heat coupling energy consumption function model, the decorative space is decomposed into multidimensional energy consumption contributions. The energy-saving feedback control module 40 may further include: a benchmark total energy consumption acquisition unit for setting a benchmark operating condition and acquiring the benchmark total energy consumption output by the light-heat coupling energy consumption function model under the benchmark operating condition; a single-dimensional control variable disturbance unit for disturbing the single-dimensional control variable through the benchmark operating condition to obtain the disturbed total energy consumption of the single-dimensional control variable; and a multidimensional energy consumption contribution quantification unit for sequentially performing multidimensional energy consumption contribution quantification on the disturbed total energy consumption of the single-dimensional control variable according to the disturbed total energy consumption to obtain a multidimensional energy consumption contribution index.

[0058] The energy-saving feedback control module 40 may further include: a sensitivity index calculation unit for calculating the sensitivity index affecting the overall energy consumption change based on each dimension of the multidimensional energy consumption contribution index using Monte Carlo sampling; and an index sorting unit for sorting the sensitivity indexes to obtain the energy consumption impact sensitivity analysis results corresponding to the multidimensional energy consumption contribution indexes, wherein the energy consumption impact sensitivity analysis results include an optimization priority identifier based on the sorting configuration.

[0059] The energy-saving feedback control module 40, which generates a multi-dimensional collaborative optimization strategy based on the energy consumption impact sensitivity analysis results, may further include: an optimization target definition unit for defining the optimization target and search step size for minimizing total energy consumption; and a priority queue sequential search unit for performing a priority queue sequential search under the optimization target based on the optimization priority identifier and the search step size, until the convergence condition of the optimization target is met, thereby generating a multi-dimensional collaborative optimization strategy.

[0060] The sensitivity index calculation unit may further include: using Monte Carlo sampling to calculate sensitivity indices affecting overall energy consumption changes, including a first-order sensitivity index and a total-order sensitivity index; the first-order sensitivity index is used to quantify the contribution of a single variable itself to the total energy consumption variance, and the total-order sensitivity index is used to quantify the contribution of a single variable and its interaction with other variables to the total energy consumption variance.

[0061] The energy-saving analysis system for decorative spaces based on sensor analysis provided in this invention can execute the energy-saving analysis method for decorative spaces based on sensor analysis provided in any embodiment of this invention, and has the corresponding functional modules and beneficial effects of the method.

[0062] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0063] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A sensor-based energy-saving analysis method for decorative spaces, characterized in that, The method includes: Deploy a sensor network within the decorative space to collect multi-source sensor datasets, including optical data, thermal data, and equipment operation auxiliary data; Based on the optical related data, thermal related data, and equipment operation auxiliary data, the surface properties of the decorative material are inverted and modeled to obtain the decorative light-heat coupling feature vector. Based on the decorative light-heat coupling feature vector, the coupling relationship between optical behavior and thermal behavior is established, and the light-heat coupling energy consumption function model is obtained. The light-heat coupling energy consumption function model is obtained by fusing the light-to-lighting energy consumption influence model and the light-to-heat load influence model. Based on the light-heat coupled energy consumption function model, a multidimensional energy consumption contribution decomposition is performed on the decorative space. According to the multidimensional energy consumption contribution index obtained from the decomposition, an energy consumption impact sensitivity analysis is conducted. Based on the results of the energy consumption impact sensitivity analysis, a multidimensional collaborative optimization strategy is generated, and the multidimensional collaborative optimization strategy is issued to execute the energy-saving feedback control of the decorative space.

2. The energy-saving analysis method for decorative spaces based on sensor analysis as described in claim 1, characterized in that, The surface properties of decorative materials are inverted and modeled based on the aforementioned optical, thermal, and equipment operation auxiliary data. The method includes: The optical-related data, thermal-related data, and equipment operation auxiliary data are subjected to multi-source time-series alignment processing to obtain a regional-level time-series data set. Based on the aforementioned regional time-series data set, optical characteristic parameters are inverted, including reflectance estimation, absorptivity estimation, and light utilization efficiency parameters, to obtain optical feature vectors. Based on the aforementioned regional time-series data set, thermal characteristic parameters are inverted, including thermal time constant estimation, equivalent heat capacity estimation, and thermal conductivity estimation, to obtain thermal feature vectors. The photothermal effect coupling model is performed based on the optical feature vector and the thermal feature vector, and the decorative light-heat coupling feature vector is obtained based on the constructed photothermal effect coupling model.

3. The energy-saving analysis method for decorative spaces based on sensor analysis as described in claim 2, characterized in that, The decorative light-heat coupling feature vector is obtained based on the constructed photothermal effect coupling model. The method includes: Based on the constructed photothermal effect coupling model, the device coupling influence vector is extracted, including the lighting coupling coefficient characterizing the influence of light reflection on lighting demand, and the air conditioning coupling coefficient characterizing the influence of surface temperature on cooling load. The device coupling influence vector, optical feature vector, and thermal feature vector are fused to obtain the decorative light-thermal coupling feature vector.

4. The energy-saving analysis method for decorative spaces based on sensor analysis as described in claim 1, characterized in that, Based on the decorative light-heat coupling feature vector, the coupling relationship between optical behavior and thermal behavior is established to obtain the light-heat coupling energy consumption function model. The method includes: Based on the decorative light-heat coupling feature vector, a variable mapping relationship is established through analysis to obtain the model input variable set, including optical control variables, thermal control variables, and device response variables; The optical control variables are used as inputs to calculate the effective illuminance. An illumination demand function is introduced to perform a demand response based on the target illuminance for the effective illuminance, and a model of the impact of light on illumination energy consumption is constructed. The thermal control variables are used as inputs to calculate the surface temperature rise. An air conditioning load function is introduced to perform a load response on the surface temperature rise, and a model of the influence of light on heat load is constructed. By fusing the light-to-lighting energy consumption model and the light-to-heat load model, a light-heat coupled energy consumption function model is obtained.

5. The energy-saving analysis method for decorative spaces based on sensor analysis as described in claim 4, characterized in that, The light-heat coupled energy consumption function model is obtained by fusing the light-to-lighting energy consumption model and the light-to-heat load model. The method includes: Obtain the lighting energy consumption response value output by the light-to-lighting energy consumption influence model and the load energy consumption response value output by the light-to-heat load influence model; The lighting energy consumption response value and the load energy consumption response value are weighted and assigned based on energy consumption sensitivity analysis. The lighting energy consumption response value and the load energy consumption response value are normalized and fused according to the weights to obtain the light-heat coupled energy consumption function model.

6. The energy-saving analysis method for decorative spaces based on sensor analysis as described in claim 1, characterized in that, The method for decomposing the energy consumption contribution of the decorative space based on the aforementioned light-heat coupled energy consumption function model includes: Set a baseline operating condition, and obtain the baseline total energy consumption output by the optical-thermal coupling energy consumption function model under the baseline operating condition; The total energy consumption of the single-dimensional control variable is obtained by perturbing the single-dimensional control variable under the reference operating condition. The multidimensional energy consumption contribution of the total energy consumption of the single-dimensional control variable is quantified sequentially according to the total energy consumption of the disturbance, so as to obtain the multidimensional energy consumption contribution index.

7. The energy-saving analysis method for decorative spaces based on sensor analysis as described in claim 6, characterized in that, Sensitivity analysis of energy consumption impact was conducted based on the multidimensional energy consumption contribution indicators obtained from the decomposition, including the following methods: Based on each dimension of the multidimensional energy consumption contribution index, Monte Carlo sampling is used to calculate the sensitivity index affecting the overall energy consumption change. The energy consumption impact sensitivity analysis results are obtained by sorting according to the sensitivity indicators and corresponding to the multidimensional energy consumption contribution indicators. The energy consumption impact sensitivity analysis results include optimization priority identifiers based on the sorting configuration.

8. The energy-saving analysis method for decorative spaces based on sensor analysis as described in claim 7, characterized in that, A multidimensional collaborative optimization strategy is generated based on the results of energy consumption impact sensitivity analysis. The method includes: Define the optimization objective and search step size for minimizing total energy consumption; Based on the optimization priority identifier and the search step size derived from the energy consumption impact sensitivity analysis, a priority queue sequential search is performed under the optimization objective until the convergence condition of the optimization objective is met, thereby generating a multi-dimensional collaborative optimization strategy.

9. The energy-saving analysis method for decorative spaces based on sensor analysis as described in claim 6, characterized in that, Monte Carlo sampling was used to calculate the sensitivity indices affecting overall energy consumption changes, including the first-order sensitivity index and the total-order sensitivity index. The first-order sensitivity index is used to quantify the contribution of a single variable to the total energy consumption variance, while the total-order sensitivity index is used to quantify the contribution of a single variable and its interaction with other variables to the total energy consumption variance.

10. A sensor-based energy-saving analysis system for decorative spaces, characterized in that, The system is used to implement the sensor-based energy-saving analysis method for decorative spaces according to any one of claims 1-9, the system comprising: The multi-source sensor data acquisition module is used to deploy a sensor network within the decorative space to collect multi-source sensor datasets, including optical data, thermal data, and equipment operation auxiliary data. The decorative light-heat coupling feature vector generation module is used to perform surface property inversion modeling of decorative materials based on the optical related data, thermal related data and equipment operation auxiliary data, and to obtain decorative light-heat coupling feature vectors. The light-heat coupling energy consumption function model construction module is used to establish the coupling relationship between optical behavior and thermal behavior based on the decorative light-heat coupling feature vector, and obtain the light-heat coupling energy consumption function model. The light-heat coupling energy consumption function model is obtained by fusing the light-to-lighting energy consumption influence model and the light-to-heat load influence model. The energy-saving feedback control module is used to perform multi-dimensional energy consumption contribution decomposition on the decorative space based on the light-heat coupling energy consumption function model, perform energy consumption impact sensitivity analysis according to the multi-dimensional energy consumption contribution index obtained by the decomposition, generate a multi-dimensional collaborative optimization strategy based on the energy consumption impact sensitivity analysis results, and issue the multi-dimensional collaborative optimization strategy to execute the energy-saving feedback control of the decorative space.

Images