CN-121977247-A - Energy-saving control method and system based on artificial intelligence and thermal insulation material

CN121977247ACN 121977247 ACN121977247 ACN 121977247ACN-121977247-A

Abstract

The invention relates to the technical field of energy conservation, in particular to an energy conservation control method and system based on artificial intelligence and thermal insulation materials, wherein the method comprises the steps of obtaining a thermal state prediction result of a house in a future preset time range based on building structure data, indoor and outdoor environment data, thermal insulation material parameters and a dynamic thermal parameter model of the house; the method comprises the steps of obtaining heat demand information based on user behavior data, weather forecast data and power grid data through a first machine learning model, obtaining a target control strategy based on a heat state prediction result, heat demand information, user behavior data, weather forecast data and power grid data through a second machine learning model, and controlling a heating system based on the target control strategy. Therefore, the building structure data of the house and the heat preservation material parameters of the heating system can be used as the basis of energy-saving control, and the energy-saving level and the intelligent level of the heating system are improved.

Inventors

ZHANG YANYAN
LIN MIAO
XU LEI
CHEN JIAYUAN

Assignees

浙江诗杭电器有限公司

Dates

Publication Date: 20260505
Application Date: 20260126

Claims (10)

1. An energy-saving control method based on artificial intelligence and thermal insulation materials is characterized by comprising the following steps: Obtaining a thermal state prediction result of the house in a future preset time range based on building structure data, indoor and outdoor environment data, heat preservation material parameters of a heating system in the house and a dynamic thermal parameter model, wherein the dynamic thermal parameter model represents a change relation between thermal parameters of the heat preservation material, service time and environmental parameters; Obtaining heat demand information based on user behavior data, weather forecast data and power grid data through a first machine learning model, wherein the heat demand information comprises a time-period temperature setting range; obtaining a target control strategy based on the thermal state prediction result, the thermal demand information, the user behavior data, the weather forecast data and the power grid data through a second machine learning model, wherein the target control strategy comprises a heat source control strategy and a heat insulation material control strategy of the heating system; And controlling the heating system based on the target control strategy.
2. The energy saving control method based on artificial intelligence and thermal insulation material according to claim 1, wherein the obtaining of the prediction result of the thermal state of the house in the future preset time range based on the building structure data, indoor and outdoor environment data, thermal insulation material parameters of the heating system in the house and dynamic thermal parameter model comprises: dividing a house into a plurality of heat exchange areas based on building structure data of the house and heat insulation material parameters of a heating system in the house, taking the heat exchange areas as nodes, determining node characteristics based on the heat insulation material parameters and indoor and outdoor environment data, and obtaining a first graph structure, wherein the first graph structure comprises indoor air nodes, building enclosure nodes, heat source nodes and door and window nodes, and the nodes provided with the heat insulation materials are defined as variable heat resistance heat capacity nodes; And updating the temperature state of each node in the first graph structure based on the indoor environment data through a graph neural network to obtain a second graph structure, updating the thermal parameters of the variable thermal resistance and heat capacity nodes in the second thermal network model based on the dynamic thermal parameter model to obtain a third graph structure, and obtaining a thermal state prediction result of the house in a future preset time range based on the third graph structure.
3. The energy saving control method based on artificial intelligence and thermal insulation material according to claim 2, wherein the indoor environment data comprises an indoor temperature acquired by a temperature sensor, the updating the temperature state of each node in the first graph structure based on the indoor environment data by a graph neural network comprises: Inputting the first graph structure into a first graph neural network for temperature prediction to obtain a first predicted temperature of each node in the first graph structure, and fusing the first predicted temperature with the indoor temperature to obtain a second predicted temperature of each node in the first graph structure; Inputting the first graph structure and the indoor temperature into a second graph neural network to obtain a third predicted temperature of each node in the first graph structure; And updating the temperature state of each node in the first graph structure based on the second predicted temperature and the third predicted temperature.
4. The method of claim 3, wherein updating the temperature state of each node in the first graph structure based on the second predicted temperature and the third predicted temperature comprises: determining temperature weights respectively corresponding to the second predicted temperature and the third predicted temperature based on context features, wherein the context features comprise at least one of data acquisition quality scores, computing resource availability, abnormal condition detection results, time contexts and user preference features of the temperature sensor; and carrying out weighted summation on the second predicted temperature and the third predicted temperature based on the temperature weights respectively corresponding to the second predicted temperature and the third predicted temperature to obtain the temperature of each node in the first graph structure.
5. The method for energy saving control based on artificial intelligence and thermal insulation material according to claim 3, wherein determining the temperature weights corresponding to the second predicted temperature and the third predicted temperature, respectively, based on the context characteristics, comprises: When the data acquisition quality score of the temperature sensor is higher than a preset score threshold, multiplying a preset weight corresponding to the third predicted temperature by a first adjustment factor to obtain a temperature weight corresponding to the third predicted temperature value, wherein the first adjustment factor is greater than 1; And when the residual available computing resource quantity is smaller than a preset resource threshold value, multiplying the preset weight corresponding to the third predicted temperature by a second adjustment factor to obtain a fusion weight corresponding to the third predicted temperature, wherein the second adjustment factor is larger than 1.
6. The energy-saving control method based on artificial intelligence and thermal insulation materials according to any one of claims 1 to 5, wherein the dynamic thermodynamic parameter model is obtained by: Determining sample insulation materials with different use times, and measuring thermal parameters of the same sample insulation material under a plurality of environmental conditions, wherein the environmental conditions comprise temperature conditions and humidity conditions, and the thermal parameters comprise effective thermal resistance and effective heat capacity; Aiming at each sample heat-insulating material, training a third machine learning model by taking the temperature, the humidity and the service time of the sample heat-insulating material as input characteristics and taking the thermal resistance and the heat capacity of the sample heat-insulating material as output targets; and taking the trained second machine learning model as a dynamic thermal parameter model.
7. The energy saving control method based on artificial intelligence and thermal insulation material according to any one of claims 1-5, wherein the user behavior data includes user real-time behavior data, user history behavior data, user schedule data and user preference data, the obtaining heat demand information based on the user behavior data, weather forecast data and grid data through the first machine learning model includes: Predicting short-term heat demands of each room in a future first time range based on user real-time behavior data and time context in the future first time range through a first machine learning model, predicting comfortable temperature demands of each preset period in the future second time range based on weather forecast data, user schedule data and user preference data in the future second time range, predicting long-term heat demands of each room in a future third time range based on user historical behavior data and time context, and predicting comfort energy consumption demands in a future fourth time range based on user historical behavior data, power grid data and the comfortable temperature demands; Determining a user heat demand based on the short-term heat demand and the long-term heat demand; and obtaining heat demand information based on the user heat demand, the comfort temperature demand and the comfort energy consumption demand.
8. The method of claim 7, wherein the short-term heat demand and the long-term heat demand are both demand temperatures, wherein the determining the user heat demand based on the short-term heat demand and the long-term heat demand comprises: mapping the short-term heat demand and the long-term heat demand into a unified space-time grid representation, and determining a first confidence level of the short-term heat demand and a second confidence level of the long-term heat demand; Determining a first fusion weight corresponding to the short-term heat demand based on the first confidence coefficient and a first time distance between the short-term heat demand corresponding period and a current time in the space-time grid representation, and determining a second fusion weight corresponding to the long-term heat demand based on the second confidence coefficient and a second time distance between the long-term heat demand corresponding period and the current time in the space-time grid representation, wherein the fusion weight corresponding to the short-term heat demand is proportional to the first confidence coefficient and inversely proportional to the first time distance, and the fusion weight corresponding to the long-term heat demand is proportional to both the second confidence coefficient and the second time distance; And when the difference value between the short-term heat demand and the long-term heat demand is smaller than a preset difference value threshold, weighting calculation is performed on the short-term heat demand and the long-term heat demand based on the first fusion weight and the second fusion weight, so that the user heat demand is obtained.
9. The energy saving control method based on artificial intelligence and thermal insulation material according to claim 8, further comprising: When the difference between the short-term heat demand and the long-term heat demand is greater than or equal to the preset difference threshold, identifying the health state of the user based on the real-time physiological data of the user, and determining a priority heat demand with higher priority from the short-term heat demand and the long-term heat demand based on the health state; Based on the indoor and outdoor environment parameters, evaluating whether the priority heat demand meets rationality; if the priority heat demand meets rationality, a new heat demand is determined as the user heat demand based on the priority heat demand within the operating constraints of the heating system with the goal of minimizing comfort deviations.
10. The energy-saving control system based on the artificial intelligence and the thermal insulation material is characterized by comprising a data sensing module, a heating system and a controller, wherein the heating system comprises heat source equipment and the thermal insulation material; the data perception module is used for acquiring building structure data, indoor and outdoor environment data, material parameters of heat preservation materials in the heating system, user behavior data, weather forecast data and power grid data; The controller is used for executing the energy-saving control method based on artificial intelligence and thermal insulation materials according to any one of claims 1-9.

Description

Energy-saving control method and system based on artificial intelligence and thermal insulation material Technical Field The disclosure relates to the technical field of energy conservation, in particular to an energy conservation control method and system based on artificial intelligence and thermal insulation materials. Background Along with the improvement of energy saving and emission reduction requirements, the intelligent heating system becomes a research hot spot. The traditional heating control system is mostly based on a simple temperature controller or a timing switch, and factors such as building thermal inertia, building envelope thermal characteristic change and the like are not fully considered, particularly the dynamic thermal performance of the novel heat insulation material is not fully utilized, so that the energy-saving control effect is poor and the energy consumption is high. Disclosure of Invention To overcome the problems in the related art, embodiments of the present disclosure provide an energy-saving control method and system based on artificial intelligence and thermal insulation materials to solve the drawbacks in the related art. According to a first aspect of embodiments of the present disclosure, there is provided an energy saving control method based on artificial intelligence and thermal insulation material, including: Obtaining a thermal state prediction result of the house in a future preset time range based on building structure data, indoor and outdoor environment data, heat preservation material parameters of a heating system in the house and a dynamic thermal parameter model, wherein the dynamic thermal parameter model represents a change relation between thermal parameters of the heat preservation material, service time and environmental parameters; Obtaining heat demand information based on user behavior data, weather forecast data and power grid data through a first machine learning model, wherein the heat demand information comprises a time-period temperature setting range; obtaining a target control strategy based on the thermal state prediction result, the thermal demand information, the user behavior data, the weather forecast data and the power grid data through a second machine learning model, wherein the target control strategy comprises a heat source control strategy and a heat insulation material control strategy of the heating system; And controlling the heating system based on the target control strategy. According to a second aspect of embodiments of the present disclosure, there is provided an energy-saving control system based on artificial intelligence and thermal insulation material, including a data sensing module, a heating system including a heat source device and thermal insulation material, and a controller; the data perception module is used for acquiring building structure data, indoor and outdoor environment data, material parameters of heat preservation materials in the heating system, user behavior data, weather forecast data and power grid data; the controller is used for executing the energy-saving control method based on the artificial intelligence and the thermal insulation material. The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects: According to the energy-saving control method based on the artificial intelligence and the heat preservation material, building structure data of a house and heat preservation material parameters of a heating system can be used as the basis of energy-saving control, future heat demands can be intelligently predicted through a first machine learning model, accurate user heat demand prediction and flexible heating control management can be achieved, and therefore energy-saving level and intelligent level of the heating system are improved. And the thermal state prediction result, the thermal demand information, the user behavior data, the weather forecast data and the power grid data with rich semantic information are deeply associated and inferred through the second machine learning model, so that a control strategy which is more in line with a complex reality scene and the real intention of the user is generated, and the energy saving level and the intelligent level of the heating system are further improved. Drawings The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure. FIG. 1 is a flow chart illustrating an artificial intelligence and insulation based energy conservation control method according to an exemplary embodiment of the present disclosure; FIG. 2 is a block diagram of an artificial intelligence and insulation based energy saving control system according to an exemplary embodiment of the present disclosure. Detailed Description Reference will now be made i