Distributed building heating parameter intelligent optimization method and system

Abstract

The invention discloses a distributed building heating parameter intelligent optimization method and system, and the method comprises the steps: carrying out the multi-scale feature extraction of a heating region through an improved SSD algorithm, building a population distribution dynamic data sequence through a heating time sequence and a population optimization model, collecting heating system parameters, and carrying out the normalization processing, and the data are input into an optimization decision model, an optimization combination scheme is calculated and output through a multi-layer neural network, heating parameters are adjusted in real time according to the optimization combination scheme, and operation data are fed back to an iterative optimization model in a set period. The system comprises a data acquisition unit, a feature extraction unit, a time sequence and population analysis unit, an optimization decision unit, a parameter adjustment unit and a feedback updating unit which work cooperatively. According to the method and system, environment and population dynamic changes can be fully considered, parameter association is deeply excavated, intelligent optimization of heating parameters is achieved, and the heating effect and the energy utilization efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of building heating, and in particular to a method and system for intelligently optimizing decentralized building heating parameters. Background Art

[0002] With the development of the construction industry and the growing demand for energy, decentralized building heating systems are gaining widespread adoption in numerous building scenarios due to their flexibility and applicability. However, traditional decentralized building heating systems face numerous challenges in parameter optimization, making them difficult to meet the current demands for efficient energy conservation and precise control.

[0003] In the existing technology, on the one hand, traditional methods of adjusting heating parameters rely heavily on manual experience or simple preset rules, lacking comprehensive consideration of dynamic factors such as the building environment and population mobility. For example, it is impossible to timely and accurately adjust the operating parameters of heating equipment based on actual conditions such as changes in the number of people in the building during different time periods, as well as fluctuations in indoor and outdoor temperatures, resulting in poor heating effects and serious energy waste. On the other hand, the algorithm models used by traditional methods are relatively simple and lagging, and are unable to fully explore the inherent connections and potential laws between the various parameters of the heating system. When dealing with complex and changing heating scenarios, it is difficult to achieve intelligent optimization of heating parameters, and it is impossible to achieve an ideal balance between heating effects and energy efficiency. Summary of the Invention

[0004] In order to overcome the shortcomings and deficiencies of the prior art, the present invention provides a method and system for intelligent optimization of decentralized building heating parameters.

[0005] The technical solution adopted by the present invention is a method for intelligent optimization of decentralized building heating parameters, comprising the following steps:

[0006] Step S1: Based on the improved SSD algorithm, multi-scale feature extraction is performed on the heating area of ​​the decentralized building to obtain feature data sets of the heating area in different spatial dimensions;

[0007] Step S2: Using the heating time series and population optimization model, combined with historical heating data and historical data on population flow within the building, a correlation mapping relationship between the heating time series and population distribution is established to obtain a dynamic data series of population distribution changing over time;

[0008] Step S3: collecting various parameters of the decentralized building heating system, including power parameters of the heating equipment, heat conductivity parameters of the pipeline, and indoor and outdoor temperature parameters, and normalizing the collected parameters to form a standardized parameter vector;

[0009] Step S4: inputting the characteristic data set, dynamic data sequence and standardized parameter vector into the optimization decision model, and outputting the optimal combination scheme of heating parameters through the multi-layer neural network calculation of the optimization decision model;

[0010] Step S5: adjusting the parameters of the decentralized building heating system in real time according to the optimized combination scheme, and synchronously recording the adjusted heating system operating data;

[0011] Step S6: Feeding back the operating data to the optimization decision model at set time intervals, iteratively updating the optimization decision model, and continuously optimizing the combination of heating parameters.

[0012] Furthermore, the optimization decision model includes a heating parameter optimization formula:

[0013]

[0014] Among them, P opt is the optimized heating parameter combination scheme; α is the weight adjustment coefficient; n is the number of data samples; X i represents the feature data extracted by the improved SSD algorithm for the i-th heating area; f SSD (X i ) is the improved SSD algorithm for feature data X i Processing function of Y i represents the dynamic data of population distribution in the building during the i-th time period; g HTPOM (Y i ) is the heating time series and population optimization model for population dynamic data Y i Processing function of Z i represents the standardized heating parameter vector at the i-th sampling moment; h para (Z i ) is the normalized parameter vector Z i Parameter processing function.

[0015] Furthermore, in step S4, the optimization decision model also includes a dynamic adjustment formula for heating parameters:

[0016]

[0017] Among them, ΔP is the adjustment amount of heating parameters; β is the time sensitivity coefficient; For the optimization solution P opt The rate of change over time; γ pop is the population mobility impact coefficient, reflecting the impact of population distribution changes on heating parameters; δ para It is the comprehensive influence coefficient of heating parameters, reflecting the coupling effect between various heating parameters.

[0018] Furthermore, in step S1, when the improved SSD algorithm extracts features from the heating area, a multi-scale sliding window mechanism is used to calculate the feature response values ​​at different scales using the following formula:

[0019]

[0020] Among them, R scale is the characteristic response value under the preset scale; m is the number of characteristic dimensions; w j is the weight of the j-th feature dimension; The characteristic data X of the heating area is calculated under the preset scale. region The transformation function of .

[0021] Furthermore, in step S2, the heating time sequence and population optimization model constructs a population distribution prediction formula:

[0022]

[0023] in, is the population distribution forecast for the next k time periods; s is the length of historical data selection; θ l is the historical population data Y t-l The weight coefficient of pop is the population distribution prediction error term.

[0024] Furthermore, in step S3, when normalizing the collected heating parameters, the formula is used:

[0025]

[0026] Among them, Z norm is the normalized parameter value; Z is the original parameter value; Z max is the maximum value of the parameter in historical data; Z min The minimum value of this parameter in historical data.

[0027] Furthermore, the step S3 includes the following sub-steps:

[0028] Step S3.1: Use a high-precision sensor array to collect power parameters of the heating equipment in real time. The multi-channel synchronous sampling technology of the sensor ensures the timeliness and integrity of the power parameter collection.

[0029] Step S3.2: Using a thermal conductivity detection device, based on the principle of a heat flow meter, measure the thermal conductivity parameters of the pipeline to obtain thermal conductivity performance data of the pipeline under different environmental conditions;

[0030] Step S3.3: Using temperature sensors placed inside and outside the building, periodically collect indoor and outdoor temperature parameters at a set sampling frequency to form a continuous temperature data sequence;

[0031] Step S3.4: The collected heating equipment power parameters, pipeline heat conductivity coefficient parameters, and indoor and outdoor temperature parameters are processed in a unified data format and converted into a standard data format that meets the system requirements.

[0032] Furthermore, the step S4 includes the following sub-steps:

[0033] Step S4.1: Perform data fusion processing on the feature data set, dynamic data sequence, and standardized parameter vector, and construct a complete input data matrix through feature splicing and time series alignment technology;

[0034] Step S4.2: Input the input data matrix to the input layer of the optimization decision model. The convolutional layer in the model performs feature extraction and dimensionality reduction on the data to enhance the expressiveness of the data features.

[0035] Step S4.3: By optimizing the recurrent neural network layer of the decision model, the temporal characteristics of the data are learned and memorized to capture the temporal changes of the heating parameters;

[0036] Step S4.4: The output layer of the optimization decision model calculates the processed data, outputs the optimized combination plan of heating parameters, and converts the data format to meet the execution requirements of the heating system.

[0037] Furthermore, the step S5 includes the following sub-steps:

[0038] Step S5.1: Generate a corresponding parameter adjustment instruction set based on the optimized combination plan, and clarify the adjustment target value and adjustment sequence of each heating equipment parameter;

[0039] Step S5.2: Sending the parameter adjustment instruction set to the controller of the heating system via the communication module, using an encrypted communication protocol to ensure the security and accuracy of instruction transmission;

[0040] Step S5.3: The heating system controller adjusts the parameters of the heating equipment one by one according to the received instruction set, and monitors the operating status of the equipment in real time during the adjustment process;

[0041] Step S5.4: After the parameter adjustment is completed, the data recording module is started to comprehensively collect and store the adjusted heating system operation data, including equipment operation parameters and indoor and outdoor environmental parameters.

[0042] A decentralized building heating parameter intelligent optimization system, comprising:

[0043] Data acquisition unit, used to collect various parameters of the decentralized building heating system, including heating equipment power parameters, pipeline heat transfer coefficient parameters, and indoor and outdoor temperature parameters;

[0044] a feature extraction unit connected to the data acquisition unit, performing multi-scale feature extraction on the heating area based on an improved SSD algorithm to obtain a feature data set;

[0045] A time series and population analysis unit is connected to the feature extraction unit, and uses a heating time series and population optimization model to establish a correlation mapping relationship between the heating time series and the population distribution, thereby obtaining a dynamic data sequence of the population distribution;

[0046] An optimization decision unit is connected to the feature extraction unit, the time series and population analysis unit, and the data acquisition unit respectively, performs calculations based on the input data, and outputs an optimized combination plan of heating parameters;

[0047] A parameter adjustment unit, connected to the optimization decision unit, adjusts the heating system parameters in real time according to the optimization combination scheme;

[0048] The feedback updating unit is connected to the parameter adjusting unit and the optimization decision unit, and feeds back the adjusted operation data of the heating system to the optimization decision unit to iteratively update the optimization decision model.

[0049] Beneficial effects: The present invention proposes a method and system for intelligent optimization of decentralized building heating parameters. The present invention uses an improved SSD algorithm to extract multi-scale features of the heating area, combines the heating time series with the population optimization model, associates the historical data of population flow in the building with the heating time series, and accurately captures dynamic changes in indoor and outdoor environments, personnel distribution, etc., so that the adjustment of heating parameters is no longer limited to fixed rules, but can be optimized in real time and intelligently according to actual scenarios. In response to the defect of single lag in traditional algorithm models, this system constructs multiple innovative model formulas. The optimization decision model is calculated through a multi-layer neural network, combined with heating parameter optimization formulas, dynamic adjustment formulas, etc., to deeply explore the potential connections between various parameters of the heating system, and achieve efficient processing of complex heating scenarios. At the same time, the system forms a closed-loop mechanism of "data collection-feature extraction-analysis and decision-making-parameter adjustment-feedback update". The collected parameters are normalized and input into the optimization decision-making model. The output optimization combination plan is used to adjust the heating system parameters in real time. The adjusted operating data is fed back to the model for iterative update, continuously improving the heating effect and energy utilization efficiency, ensuring indoor heating comfort, and greatly reducing energy waste, bringing efficient and intelligent solutions to the field of decentralized building heating. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flow chart of the method steps of the present invention;

[0051] Figure 2 It is a diagram of the system unit composition of the present invention. DETAILED DESCRIPTION

[0052] It should be noted that, unless there is a conflict, the embodiments in this application and the features described in the embodiments can be combined with each other. The application is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0053] like Figure 1 As shown, a method for intelligent optimization of decentralized building heating parameters includes the following steps:

[0054] Step S1: Based on the improved SSD algorithm, multi-scale feature extraction is performed on the heating area of ​​the decentralized building to obtain feature data sets of the heating area in different spatial dimensions;

[0055] Specifically, this step implements multi-scale feature extraction operations for the heating areas of decentralized buildings by using the improved SSD (Single Shot Detector) algorithm. During the implementation process, the algorithm scans and analyzes the heating area from different spatial dimensions based on a variety of pre-set scale specifications. For example, from tiny room corners to the entire floor space, or even the heating area of ​​the entire building, the algorithm can traverse with windows of different scales, thereby capturing characteristic information such as the environment and structure at each spatial level. These characteristic information covers spatial parameters related to heating, such as the layout and shape of the room, the thermal insulation performance of the walls, the orientation and airtightness of doors and windows. Through such comprehensive and detailed multi-scale scanning, a heating area feature data set containing rich spatial dimension features is finally obtained, providing important basic data support for the subsequent optimization of heating parameters.

[0056] Multi-scale feature extraction fully accounts for the complex and variable spatial characteristics of decentralized building heating areas. Feature data extracted at different scales can reflect different levels of heating influencing factors. Large-scale features help grasp the overall heating layout and environment, while small-scale features can accurately locate specific needs and potential problems in local areas. This comprehensive feature data set enables subsequent optimization decisions to be based on more accurate and complete information, avoiding optimization bias caused by only considering features at a single scale. This lays a solid foundation for more efficient and precise heating parameter optimization.

[0057] Step S2: Using the heating time series and population optimization model, combined with historical heating data and historical data on population flow within the building, a correlation mapping relationship between the heating time series and population distribution is established to obtain a dynamic data series of population distribution changing over time;

[0058] Specifically, this step uses the heating time series and population optimization model to conduct in-depth mining and analysis of historical heating data and historical data on population flow within the building. During implementation, the model will subdivide the time dimension and extract and integrate the heating data and population flow data at each time node at specific time intervals (such as every hour, every half hour, etc.). Historical heating data contains information such as the operating parameters of heating equipment and changes in indoor and outdoor temperatures during different time periods; historical population flow data records data such as the entry and exit time, length of stay, and number of gatherings of people in various areas of the building. By analyzing and processing these massive amounts of historical data, the model can discover the inherent connection between heating demand and population distribution, and then establish a correlation mapping relationship between the two. Based on this mapping relationship, the model can predict the dynamic changes in population distribution in various areas of the building at different time points in the future, and ultimately generate a dynamic data sequence of population distribution changes over time.

[0059] Population distribution is one of the key factors affecting heating demand. The activity patterns and gathering areas of people in a building will change over time, and the corresponding heating demand will also change accordingly. By establishing a correlation mapping relationship between heating time series and population distribution, we can accurately grasp the impact of population dynamics on heating demand, so that the heating system no longer operates blindly. Instead, we can plan and adjust heating parameters in advance based on the dynamic data series of population distribution, provide sufficient heat supply in areas and time periods where people gather, and reasonably reduce heating intensity in areas and time periods where people are sparsely populated, so as to achieve on-demand heating, improve the relevance and effectiveness of heating, and also help reduce energy consumption and improve energy efficiency.

[0060] Step S3: collecting various parameters of the decentralized building heating system, including power parameters of the heating equipment, heat conductivity parameters of the pipeline, and indoor and outdoor temperature parameters, and normalizing the collected parameters to form a standardized parameter vector;

[0061] Specifically, in this step, various specialized sensor devices are first used to collect key parameters of the decentralized building heating system in real time. For heating equipment power parameters, high-precision power sensors are installed at key circuit nodes to monitor power consumption during operation. For pipeline thermal conductivity parameters, heat flow meter-based detection devices are deployed at various locations along the pipeline to measure the thermal conductivity of the pipeline under varying ambient temperatures and fluid conditions. Indoor and outdoor temperature parameters are periodically collected at a set sampling frequency (e.g., once per minute) using temperature sensors distributed throughout the building. After these parameters are collected, they differ in numerical range and dimension, requiring normalization to facilitate subsequent data processing and analysis. Normalization maps all parameter values ​​to a unified numerical interval (typically [0, 1] or [-1, 1]), eliminating differences in dimension and magnitude. This ultimately creates a standardized parameter vector, making different parameter types comparable and amenable to integration.

[0062] The operating status of a decentralized building heating system is determined by numerous different types of parameters. Only by comprehensively and accurately collecting these parameters and applying appropriate processing can the system's actual operating status be truly reflected. Normalization allows all parameters to be analyzed and calculated under the same standard, avoiding calculation errors and decision-making errors caused by significant parameter differences. The standardized parameter vector serves as important input data for subsequent optimization decision-making models. Its accuracy and standardization directly impact the quality and reliability of the optimization solution, providing effective data support for precise heating parameter optimization.

[0063] Step S4: inputting the characteristic data set, dynamic data sequence and standardized parameter vector into the optimization decision model, and outputting the optimal combination scheme of heating parameters through the multi-layer neural network calculation of the optimization decision model;

[0064] Specifically, this step uses the feature data set, population distribution dynamics data series, and standardized parameter vectors obtained in the previous three steps as input data for the optimization decision model. The optimization decision model is constructed based on a multi-layer neural network architecture consisting of an input layer, multiple hidden layers, and an output layer. Once data is input to the model's input layer, it is processed sequentially through each hidden layer. Within the hidden layers, neurons calculate and transform the input data using specific activation functions, continuously extracting key features and inherent patterns within the data, thereby achieving feature extraction, dimensionality reduction, and information fusion. As data is passed through and processed layer by layer in the multi-layer neural network, the model gradually learns and understands the complex relationships between the spatial characteristics of the heating area, population dynamics, and heating system parameters. Finally, after calculations in the output layer, the model, based on the learned knowledge and patterns, outputs an optimized combination of heating parameters for the current heating conditions. This combination specifies optimized values ​​for specific parameters such as the operating power of the heating equipment, flow control in the pipelines, and temperature settings.

[0065] Through comprehensive analysis and in-depth processing of multi-source data, the optimization decision-making model can overcome the limitations and one-sidedness of traditional methods for adjusting heating parameters. The powerful learning and computing capabilities of multi-layer neural networks enable them to uncover complex hidden connections between data, fully considering the impact of multiple factors such as spatial environment, population changes, and system parameters on heating effectiveness. The output optimization combination solution is based on comprehensive and accurate data analysis. Compared with traditional empirical or simple rule-based parameter adjustment methods, it can optimize heating parameters more scientifically and rationally, effectively improving the operating efficiency and heating quality of the heating system, and achieving the dual goals of energy conservation and comfort.

[0066] Step S5: adjusting the parameters of the decentralized building heating system in real time according to the optimized combination scheme, and synchronously recording the adjusted heating system operating data;

[0067] Specifically, after obtaining the optimal heating parameter combination output by the optimization decision model, this step immediately performs real-time adjustments to the parameters of the decentralized building heating system. In practice, the communication module converts the optimized combination into corresponding control instructions, which are transmitted via an encrypted communication protocol to the various controllers in the heating system. These controllers are responsible for controlling different heating equipment and components, such as heating boilers, circulating water pumps, and valves. Upon receiving the instructions, the controllers adjust the operating parameters of the heating equipment one by one, such as adjusting the combustion power of the heating boiler, changing the speed of the circulating water pump to control pipeline flow, and adjusting the valve opening to adjust heat distribution. While adjusting the parameters, the system activates the data logging module, utilizing various sensors and data acquisition devices to collect comprehensive, real-time operating data from the adjusted heating system. The collected data includes the actual operating parameters of the heating equipment (such as power, temperature, and flow), indoor and outdoor environmental parameters (such as temperature, humidity, and wind speed), and the system's energy consumption data. This data is stored to form a complete operational data record.

[0068] Translating the theoretical optimization solution output by the optimization decision-making model into actual heating system operation control realizes a significant transition from data analysis to actual operation. Real-time adjustments ensure that the heating system responds promptly to changes in the environment and demand, quickly achieving an optimized operating state and improving heating effectiveness. Simultaneously recording the adjusted operating data provides a reliable basis for subsequent optimization and evaluation of the system. By analyzing this operating data, we can understand the actual implementation effect of the optimization plan, identify potential problems and deficiencies, and provide data support for further improvement and optimization of heating parameters, forming a continuously optimized closed-loop management model to ensure that the heating system is always in an efficient and stable operating state.

[0069] Step S6: Feeding back the operating data to the optimization decision model at set time intervals, iteratively updating the optimization decision model, and continuously optimizing the combination of heating parameters.

[0070] Specifically, this step feeds back the heating system operation data recorded in step S5 to the optimization decision model according to a pre-set fixed time period (such as every hour, every day, etc.). The operation data contains various real information of the heating system during the actual operation process, reflecting the effect and existing problems of the current optimization scheme in actual application. After the operation data is input into the optimization decision model, the model adjusts and optimizes its own parameters and structure based on these new data, that is, it performs iterative updates. During the iterative process, the model will re-learn and analyze the characteristics and rules in the data, compare the previous learning results, and discover new changes and new trends in the data, thereby adjusting the neuron connection weights, activation function parameters, etc. within the model, so that the model can better adapt to the ever-changing heating environment and needs. After the iterative update, the optimization decision model can output a more accurate and optimized heating parameter combination plan when it receives new input data in the future, thereby achieving continuous optimization of the heating parameters and continuously improving the operating performance and energy efficiency of the heating system.

[0071] The heating environment in decentralized buildings is dynamic, influenced by shifts in occupant activity patterns, fluctuating weather conditions, and declining equipment performance. Regularly feeding operational data back into the optimization decision-making model for iterative updates ensures the model remains adaptable and sensitive to current conditions. This prevents optimization failures caused by model lags and ensures that the heating system can adjust heating parameters promptly based on actual needs in a variety of complex and changing environments, achieving efficient, energy-efficient, and comfortable heating. This continuous optimization mechanism provides a strong guarantee for the long-term stable operation and performance improvement of decentralized building heating systems.

[0072] Preferably, the optimization decision model includes a heating parameter optimization formula:

[0073]

[0074] Among them, P opt is the optimized heating parameter combination scheme; α is the weight adjustment coefficient; n is the number of data samples; X i represents the feature data extracted by the improved SSD algorithm for the i-th heating area; f SSD (X i ) is the improved SSD algorithm for feature data X i Processing function of Y i represents the dynamic data of population distribution in the building during the i-th time period; g HTPOM (Y i ) is the heating time series and population optimization model for population dynamic data Y i Processing function of Z i represents the standardized heating parameter vector at the i-th sampling moment; h para (Zi ) is the normalized parameter vector Z i Parameter processing function.

[0075] Specifically, the heating parameter optimization formula in the optimization decision model is used to generate an optimized heating parameter combination scheme by comprehensively considering multiple factors. In terms of implementation, a weighted summation operation is performed on the heating area characteristic data processed by the improved SSD algorithm, the heating time series and population dynamics data output by the population optimization model, and the standardized heating parameter vector. Among them, the weight adjustment coefficient is set according to actual needs and is used to balance the influence of different data; the number of data samples determines the amount of data involved in the calculation. Its significance lies in the close combination of spatial characteristics, population changes and system parameters, and the deriving of a scientific and reasonable combination of heating parameters through quantitative calculation, so that the operating parameters of the heating system can accurately match the actual needs, avoiding energy waste and poor heating effects.

[0076] Preferably, in step S4, the optimization decision model further includes a dynamic adjustment formula for heating parameters:

[0077]

[0078] Among them, ΔP is the adjustment amount of heating parameters; β is the time sensitivity coefficient; For the optimization solution P opt The rate of change over time; γ pop is the population mobility impact coefficient, reflecting the impact of population distribution changes on heating parameters; δ para It is the comprehensive influence coefficient of heating parameters, reflecting the coupling effect between various heating parameters.

[0079] Specifically, the dynamic adjustment formula for heating parameters is used to determine the real-time adjustment amount of heating parameters. During implementation, the heating parameters are dynamically adjusted based on the time-sensitive coefficient, the rate of change of the optimization scheme over time, the population flow impact coefficient, and the comprehensive impact coefficient of the heating parameters. The time-sensitive coefficient reflects the degree of response of the system to time changes, the rate of change of the optimization scheme reflects the dynamic trend of heating demand, the population flow impact coefficient highlights the impact of changes in personnel distribution on heating, and the comprehensive parameter impact coefficient considers the coupling relationship between various heating parameters. Its significance lies in enabling the heating system to adjust the heating parameters in real time and accurately according to the passage of time, population flow, and the interaction between parameters, thereby improving the dynamic adaptability and energy efficiency of the heating system.

[0080] Preferably, in step S1, when the improved SSD algorithm extracts features from the heating area, a multi-scale sliding window mechanism is used to calculate the feature response values ​​at different scales using the following formula:

[0081]

[0082] Among them, R scale is the characteristic response value under the preset scale; m is the number of characteristic dimensions; w j is the weight of the j-th feature dimension; The characteristic data X of the heating area is calculated under the preset scale. region The transformation function of .

[0083] Specifically, the improved SSD algorithm feature extraction process in step S1 uses a multi-scale sliding window mechanism to calculate the feature response value. During implementation, the characteristic data of the heating area at different scales is transformed and calculated based on the weights of each feature dimension. The number of feature dimensions covers a variety of heating-related characteristic factors such as spatial structure and building materials. The weights are set according to the importance of each feature to the heating effect, and the transformation function realizes the conversion processing of the feature data. This mechanism can comprehensively capture the characteristic information of the heating area at different scales, providing rich and accurate basic data for the subsequent optimization of heating parameters, ensuring that the optimization decision can fully consider the impact of spatial factors on heating.

[0084] Preferably, in step S2, the heating timing and population optimization model constructs a population distribution prediction formula:

[0085]

[0086] in, is the population distribution forecast for the next k time periods; s is the length of historical data selection; θ l is the historical population data Y t-l The weight coefficient of pop is the population distribution prediction error term.

[0087] Specifically, the population distribution prediction formula of the heating time series and population optimization model in step S2 predicts future population distribution using historical population data. During implementation, a certain length of historical population data is selected, weighted and summed according to the corresponding weight coefficients for each historical data point, and a prediction error term is added to obtain the predicted value of the future population distribution. The length of the selected historical data determines the time span of the reference data, the weight coefficient reflects the degree of influence of data at different historical moments on the prediction results, and the error term is used to correct the prediction deviation. This formula can predict population dynamics based on historical patterns, allowing heating systems to be planned in advance, adjusting heating parameters according to population distribution trends, achieving on-demand heating, and improving heating accuracy and energy efficiency.

[0088] Preferably, in step S3, when normalizing the collected heating parameters, the formula is used:

[0089]

[0090] Among them, Z norm is the normalized parameter value; Z is the original parameter value; Z max is the maximum value of the parameter in historical data; Z min The minimum value of this parameter in historical data.

[0091] Specifically, the heating parameter normalization processing formula in step S3 is used to convert the collected original heating parameters into data of a unified standard. During implementation, the original parameters are linearly transformed according to the maximum and minimum values ​​of each parameter in the historical data and mapped to a specific interval. The normalized parameters eliminate the differences in dimension and numerical size, which facilitates subsequent data processing and analysis. This process ensures that heating parameters of different types and magnitudes are comparable and fusible, provides a guarantee for the optimization decision model to accurately process data and output reliable optimization solutions, and improves the overall data processing efficiency and optimization effect of the system.

[0092] Preferably, the step S3 includes the following sub-steps:

[0093] Step S3.1: Use a high-precision sensor array to collect power parameters of the heating equipment in real time. The multi-channel synchronous sampling technology of the sensor ensures the timeliness and integrity of the power parameter collection.

[0094] Step S3.2: Using a thermal conductivity detection device, based on the principle of a heat flow meter, measure the thermal conductivity parameters of the pipeline to obtain thermal conductivity performance data of the pipeline under different environmental conditions;

[0095] Step S3.3: Using temperature sensors placed inside and outside the building, periodically collect indoor and outdoor temperature parameters at a set sampling frequency to form a continuous temperature data sequence;

[0096] Step S3.4: The collected heating equipment power parameters, pipeline heat conductivity coefficient parameters, and indoor and outdoor temperature parameters are processed in a unified data format and converted into a standard data format that meets the system requirements.

[0097] Specifically, first, a high-precision sensor array combined with multi-channel synchronous sampling technology is used to collect heating equipment power parameters to ensure real-time and complete data. Second, a detection device based on the principle of a heat flow meter measures the thermal conductivity parameters of the pipeline to obtain performance data under different environments. Then, temperature sensors placed inside and outside the building collect indoor and outdoor temperature parameters at a set frequency to form a continuous data sequence. Finally, all collected parameters are formatted in a unified manner to meet system requirements. These steps comprehensively and accurately collect and process heating system parameters, providing an accurate and standardized data foundation for subsequent optimization decisions.

[0098] Preferably, the step S4 includes the following sub-steps:

[0099] Step S4.1: Perform data fusion processing on the feature data set, dynamic data sequence, and standardized parameter vector, and construct a complete input data matrix through feature splicing and time series alignment technology;

[0100] Step S4.2: Input the input data matrix to the input layer of the optimization decision model. The convolutional layer in the model performs feature extraction and dimensionality reduction on the data to enhance the expressiveness of the data features.

[0101] Step S4.3: By optimizing the recurrent neural network layer of the decision model, the temporal characteristics of the data are learned and memorized to capture the temporal changes of the heating parameters;

[0102] Step S4.4: The output layer of the optimization decision model calculates the processed data, outputs the optimized combination plan of heating parameters, and converts the data format to meet the execution requirements of the heating system.

[0103] Specifically, the feature data set, dynamic data sequence, and standardized parameter vector are first fused, and a complete input matrix is ​​constructed through feature concatenation and time series alignment. This matrix is ​​then input into the optimization decision model, where it is processed through a convolutional layer for feature extraction and dimensionality reduction, enhancing the data representation. A recurrent neural network layer then learns the temporal characteristics of the data to capture the patterns of heating parameter changes. Finally, the output layer calculates and outputs the optimized combination solution and converts the data format. These steps work together to enable the optimization decision model to fully process multi-source data, deeply explore its value, and output a scientific and reasonable heating parameter optimization solution.

[0104] Preferably, the step S5 includes the following sub-steps:

[0105] Step S5.1: Generate a corresponding parameter adjustment instruction set based on the optimized combination plan, and clarify the adjustment target value and adjustment sequence of each heating equipment parameter;

[0106] Step S5.2: Sending the parameter adjustment instruction set to the controller of the heating system via the communication module, using an encrypted communication protocol to ensure the security and accuracy of instruction transmission;

[0107] Step S5.3: The heating system controller adjusts the parameters of the heating equipment one by one according to the received instruction set, and monitors the operating status of the equipment in real time during the adjustment process;

[0108] Step S5.4: After the parameter adjustment is completed, the data recording module is started to comprehensively collect and store the adjusted heating system operation data, including equipment operation parameters and indoor and outdoor environmental parameters.

[0109] Specifically, a parameter adjustment instruction set is first generated based on the optimized combination plan, clarifying the parameter adjustment targets and sequence for each device. This instruction set is then sent to the heating system controller via a communication module using an encrypted protocol to ensure secure and accurate transmission. The controller then adjusts the heating equipment parameter by parameter according to the instructions and monitors the equipment status in real time. Finally, after the adjustments are complete, the data logging module is activated to collect and store system operating data. This process ensures that the optimization plan can be accurately and securely implemented in the heating system, providing data support for subsequent system evaluation and optimization, achieving dynamic optimization and efficient operation of the heating system.

[0110] like Figure 2 As shown, a decentralized building heating parameter intelligent optimization system includes:

[0111] Data acquisition unit, used to collect various parameters of the decentralized building heating system, including heating equipment power parameters, pipeline heat transfer coefficient parameters, and indoor and outdoor temperature parameters;

[0112] a feature extraction unit connected to the data acquisition unit, performing multi-scale feature extraction on the heating area based on an improved SSD algorithm to obtain a feature data set;

[0113] A time series and population analysis unit is connected to the feature extraction unit, and uses a heating time series and population optimization model to establish a correlation mapping relationship between the heating time series and the population distribution, thereby obtaining a dynamic data sequence of the population distribution;

[0114] An optimization decision unit is connected to the feature extraction unit, the time series and population analysis unit, and the data acquisition unit respectively, performs calculations based on the input data, and outputs an optimized combination plan of heating parameters;

[0115] A parameter adjustment unit, connected to the optimization decision unit, adjusts the heating system parameters in real time according to the optimization combination scheme;

[0116] The feedback updating unit is connected to the parameter adjusting unit and the optimization decision unit, and feeds back the adjusted operation data of the heating system to the optimization decision unit to iteratively update the optimization decision model.

[0117] The intelligent optimization method and system for decentralized building heating parameters uses an improved SSD algorithm to extract multi-scale features from the heating area, capturing environmental information across different spatial dimensions. Simultaneously, a heating time series and population optimization model is employed to deeply correlate historical heating data with population mobility data, establishing a precise time series-population distribution mapping. This data-driven analysis model enables the system to perceive real-time fluctuations in indoor and outdoor temperatures, as well as changes in the gathering or evacuation of people. This provides a comprehensive and dynamic basis for parameter optimization, completely eliminating reliance on empirical rules.

[0118] At the algorithm model level, traditional technologies are unable to tap into the potential connections between parameters due to their single and lagging models, resulting in inefficient heating control. The optimization decision-making model constructed by this system integrates a multi-layer neural network and innovatively introduces multiple formulas. The heating parameter optimization formula comprehensively considers the characteristic data processed by the improved SSD algorithm, the dynamic data output by the heating time series and population optimization model, and the standardized heating parameter vector, and outputs an accurate parameter combination plan through weighted calculation; the dynamic adjustment formula combines the time rate of change, the population mobility influence coefficient and the parameter coupling relationship to achieve real-time dynamic adjustment of the parameters. These formulas work together to enable the system to deeply analyze the complex characteristics of the heating system, accurately grasp the inherent logic between the parameters, and greatly improve the scientificity and effectiveness of optimization decisions.

[0119] The system further enhances its advantages through a closed-loop operation mechanism. The data acquisition unit accurately captures parameters such as heating equipment power and pipeline thermal conductivity, normalizing them before inputting them into the optimization decision-making unit. The parameter adjustment unit then controls the heating system in real time based on the output optimization solution and feeds the adjusted operating data back to the optimization decision-making unit for iterative updates. This continuous optimization model not only ensures the stability and comfort of heating effects but also significantly improves energy efficiency, effectively avoiding the energy waste caused by the extensive parameter adjustments of traditional technologies. It provides an efficient, intelligent, and innovative solution for decentralized building heating.

[0120] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," "connected," and "fixed" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0121] While embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent optimization of decentralized building heating parameters, characterized in that: The steps include: Step S1: Based on the improved SSD algorithm, multi-scale feature extraction is performed on the heating area of ​​the decentralized building to obtain feature data sets of the heating area in different spatial dimensions; Step S2: Using the heating time series and population optimization model, combined with historical heating data and historical data on population flow within the building, a correlation mapping relationship between the heating time series and population distribution is established to obtain a dynamic data series of population distribution changing over time; Step S3: collecting various parameters of the decentralized building heating system, including power parameters of the heating equipment, heat conductivity parameters of the pipeline, and indoor and outdoor temperature parameters, and normalizing the collected parameters to form a standardized parameter vector; Step S4: inputting the characteristic data set, dynamic data sequence and standardized parameter vector into the optimization decision model, and outputting the optimal combination scheme of heating parameters through the multi-layer neural network calculation of the optimization decision model; Step S5: adjusting the parameters of the decentralized building heating system in real time according to the optimized combination scheme, and synchronously recording the adjusted heating system operating data; Step S6: Feeding back the operating data to the optimization decision model at set time intervals, iteratively updating the optimization decision model, and continuously optimizing the combination of heating parameters.

2. The method for intelligent optimization of decentralized building heating parameters according to claim 1, characterized in that: The optimization decision model includes the heating parameter optimization formula: Among them, P opt is the optimized heating parameter combination scheme; α is the weight adjustment coefficient; n is the number of data samples; X i represents the feature data extracted by the improved SSD algorithm for the i-th heating area; f SSD (X i ) is the improved SSD algorithm for feature data X i Processing function of Y i represents the dynamic data of population distribution in the building during the i-th time period; g HTPOM (Y i ) is the heating time series and population optimization model for population dynamic data Y i Processing function of Z i represents the standardized heating parameter vector at the i-th sampling moment; h para (Z i ) is the normalized parameter vector Z i Parameter processing function.

3. The method for intelligent optimization of decentralized building heating parameters according to claim 1, characterized in that: In step S4, the optimization decision model also includes a dynamic adjustment formula for heating parameters: Among them, ΔP is the adjustment amount of heating parameters; β is the time sensitivity coefficient; For the optimization solution P opt The rate of change over time; γ pop is the population mobility impact coefficient, reflecting the impact of population distribution changes on heating parameters; δ para It is the comprehensive influence coefficient of heating parameters, reflecting the coupling effect between various heating parameters.

4. The method for intelligent optimization of decentralized building heating parameters according to claim 1, characterized in that: In step S1, when the improved SSD algorithm extracts features from the heating area, a multi-scale sliding window mechanism is used to calculate the feature response values ​​at different scales using the following formula: Among them, R scale is the characteristic response value under the preset scale; m is the number of characteristic dimensions; w j is the weight of the j-th feature dimension; The characteristic data X of the heating area is calculated under the preset scale. region The transformation function of .

5. The method for intelligent optimization of decentralized building heating parameters according to claim 1, characterized in that: In step S2, the heating time sequence and population optimization model constructs a population distribution prediction formula: in, is the population distribution forecast for the next k time periods; s is the length of historical data selection; θ l is the historical population data Y t-l The weight coefficient of pop is the population distribution prediction error term.

6. The method for intelligent optimization of decentralized building heating parameters according to claim 1, characterized in that: In step S3, the collected heating parameters are normalized using the formula: Among them, Z norm is the normalized parameter value; Z is the original parameter value; Z max is the maximum value of the parameter in historical data; Z min The minimum value of this parameter in historical data.

7. The method for intelligent optimization of decentralized building heating parameters according to claim 1, characterized in that: The step S3 includes the following sub-steps: Step S3.1: using a high-precision sensor array to collect power parameters of the heating equipment in real time; Step S3.2: Using a thermal conductivity detection device, based on the principle of a heat flow meter, measure the thermal conductivity parameters of the pipeline to obtain thermal conductivity performance data of the pipeline under different environmental conditions; Step S3.3: Using temperature sensors placed inside and outside the building, periodically collect indoor and outdoor temperature parameters at a set sampling frequency to form a continuous temperature data sequence; Step S3.4: The collected heating equipment power parameters, pipeline heat conductivity coefficient parameters, and indoor and outdoor temperature parameters are processed in a unified data format and converted into a standard data format that meets the system requirements.

8. The method for intelligent optimization of decentralized building heating parameters according to claim 1, characterized in that: The step S4 includes the following sub-steps: Step S4.1: Perform data fusion processing on the feature data set, dynamic data sequence, and standardized parameter vector, and construct a complete input data matrix through feature splicing and time series alignment technology; Step S4.2: Input the input data matrix to the input layer of the optimization decision model. The convolutional layer in the model performs feature extraction and dimensionality reduction on the data to enhance the expressiveness of the data features. Step S4.3: By optimizing the recurrent neural network layer of the decision model, the temporal characteristics of the data are learned and memorized to capture the temporal changes of the heating parameters; Step S4.4: The output layer of the optimization decision model calculates the processed data, outputs the optimized combination plan of heating parameters, and converts the data format to meet the execution requirements of the heating system.

9. The method for intelligent optimization of decentralized building heating parameters according to claim 1, characterized in that: The step S5 includes the following sub-steps: Step S5.1: Generate a corresponding parameter adjustment instruction set based on the optimized combination plan, and clarify the adjustment target value and adjustment sequence of each heating equipment parameter; Step S5.2: sending the parameter adjustment instruction set to the controller of the heating system through the communication module; Step S5.3: The heating system controller adjusts the parameters of the heating equipment one by one according to the received instruction set, and monitors the operating status of the equipment in real time during the adjustment process; Step S5.4: After the parameter adjustment is completed, the data recording module is started to comprehensively collect and store the adjusted heating system operation data, including equipment operation parameters and indoor and outdoor environmental parameters.

10. A decentralized building heating parameter intelligent optimization system, characterized in that: include: Data acquisition unit, used to collect various parameters of the decentralized building heating system, including heating equipment power parameters, pipeline heat transfer coefficient parameters, and indoor and outdoor temperature parameters; a feature extraction unit connected to the data acquisition unit, performing multi-scale feature extraction on the heating area based on an improved SSD algorithm to obtain a feature data set; A time series and population analysis unit is connected to the feature extraction unit, and uses a heating time series and population optimization model to establish a correlation mapping relationship between the heating time series and the population distribution, thereby obtaining a dynamic data sequence of the population distribution; An optimization decision unit is connected to the feature extraction unit, the time series and population analysis unit, and the data acquisition unit respectively, performs calculations based on the input data, and outputs an optimized combination plan of heating parameters; A parameter adjustment unit, connected to the optimization decision unit, adjusts the heating system parameters in real time according to the optimization combination scheme; The feedback updating unit is connected to the parameter adjusting unit and the optimization decision unit, and feeds back the adjusted operation data of the heating system to the optimization decision unit to iteratively update the optimization decision model.

Images