An intelligent temperature-limited heating system coupled with carbon fiber and heating pipe network

By adopting carbon fiber sensing technology and AI prediction modules and other technologies in the intelligent temperature limit heating system, the shortcomings in the existing system in temperature monitoring, prediction and heating strategy formulation are solved, and high-precision, uniform and personalized supply is achieved Thermal effect improves the health monitoring of the system and user comfort.

CN117706934BActive Publication Date: 2024-12-03HEBEI JIANYAN ENERGY SAVING EQUIP CO LTD +4
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311763487.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-20
Publication Date
2024-12-03
Estimated Expiration
2043-12-20

AI Technical Summary

Technical Problem

The existing intelligent temperature-limited heating system has shortcomings in temperature monitoring, heating demand forecast, heating strategy formulation, heating uniformity and system health monitoring, resulting in inaccurate data, inaccurate prediction, user comfort and energy consumption Balance is difficult to achieve and lacks real-time and in-depth data mining capabilities.

Method used

Coupled with the heating pipeline network using carbon fiber sensing technology, combined with AI prediction module, optimization control module, adaptive strategy module, regional dynamic regulation module, pipeline network health monitoring module, energy consumption behavior analysis module and nonlinear configuration module, LSTM Deep learning, Pareto optimization, fuzzy logic control, acoustic emission technology and association rule learning and other technologies to achieve high-precision temperature monitoring, accurate prediction, uniform heating and personalized services.

Benefits of technology

Improve the accuracy and prediction accuracy of temperature data, achieve the best balance of comfort, energy consumption and environmental benefits, ensure uniformity of heating and systematic health monitoring, and provide in-depth energy-using behavior analysis and personalized services. .

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117706934B_ABST
    Figure CN117706934B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of automation technology, specifically to an intelligent temperature-limited heating system coupled with a carbon fiber and a heating network, which is composed of a sensor data acquisition module, an AI prediction module, an optimization control module, an adaptive strategy module, a regional dynamic regulation module, a network health monitoring module, an energy behavior analysis module, and a nonlinear configuration module. In the present invention, high-precision temperature monitoring is achieved through carbon fiber sensing technology, which improves the accuracy of temperature data, thereby providing a reliable data basis for subsequent analysis and optimization. The use of an LSTM deep learning network can more accurately predict future heating demand, and a multi-objective Pareto optimization strategy enables the system to achieve the best balance between comfort, energy consumption and environmental benefits. The fuzzy logic controller ensures the uniformity of heating, and the acoustic emission technology and association rule learning realize intelligent fault warning and deep mining of energy behavior.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of automation technology, and in particular to an intelligent temperature-limited heating system in which carbon fibers are coupled to a heating pipe network. Background Art

[0002] Automation technology is a field that uses electronics, computers, information technology and other means to conduct intelligent and automated management of system control, monitoring and operation. Among them, the intelligent temperature-limited heating system is a heating system that applies automation technology. It uses sensors to sense changes in indoor and outdoor temperatures, and uses intelligent algorithms and control strategies to adjust the operation of heating equipment in real time to achieve a stable and energy-saving heating effect. The purpose of this system is to achieve precise temperature control, ensure that the indoor temperature is stable within the set temperature limit range, and improve the comfort and energy efficiency of heating. Through automation technology and intelligent control methods, the system can automatically adjust the working state of the heating equipment according to factors such as indoor and outdoor temperature changes, actual indoor heat load and user needs, so as to achieve precise temperature control and effective use of energy.

[0003] There are many shortcomings in the existing intelligent temperature-limited heating system. First, in terms of temperature monitoring, traditional sensors may not be able to provide such high accuracy and response speed, resulting in data delays and inaccuracies. Secondly, the existing systems often use simple statistical models to predict heating demand, which often cannot take into account the complex interactions of multiple factors, thus affecting the accuracy of the prediction. In the formulation of heating strategies, most existing systems lack the idea of ​​comprehensive optimization and may be overly biased towards one aspect, such as excessive pursuit of energy consumption reduction at the expense of user comfort. In addition, for the uniformity of heating and system health monitoring, traditional methods often lack real-time and intelligence, and cannot respond to various emergencies in a timely manner, increasing the difficulty and cost of operation and maintenance. Finally, in terms of energy consumption behavior analysis, the existing systems mostly stay on the surface and lack in-depth data mining capabilities, thus missing the opportunity to provide users with more personalized services. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent temperature-limited heating system in which carbon fibers are coupled to a heating pipe network.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an intelligent temperature-limited heating system coupled with carbon fiber and heating pipe network is composed of a sensor data acquisition module, an AI prediction module, an optimization control module, an adaptive strategy module, a regional dynamic control module, a pipe network health monitoring module, an energy consumption behavior analysis module, and a nonlinear configuration module;

[0006] The sensor data acquisition module uses carbon fiber sensor technology and time domain reflectometry to monitor the temperature distribution and changes in the heating network in real time and generate real-time temperature data;

[0007] The AI ​​prediction module uses LSTM deep learning network to analyze historical temperature distribution based on real-time temperature data and generate predicted heating demand;

[0008] The optimization control module generates an optimized heating strategy by using a multi-objective optimization algorithm specifically a Pareto optimization based on the predicted heating demand, taking into account comfort, energy consumption and environmental benefits;

[0009] The adaptive strategy module dynamically adjusts the heating temperature and strategy based on the optimized heating strategy, combined with external environmental factors and real-time temperature data, and generates adaptive adjustment instructions;

[0010] The regional dynamic control module divides the heating area based on the adaptive adjustment instructions, and uses the fuzzy logic controller to make fine adjustments to ensure the temperature balance of each area and generate a regional heating adjustment strategy;

[0011] The pipeline network health monitoring module uses real-time temperature data and acoustic emission technology to analyze the pipeline network status, detect potential faults, and generate a pipeline network health report;

[0012] The energy consumption behavior analysis module combines the predicted heating demand and the user's historical data, adopts association rule learning to analyze the user's energy consumption behavior, and generates a user energy consumption behavior report;

[0013] The nonlinear configuration module uses a nonlinear optimization method, specifically a particle swarm optimization, based on the user energy consumption behavior report to fine-tune system parameters and generate a final heating plan.

[0014] As a further solution of the present invention: the sensor data acquisition module includes a data preprocessing submodule, a temperature monitoring submodule, and a sensor calibration submodule;

[0015] The AI ​​prediction module includes a data normalization submodule, a model training submodule, and a model verification submodule;

[0016] The optimization control module includes an energy consumption assessment submodule, a comfort simulation submodule, and an environmental evaluation submodule;

[0017] The adaptive strategy module includes an external environment monitoring submodule, a dynamic parameter adjustment submodule, and a temperature stability evaluation submodule;

[0018] The regional dynamic control module includes a regional division submodule, a temperature balance submodule, and a fine-tuning control submodule;

[0019] The pipeline network health monitoring module includes a fault diagnosis submodule, a potential problem warning submodule, and a maintenance suggestion submodule;

[0020] The energy usage behavior analysis module includes a user data analysis submodule, a behavior pattern recognition submodule, and an energy usage suggestion submodule;

[0021] The nonlinear configuration module includes a parameter modeling submodule, a nonlinear tuning submodule, and a solution verification submodule.

[0022] As a further solution of the present invention: the data preprocessing submodule uses Fourier transform denoising algorithm and Z-score normalization processing to standardize the original temperature data to generate processed real-time data;

[0023] The temperature monitoring submodule uses carbon fiber sensing technology and Kalman filtering to perform high-precision temperature monitoring based on the processed real-time data and generates a real-time temperature distribution map;

[0024] The sensor calibration submodule performs standard calibration of the sensor by the least square method to calibrate the real-time temperature distribution diagram and generate calibrated temperature data.

[0025] As a further solution of the present invention: the data standardization submodule uses MinMaxScaler to perform data standardization based on the calibrated temperature data to generate standardized temperature data;

[0026] The model training submodule uses a long short-term memory network to perform deep learning training on the standardized temperature data to generate an LSTM model;

[0027] The model validation submodule uses a cross-validation method to evaluate the model accuracy based on the LSTM model and an independent validation data set to generate a model accuracy report.

[0028] As a further solution of the present invention: the energy consumption assessment submodule uses the model accuracy report to apply a fuzzy logic algorithm to calculate the predicted energy consumption and generate a predicted energy consumption report;

[0029] The comfort simulation submodule uses the Fanger human comfort model to simulate based on the predicted energy consumption report and generates a comfort simulation result;

[0030] The environmental assessment submodule combines the comfort simulation results and the predicted energy consumption report, uses the life cycle assessment method to conduct an environmental impact assessment, and generates an environmental impact report.

[0031] As a further solution of the present invention: the external environment monitoring submodule applies multi-source data fusion and random forest algorithm to analyze external meteorological data and generate an external environment report;

[0032] The dynamic parameter adjustment submodule resets the system parameters using a dynamic weight adjustment algorithm based on the external environment report and the internal calibrated temperature data to generate a dynamic parameter configuration file;

[0033] The temperature stability assessment submodule utilizes the dynamic parameter configuration file and the real-time temperature distribution diagram, applies the Bayesian network to perform temperature stability assessment, and generates a temperature stability report.

[0034] As a further solution of the present invention: the region division submodule uses a K-means clustering algorithm to perform region division based on the temperature stability report to generate a region division map;

[0035] The temperature balance submodule refers to the regional division map and the standardized temperature data, uses a multi-objective optimization algorithm to perform temperature balance, and generates a temperature balance solution;

[0036] The fine-tuning control submodule performs fine-tuning according to the temperature balance scheme using PID control logic to generate a fine-tuning control record.

[0037] As a further solution of the present invention: the fault diagnosis submodule uses a neural network to perform fault diagnosis based on the fine-tuning control record and the real-time temperature distribution diagram, and generates a fault diagnosis report;

[0038] The potential problem warning submodule uses the fault diagnosis report and the model accuracy report to apply the decision tree algorithm to warn of potential problems and generate a potential problem warning notification;

[0039] The maintenance suggestion submodule generates a maintenance suggestion report based on the potential problem warning notification using a natural language processing algorithm.

[0040] As a further solution of the present invention: the user data analysis submodule uses the maintenance suggestion report and the user usage data to analyze the user data using data mining technology to generate a user data analysis report;

[0041] The behavior pattern recognition submodule uses association rule learning to perform behavior pattern recognition based on the user data analysis report and generates a behavior pattern recognition report;

[0042] The energy usage suggestion submodule generates an energy usage suggestion report using multi-factor analysis based on the behavior pattern recognition report and the predicted energy consumption report.

[0043] As a further solution of the present invention: the parameter modeling submodule uses the energy use recommendation report and historical data to perform parameter modeling using a support vector machine to generate a parameter model file;

[0044] The nonlinear tuning submodule uses a genetic algorithm to perform nonlinear tuning based on a parameter model file to generate a nonlinear tuning solution;

[0045] The scheme verification submodule utilizes the nonlinear optimization scheme and the environmental impact report, applies a simulated annealing algorithm to perform scheme verification, and generates a scheme verification report.

[0046] Compared with the prior art, the advantages and positive effects of the present invention are:

[0047] In the present invention, high-precision temperature monitoring is achieved through carbon fiber sensing technology, which improves the accuracy of temperature data and provides a reliable data basis for subsequent analysis and optimization. The use of LSTM deep learning network can more accurately predict future heating demand and reduce energy waste. The multi-objective Pareto optimization strategy enables the system to achieve the best balance between comfort, energy consumption and environmental benefits. The fuzzy logic controller ensures the uniformity of heating, thereby improving the comfort of users. Acoustic emission technology and association rule learning provide strong technical support for system operation and maintenance and user behavior analysis, and realize intelligent fault warning and deep mining of energy consumption behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a system flow chart of the present invention;

[0049] Figure 2 is a system block diagram of the present invention;

[0050] Figure 3 It is a flow chart of the sensor data acquisition module of the present invention;

[0051] Figure 4 This is a flow chart of the AI ​​prediction module of the present invention;

[0052] Figure 5 It is a flow chart of the optimization control module of the present invention;

[0053] Figure 6 It is a flow chart of the adaptive strategy module of the present invention;

[0054] Figure 7 This is a flow chart of the regional dynamic control module of the present invention;

[0055] Figure 8 This is a flow chart of the pipeline health monitoring module of the present invention;

[0056] Fig. 9 This is a flow chart of the energy consumption behavior analysis module of the present invention;

[0057] Fig.10 This is a flow chart of the nonlinear configuration module of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0060] Embodiment 1

[0061] See also Figure 1 , an intelligent temperature-limited heating system coupled with carbon fiber and heating pipe network is composed of a sensor data acquisition module, an AI prediction module, an optimization control module, an adaptive strategy module, a regional dynamic control module, a pipe network health monitoring module, an energy consumption behavior analysis module, and a nonlinear configuration module;

[0062] The sensor data acquisition module uses carbon fiber sensor technology and time domain reflection measurement method to monitor the temperature distribution and changes in the heating network in real time and generate real-time temperature data;

[0063] The AI ​​prediction module uses LSTM deep learning network to analyze historical temperature distribution based on real-time temperature data and generate predicted heating demand;

[0064] The optimization control module generates an optimized heating strategy based on the predicted heating demand, using a multi-objective optimization algorithm specifically for Pareto optimization, taking into account comfort, energy consumption, and environmental benefits;

[0065] The adaptive strategy module dynamically adjusts the heating temperature and strategy based on the optimized heating strategy, combined with external environmental factors and real-time temperature data, and generates adaptive adjustment instructions;

[0066] The regional dynamic control module divides the heating area based on the adaptive adjustment instructions, and uses the fuzzy logic controller to make fine adjustments to ensure the temperature balance of each area and generate the regional heating adjustment strategy;

[0067] The pipeline health monitoring module uses real-time temperature data and acoustic emission technology to analyze the pipeline status, detect potential faults, and generate pipeline health reports;

[0068] The energy consumption behavior analysis module combines the predicted heating demand and user historical data, uses association rules to learn and analyze user energy consumption behavior, and generates a user energy consumption behavior report;

[0069] The nonlinear configuration module uses a nonlinear optimization method, specifically particle swarm optimization, based on the user energy consumption behavior report to fine-tune the system parameters and generate the final heating plan.

[0070] First, the sensor data acquisition module uses carbon fiber sensing technology and time domain reflection measurement method to monitor the temperature distribution and changes of the heating network in real time. This coupling can accurately obtain the temperature information of the network and provide an accurate data basis for subsequent modules.

[0071] Secondly, the AI ​​prediction module uses the LSTM deep learning network to analyze the historical temperature distribution based on real-time temperature data to generate a predicted heating demand. This prediction function can predict and accurately estimate the heating demand in advance, providing a decision-making basis for the optimization control module.

[0072] The optimization control module adopts the multi-objective optimization algorithm of Pareto optimization, comprehensively considers comfort, energy consumption and environmental benefits, and generates the optimal heating strategy. Through optimization control, the system can minimize energy consumption and environmental impact while meeting comfort requirements.

[0073] The adaptive strategy module dynamically adjusts the heating temperature and strategy based on the optimized heating strategy, external environmental factors and real-time temperature data to achieve real-time adaptation to actual conditions. This adaptive performance ensures that the heating system is always in the best working state, improving the heating effect and energy efficiency.

[0074] The regional dynamic control module combines adaptive adjustment instructions, fuzzy logic controller and other technologies to achieve balanced and fine control of heating areas. The module can dynamically adjust according to the actual needs of different areas to improve the balance and comfort of heating.

[0075] The network health monitoring module detects the health status of the heating network by analyzing real-time temperature data and acoustic emission technology, and generates a network health report. This monitoring mechanism can detect potential failures in the network in advance, and perform repairs and maintenance in a timely manner to ensure the reliability and safety of the heating system.

[0076] The energy consumption behavior analysis module combines the predicted heating demand and user historical data, and uses methods such as association rule learning to analyze the user's energy consumption behavior. By understanding user needs, the heating system can be adjusted in a personalized manner to provide heating services that better meet user needs.

[0077] Finally, the nonlinear configuration module uses nonlinear optimization methods to fine-tune system parameters and further optimize the heating solution. This parameter optimization can improve the stability and performance of the system, making the heating system more efficient and reliable.

[0078] See also Figure 2 The sensor data acquisition module includes a data preprocessing submodule, a temperature monitoring submodule and a sensor calibration submodule. The data preprocessing submodule processes and cleans the collected data to ensure the accuracy and reliability of the data. The temperature monitoring submodule uses carbon fiber sensing technology to monitor the temperature distribution of the pipe network in real time and provide temperature data of the heating system. The sensor calibration submodule calibrates the sensor to ensure the accuracy and consistency of the sensor measurement.

[0079] The AI ​​prediction module includes a data standardization submodule, a model training submodule, and a model verification submodule. The data standardization submodule standardizes the sensor data to adapt it to the needs of model training. The model training submodule uses the standardized data to train AI models, such as LSTM deep learning networks, to predict heating demand. The model verification submodule verifies the trained model and evaluates its prediction accuracy and reliability.

[0080] The optimization control module includes an energy consumption evaluation submodule, a comfort simulation submodule, and an environmental evaluation submodule. The energy consumption evaluation submodule evaluates the energy efficiency and energy saving potential of the heating system by analyzing the energy consumption data of the heating system. The comfort simulation submodule helps optimize the control strategy of the heating system and improve user satisfaction by simulating and predicting the user's comfort. The environmental evaluation submodule considers the impact of the heating system on the environment and comprehensively evaluates its environmental benefits and sustainability.

[0081] The adaptive strategy module includes an external environment monitoring submodule, a dynamic parameter adjustment submodule, and a temperature stability evaluation submodule. The external environment monitoring submodule monitors external environmental factors in real time, such as outdoor temperature and weather conditions, to implement an adaptive control strategy that adapts to the external environment. The dynamic parameter adjustment submodule adjusts the parameters of the heating system based on data such as the external environment and real-time temperature to achieve temperature stability and energy conservation. The temperature stability evaluation submodule evaluates the stability and control accuracy of the heating system to ensure stable heating effects and comfort.

[0082] The regional dynamic control module includes the regional division submodule, the temperature balance submodule and the fine-tuning control submodule. The regional division submodule divides the heating area to achieve independent control of different areas. The temperature balance submodule dynamically adjusts the heating temperature and flow to maintain temperature balance in different areas and improve heating comfort. The fine-tuning control submodule performs fine-tuning control according to real-time temperature and comfort requirements to further improve the heating effect of the area.

[0083] The network health monitoring module includes a fault diagnosis submodule, a potential problem warning submodule, and a maintenance suggestion submodule. The fault diagnosis submodule detects faults and abnormalities in the heating network by analyzing real-time temperature data and acoustic emission technology. The potential problem warning submodule warns of potential fault risks and problems in the network in advance so that maintenance measures can be taken in time. The maintenance suggestion submodule provides corresponding repair and maintenance suggestions based on the evaluation results of the network health status to ensure the normal operation of the heating system.

[0084] The energy consumption behavior analysis module includes a user data analysis submodule, a behavior pattern recognition submodule, and an energy consumption suggestion submodule. The user data analysis submodule analyzes and processes user historical data, extracts and organizes user energy consumption behavior data. The behavior pattern recognition submodule identifies user-specific needs and habit patterns by analyzing and learning user energy consumption behaviors. The energy consumption suggestion submodule provides users with personalized energy consumption suggestions based on the identified behavior patterns to help them optimize energy use and save energy costs.

[0085] The nonlinear configuration module includes parameter modeling submodule, nonlinear tuning submodule and scheme verification submodule. The parameter modeling submodule establishes a nonlinear model based on the characteristics and requirements of the system to describe the relationship between the key parameters and performance of the heating system. The nonlinear tuning submodule uses the corresponding nonlinear optimization method to optimize the overall performance of the system by optimizing the parameter configuration. The scheme verification submodule verifies and evaluates the optimization results to ensure the feasibility and practicality of the final heating scheme.

[0086] See also Figure 3 ,The data preprocessing submodule uses Fourier transform denoising algorithm and Z-score normalization processing to standardize the raw temperature data and generate the processed real-time data;

[0087] The temperature monitoring submodule uses carbon fiber sensing technology and Kalman filtering to perform high-precision temperature monitoring based on processed real-time data and generate a real-time temperature distribution map;

[0088] The sensor calibration submodule performs standard calibration of the sensor through the least square method to calibrate the real-time temperature distribution map and generate calibrated temperature data.

[0089] The Fourier transform denoising algorithm and Z-score normalization processing of the data preprocessing submodule can effectively eliminate noise and outliers in the temperature data and improve the accuracy and reliability of the data. This helps to improve the performance and result reliability of subsequent modules.

[0090] The temperature monitoring submodule combines carbon fiber sensing technology and Kalman filter algorithm to achieve high-precision temperature monitoring. Carbon fiber sensing technology has the advantages of fast response, high sensitivity and reliability, and can accurately capture the temperature changes at various locations in the heating system. Kalman filtering can integrate measurement data and prediction models, reduce measurement errors, and improve the accuracy of temperature monitoring.

[0091] The sensor calibration submodule uses the least squares method to perform standard calibration on the sensor, further improving the accuracy and consistency of the temperature data. Sensor calibration can correct the drift and nonlinear characteristics of the sensor, making the temperature data more reliable and accurate.

[0092] See also Figure 4 ,The data standardization submodule uses MinMaxScaler to perform data standardization based on the calibrated temperature data to generate standardized temperature data;

[0093] The model training submodule uses a long short-term memory network to perform deep learning training on standardized temperature data to generate an LSTM model;

[0094] The model validation submodule uses a cross-validation method to evaluate the model accuracy based on the LSTM model and an independent validation dataset and generate a model accuracy report.

[0095] The data normalization submodule uses MinMaxScaler to normalize the calibrated temperature data. Normalization can scale the data to a uniform range, eliminate the differences between different features, and make the data more suitable for training deep learning models. Through normalization, the temperature data can better meet the input requirements of the model, improving the effect and stability of model training.

[0096] The model training submodule uses a long short-term memory network (LSTM) to perform deep learning training on standardized temperature data. LSTM is a powerful model suitable for modeling sequence data, which can capture the time dependency and long-term memory in the data. Through the training of the LSTM model, the system can learn the complex time series patterns and feature representations in the temperature data, improving the understanding and prediction capabilities of temperature changes.

[0097] The model validation submodule uses a cross-validation method to evaluate the accuracy of the trained LSTM model based on an independent validation data set. Cross-validation can more objectively evaluate the generalization ability and performance stability of the model. Through the model accuracy report, you can understand the prediction accuracy of the LSTM model in practical applications and further improve and optimize the model.

[0098] See also Figure 5,The energy consumption assessment submodule utilizes the model accuracy report and applies fuzzy logic algorithm to calculate the predicted energy consumption and generate the predicted energy consumption report;

[0099] The comfort simulation submodule uses the Fanger human comfort model to simulate based on the predicted energy consumption report and generates comfort simulation results;

[0100] The environmental assessment submodule combines the comfort simulation results and the predicted energy consumption report, uses the life cycle assessment method to conduct an environmental impact assessment, and generates an environmental impact report.

[0101] The energy consumption assessment submodule uses the model accuracy report and applies fuzzy logic algorithms to calculate the predicted energy consumption. By combining the model accuracy report with the fuzzy logic algorithm, the energy consumption level of the system can be predicted more accurately. The generated predicted energy consumption report provides system managers with real-time energy consumption information and decision-making basis, helping them optimize energy utilization and energy consumption management.

[0102] The comfort simulation submodule uses the Fanger human comfort model for simulation based on the predicted energy consumption report. This module can evaluate the impact of the system's thermal environment on the human body, thereby predicting and optimizing indoor comfort. By simulating the comfort level under different temperature conditions, system managers can adjust the temperature according to different needs, improve people's comfort, and reduce energy consumption.

[0103] The environmental assessment submodule combines the comfort simulation results and the predicted energy consumption report, and uses the life cycle assessment method to conduct an environmental impact assessment. This submodule can comprehensively consider the impact of comfort and energy consumption on the environment and conduct a comprehensive environmental assessment. By evaluating the environmental impact of the system's life cycle, including resource consumption, carbon emissions, etc., the sustainability and environmental impact of the system on the environment can be evaluated, providing a scientific basis for environmental decision makers.

[0104] See also Figure 6 ,The external environment monitoring submodule applies multi-source data fusion and random forest algorithm to analyze external meteorological data and generate external environment reports;

[0105] The dynamic parameter adjustment submodule resets system parameters using a dynamic weight adjustment algorithm based on external environmental reports and internal calibrated temperature data to generate a dynamic parameter configuration file;

[0106] The temperature stability assessment submodule uses dynamic parameter configuration files and real-time temperature distribution diagrams, applies Bayesian networks to perform temperature stability assessment, and generates a temperature stability report.

[0107] The external environment monitoring submodule applies multi-source data fusion and random forest algorithm to analyze external meteorological data and generate external environment reports. By integrating external meteorological data from multiple data sources and applying the powerful random forest algorithm for analysis, it is possible to accurately assess the influencing factors of the external environment, such as outdoor temperature, humidity, wind speed, etc. The external environment report provides the system with real-time external environment information, which helps to dynamically adjust system parameters and optimize heating strategies.

[0108] The dynamic parameter adjustment submodule uses a dynamic weight adjustment algorithm to reset system parameters and generate a dynamic parameter configuration file based on the external environment report and internal calibrated temperature data. Through comprehensive analysis of the external environment report and internal temperature data, the dynamic parameter adjustment submodule can automatically adjust the parameter configuration of the heating system, such as heating temperature, flow, etc., according to actual needs and external conditions. This helps to achieve adaptive control of different external environments and improve the stability and energy efficiency of the system.

[0109] The temperature stability assessment submodule uses dynamic parameter configuration files and real-time temperature distribution graphs to apply Bayesian networks to perform temperature stability assessment and generate temperature stability reports. With the help of dynamic parameter configuration files and real-time temperature distribution graphs, the temperature stability assessment submodule can analyze and assess temperature stability through Bayesian networks. The temperature stability report provides system managers with information about the accuracy and stability of temperature control, helping them determine the temperature stability level of the system and take appropriate measures to optimize and improve it.

[0110] See also Figure 7 ,The regional division submodule uses the K-means clustering algorithm to perform regional division based on the temperature stability report and generates a regional division map;

[0111] The temperature balance submodule refers to the regional division map and standardized temperature data, uses a multi-objective optimization algorithm to perform temperature balance, and generates a temperature balance solution;

[0112] The fine-tuning control submodule uses PID control logic to perform fine-tuning according to the temperature balance solution and generates fine-tuning control records.

[0113] The regional division submodule uses the K-means clustering algorithm to divide the region based on the temperature stability report and generate a regional division map. By analyzing the temperature stability report, the system can divide the heating area into multiple regions, each with similar temperature stability characteristics. The regional division map provides spatial reference and guidance for subsequent temperature balance and fine-tuning control.

[0114] The temperature balance submodule references the regional division map and standardized temperature data, uses a multi-objective optimization algorithm to balance the temperature, and generates a temperature balance plan. Based on the regional division map and real-time standardized temperature data, the temperature balance submodule can use a multi-objective optimization algorithm to adjust the temperature between different areas, thereby achieving the overall temperature balance of the heating system. The temperature balance plan can make the temperature of different areas tend to be consistent, improving the stability and balance of the overall temperature control.

[0115] The fine-tuning control submodule uses PID control logic to perform fine-tuning according to the temperature balance solution and generates fine-tuning control records. The fine-tuning control submodule combines the temperature balance solution and uses PID control logic to fine-tune the temperature according to real-time temperature feedback information. Through fine-tuning control, the system can make subtle adjustments to the temperature to better meet the user's comfort needs. The fine-tuning control record records the operations and results of the fine-tuning process and provides a reference for system operation monitoring and optimization.

[0116] See also Figure 8 ,The fault diagnosis submodule uses neural network to perform fault diagnosis and generate fault diagnosis report based on the ,fine-tuning control records and real-time temperature distribution graph;

[0117] The potential problem warning submodule uses the fault diagnosis report and model accuracy report to apply the decision tree algorithm to warn of potential problems and generate potential problem warning notifications;

[0118] The maintenance suggestion submodule generates a maintenance suggestion report based on the potential problem warning notification using a natural language processing algorithm.

[0119] The fault diagnosis submodule uses neural networks to perform fault diagnosis and generate fault diagnosis reports based on fine-tuning control records and real-time temperature distribution maps. By analyzing fine-tuning control records and real-time temperature distribution maps, the fault diagnosis submodule can use neural networks to detect possible faults or abnormal conditions. The generated fault diagnosis report provides detailed fault information and diagnostic results, which helps system managers to find and solve problems in a timely manner and improve the reliability and stability of the heating system.

[0120] The potential problem warning submodule uses the fault diagnosis report and model accuracy report to apply the decision tree algorithm to warn potential problems and generate potential problem warning notifications. Combining the fault diagnosis report and model accuracy report, the potential problem warning submodule uses the decision tree algorithm to identify potential problems and abnormal situations and generate corresponding warning notifications. Warning notifications can remind system managers of potential problems that are about to occur, so that they can take timely measures to deal with them and avoid the situation from getting worse.

[0121] The maintenance suggestion submodule generates a maintenance suggestion report based on the potential problem warning notification using natural language processing algorithms. Potential problem warning notifications provide the maintenance suggestion submodule with a basis for identifying and handling potential problems. Based on the potential problem warning notifications, the maintenance suggestion submodule generates a maintenance suggestion report using natural language processing algorithms, including specific maintenance measures, operating instructions, etc. This can help maintenance personnel quickly understand the problem and provide corresponding repair suggestions to speed up troubleshooting and system recovery.

[0122] See also Fig. 9 ,The user data analysis submodule utilizes the maintenance suggestion report and the user usage data, applies data mining technology to analyze the user data, and generates a user data analysis report;

[0123] The behavior pattern recognition submodule uses association rule learning to perform behavior pattern recognition based on user data analysis reports and generates a behavior pattern recognition report;

[0124] The energy usage suggestion submodule generates an energy usage suggestion report based on the behavior pattern recognition report and the predicted energy consumption report using multi-factor analysis.

[0125] The user data analysis submodule uses the maintenance suggestion report and user usage data, applies data mining technology to analyze user data, and generates a user data analysis report. By analyzing the maintenance suggestion report and user usage data, the user data analysis submodule can extract information such as user behavior and preferences. By applying data mining techniques, such as clustering, classification, association rules, etc., user data can be parsed and analyzed to provide system managers with an in-depth understanding of user behavior and needs.

[0126] Based on the user data analysis report, the behavior pattern recognition submodule uses association rule learning to identify behavior patterns and generate a behavior pattern recognition report. Based on the user data analysis report, the behavior pattern recognition submodule uses the association rule learning method to identify the behavior patterns and rules of different users. The behavior pattern recognition report provides analysis and summary of user behavior, providing a reference for system managers to understand user needs, habits and preferences.

[0127] The energy suggestion submodule generates an energy suggestion report based on the behavior pattern recognition report and the predicted energy consumption report using multi-factor analysis. Based on the behavior pattern recognition report and the predicted energy consumption report, the energy suggestion submodule can use the multi-factor analysis method to comprehensively consider user behavior and energy consumption to provide users with personalized energy suggestions. The energy suggestion report can include energy-saving strategies, optimize energy utilization methods and other suggestions to help users reduce energy consumption, improve energy efficiency, and meet users' comfort needs.

[0128] See also Fig.10,The parameter modeling submodule uses the energy usage recommendation report and historical data, uses the support vector machine to perform parameter modeling, and generates a parameter model file;

[0129] The nonlinear tuning submodule uses genetic algorithm to perform nonlinear tuning based on parameter model files and generate nonlinear tuning solutions;

[0130] The solution verification submodule uses the nonlinear tuning plan and environmental impact report, applies the simulated annealing algorithm to verify the solution, and generates a solution verification report.

[0131] The parameter modeling submodule uses the energy usage recommendation report and historical data to perform parameter modeling using support vector machines and generate parameter model files. By using the energy usage recommendation report and historical data, the parameter modeling submodule can use machine learning algorithms such as support vector machines to build parameter models. The parameter model file contains the relationship between system parameters and energy consumption, and can more accurately predict and evaluate the energy consumption effect of the system.

[0132] The nonlinear tuning submodule uses genetic algorithms to perform nonlinear tuning based on the parameter model file and generates a nonlinear tuning solution. Based on the parameter model file, the nonlinear tuning submodule uses optimization algorithms such as genetic algorithms to adjust system parameters by finding the optimal solution. The nonlinear tuning solution can further optimize the parameter configuration and improve the energy efficiency and stability of the heating system.

[0133] The solution verification submodule uses the nonlinear tuning scheme and environmental impact report, applies the simulated annealing algorithm to verify the scheme, and generates a solution verification report. The solution verification submodule combines the nonlinear tuning scheme and environmental impact report, and uses algorithms such as the simulated annealing algorithm to verify the scheme. Through the optimization search process of the simulated annealing algorithm, the solution verification submodule can evaluate the performance and feasibility of the scheme and generate a corresponding solution verification report.

[0134] Working principle:

[0135] The sensor data acquisition module uses carbon fiber sensing technology and time domain reflectometry to monitor the temperature distribution and changes in the heating network in real time and generate real-time temperature data. This data acquisition method can provide high-precision temperature information for subsequent analysis and prediction.

[0136] The AI ​​prediction module uses LSTM deep learning network to analyze historical temperature distribution based on real-time temperature data and generate predicted heating demand. Through the training and prediction of deep learning algorithms, the system can accurately predict future heating demand and provide a basis for optimized control.

[0137] The optimization control module generates an optimized heating strategy based on the predicted heating demand, using a multi-objective optimization algorithm with Pareto optimization characteristics to comprehensively consider comfort, energy consumption and environmental benefits. This module can provide the best heating strategy by weighing the trade-offs between various objectives to achieve energy conservation and environmental friendliness.

[0138] The adaptive strategy module dynamically adjusts the heating temperature and strategy based on the optimized heating strategy, combined with external environmental factors and real-time temperature data, and generates adaptive adjustment instructions. This module can adjust the operating parameters of the heating system in real time according to actual conditions to adapt to changes in the external environment and dynamic changes in user needs.

[0139] The regional dynamic control module divides the heating area based on the adaptive adjustment instructions and uses the fuzzy logic controller to make fine adjustments to ensure the temperature balance in each area. This module can divide the heating network into regions and control the temperature balance, provide high-quality heating services, and enhance the comfort of users.

[0140] The network health monitoring module uses real-time temperature data and acoustic emission technology to analyze the network status, detect potential faults, and generate a network health report. By monitoring the health of the network, the system can detect abnormal phenomena in a timely manner and take corresponding maintenance and repair measures to ensure the reliable operation of the heating network.

[0141] The energy behavior analysis module combines the predicted heating demand and user historical data, uses association rules to learn and analyze user energy behavior, and generates a user energy behavior report. This module can deeply understand the user's energy characteristics and behavior patterns, and provide a basis for optimizing heating plans and energy recommendations.

[0142] The nonlinear configuration module uses a nonlinear optimization method, specifically particle swarm optimization, to fine-tune system parameters based on user energy consumption behavior reports and generate the final heating solution. By optimizing system parameters, the system can better meet user needs and improve heating effects and energy efficiency.

[0143] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent temperature-limited heating system coupled with carbon fiber and a heating pipe network, characterized in that: The intelligent temperature-limited heating system coupled with carbon fiber and heating pipe network is composed of a sensor data acquisition module, an AI prediction module, an optimization control module, an adaptive strategy module, a regional dynamic control module, a pipe network health monitoring module, an energy consumption behavior analysis module, and a nonlinear configuration module; The sensor data acquisition module uses carbon fiber sensor technology and time domain reflectometry to monitor the temperature distribution and changes in the heating network in real time and generate real-time temperature data; The AI ​​prediction module uses LSTM deep learning network to analyze historical temperature distribution based on real-time temperature data and generate predicted heating demand; The optimization control module generates an optimized heating strategy by using a multi-objective optimization algorithm specifically a Pareto optimization based on the predicted heating demand, taking into account comfort, energy consumption and environmental benefits; The adaptive strategy module dynamically adjusts the heating temperature and strategy based on the optimized heating strategy, combined with external environmental factors and real-time temperature data, and generates adaptive adjustment instructions; The regional dynamic control module divides the heating area based on the adaptive adjustment instructions, and uses the fuzzy logic controller to make fine adjustments to ensure the temperature balance of each area and generate a regional heating adjustment strategy; The pipeline network health monitoring module uses real-time temperature data and acoustic emission technology to analyze the pipeline network status, detect potential faults, and generate a pipeline network health report; The energy consumption behavior analysis module combines the predicted heating demand and the user's historical data, adopts association rule learning to analyze the user's energy consumption behavior, and generates a user energy consumption behavior report; The nonlinear configuration module uses a nonlinear optimization method, specifically a particle swarm optimization, based on the user energy consumption behavior report to fine-tune system parameters and generate a final heating plan.

2. The intelligent temperature-limited heating system of carbon fiber coupled with a heating pipe network according to claim 1 is characterized in that: The sensor data acquisition module includes a data preprocessing submodule, a temperature monitoring submodule, and a sensor calibration submodule; The AI ​​prediction module includes a data normalization submodule, a model training submodule, and a model verification submodule; The optimization control module includes an energy consumption assessment submodule, a comfort simulation submodule, and an environmental evaluation submodule; The adaptive strategy module includes an external environment monitoring submodule, a dynamic parameter adjustment submodule, and a temperature stability evaluation submodule; The regional dynamic control module includes a regional division submodule, a temperature balance submodule, and a fine-tuning control submodule; The pipeline network health monitoring module includes a fault diagnosis submodule, a potential problem warning submodule, and a maintenance suggestion submodule; The energy usage behavior analysis module includes a user data analysis submodule, a behavior pattern recognition submodule, and an energy usage suggestion submodule; The nonlinear configuration module includes a parameter modeling submodule, a nonlinear tuning submodule, and a solution verification submodule.

3. The intelligent temperature-limited heating system of carbon fiber coupled with a heating pipe network according to claim 2 is characterized in that: The data preprocessing submodule uses Fourier transform denoising algorithm and Z-score normalization processing to standardize the original temperature data and generate processed real-time data; The temperature monitoring submodule uses carbon fiber sensing technology and Kalman filtering to perform high-precision temperature monitoring based on the processed real-time data and generates a real-time temperature distribution map; The sensor calibration submodule performs standard calibration of the sensor by the least square method to calibrate the real-time temperature distribution diagram and generate calibrated temperature data.

4. The intelligent temperature-limited heating system of carbon fiber coupled with a heating pipe network according to claim 2 is characterized in that: The data standardization submodule uses MinMaxScaler to perform data standardization based on the calibrated temperature data to generate standardized temperature data; The model training submodule uses a long short-term memory network to perform deep learning training on the standardized temperature data to generate an LSTM model; The model validation submodule uses a cross-validation method to evaluate the model accuracy based on the LSTM model and an independent validation data set to generate a model accuracy report.

5. The intelligent temperature-limited heating system of carbon fiber coupled with a heating pipe network according to claim 2 is characterized in that: The energy consumption assessment submodule uses the model accuracy report and applies the fuzzy logic algorithm to calculate the predicted energy consumption and generate a predicted energy consumption report; The comfort simulation submodule uses the Fanger human comfort model to simulate based on the predicted energy consumption report and generates a comfort simulation result; The environmental assessment submodule combines the comfort simulation results and the predicted energy consumption report, uses the life cycle assessment method to conduct an environmental impact assessment, and generates an environmental impact report.

6. The intelligent temperature-limited heating system of carbon fiber coupled with a heating pipe network according to claim 2 is characterized in that: The external environment monitoring submodule uses multi-source data fusion and random forest algorithm to analyze external meteorological data and generate an external environment report; The dynamic parameter adjustment submodule resets the system parameters using a dynamic weight adjustment algorithm based on the external environment report and the internal calibrated temperature data to generate a dynamic parameter configuration file; The temperature stability assessment submodule utilizes the dynamic parameter configuration file and the real-time temperature distribution diagram, applies the Bayesian network to perform temperature stability assessment, and generates a temperature stability report.

7. The intelligent temperature-limited heating system of carbon fiber coupled with a heating pipe network according to claim 2 is characterized in that: The regional division submodule uses K-means clustering algorithm to perform regional division based on the temperature stability report and generates a regional division map; The temperature balance submodule refers to the regional division map and the standardized temperature data, uses a multi-objective optimization algorithm to perform temperature balance, and generates a temperature balance solution; The fine-tuning control submodule performs fine-tuning according to the temperature balance scheme using PID control logic to generate a fine-tuning control record.

8. The intelligent temperature-limited heating system of carbon fiber coupled with a heating pipe network according to claim 2 is characterized in that: The fault diagnosis submodule uses a neural network to perform fault diagnosis based on the fine-tuning control record and the real-time temperature distribution diagram, and generates a fault diagnosis report; The potential problem warning submodule uses the fault diagnosis report and the model accuracy report to apply the decision tree algorithm to warn of potential problems and generate a potential problem warning notification; The maintenance suggestion submodule generates a maintenance suggestion report based on the potential problem warning notification using a natural language processing algorithm.

9. The intelligent temperature-limited heating system of carbon fiber coupled with a heating pipe network according to claim 2 is characterized in that: The user data analysis submodule uses the maintenance suggestion report and user usage data to analyze user data using data mining technology to generate a user data analysis report; The behavior pattern recognition submodule uses association rule learning to perform behavior pattern recognition based on the user data analysis report and generates a behavior pattern recognition report; The energy usage suggestion submodule generates an energy usage suggestion report using multi-factor analysis based on the behavior pattern recognition report and the predicted energy consumption report.

10. The intelligent temperature-limited heating system of carbon fiber coupled with a heating pipe network according to claim 2 is characterized in that: The parameter modeling submodule uses the energy use recommendation report and historical data to perform parameter modeling using a support vector machine to generate a parameter model file; The nonlinear tuning submodule uses a genetic algorithm to perform nonlinear tuning based on a parameter model file to generate a nonlinear tuning solution; The scheme verification submodule utilizes the nonlinear optimization scheme and the environmental impact report, applies a simulated annealing algorithm to perform scheme verification, and generates a scheme verification report.

Citation Information

Patent Citations

  • Battery thermal runaway early warning protection system and protection method thereof

    CN116722249A

  • Dynamic optimization method for technological parameters in carbon fiber drafting process and computer storage medium

    CN116913428A