Intelligent heat supply system and method for predicting peak regulation based on AI

Abstract

The invention provides an intelligent heat supply system and method based on AI prediction peak regulation, the intelligent heat supply system comprises a waste heat recovery module, a conventional heat source module, a phase change energy storage module and an intelligent control center, a heat source outlet of the waste heat recovery module is connected with a heat supply pipe network, and the waste heat recovery module is used for converting recovered industrial waste heat into available heat energy to supply heat to a user side; the heat source outlets of the waste heat recovery module and the conventional heat source module are connected with the phase change energy storage module and are used for charging the energy storage module when the heat load is in a valley and the waste heat is sufficient; heat source outlets of the phase-change energy storage module and the conventional heat source module are connected with a heat supply pipe network, so that the phase-change energy storage module and the conventional heat source module supply heat to a user side in a cooperative manner when heat load peak occurs and waste heat is insufficient; the intelligent control center is connected with the waste heat recovery module, the conventional heat source module and the phase change energy storage module and used for collecting data in real time and issuing a regulation and control instruction. According to the system, the free waste heat resource value is excavated to the maximum extent, meanwhile, through energy storage buffering and intelligent optimization control, consumption and cost of conventional energy are minimized, and an efficient regional heat supply solution integrating energy conservation, economy, reliability and environmental protection is formed.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of urban central heating, and particularly relates to an intelligent heating system and method based on AI prediction peak regulation. BACKGROUND

[0002] Central heating is the core infrastructure in northern cities in China, but the traditional system has two core pain points: regulation lag, that is, the traditional system relies on experience regulation or simple feedback control of "burning fire according to the weather", and cannot adjust the heating capacity in time when there is a cold wave or daytime temperature fluctuation, resulting in over-heating / over-cooling on the user side and energy waste rate exceeding 20%; waste heat idling, that is, a large amount of high-temperature exhaust gas (400-800 DEG C) and low-temperature wastewater (30-60 DEG C) generated in the fields of industrial production (such as chemical industry and steel) and transportation are not utilized, and direct discharge not only causes energy waste but also causes heat pollution; at the same time, the traditional system lacks energy storage devices, and the heat source continuously runs during non-heating peak periods, further increasing energy consumption.

[0003] With the development of Internet of Things, big data and AI technology, the heating system has massive data collection capability, but the existing intelligent heating scheme focuses on "prediction peak regulation" and does not combine waste heat recovery and phase change energy storage technology, and cannot fundamentally solve the dual contradiction of "energy waste + regulation lag". Therefore, the research and development of an intelligent heating system based on the cooperation of "AI prediction + waste heat recovery + phase change energy storage" has become a key direction for the upgrading of the industry. SUMMARY

[0004] The purpose of the present application is to provide an intelligent heating system and method based on AI prediction peak regulation, which is suitable for industrial waste heat cooperative regional central heating, commercial building heating and residential heating scenarios, and aims to solve the three problems of "response lag, energy waste and waste heat idling" of the traditional heating system, and promote the green low-carbon and intelligent upgrading of the heating field.

[0005] In order to achieve the above purpose, the technical scheme adopted by the present application is: In a first aspect, the present application provides an intelligent heating system based on AI prediction peak regulation, comprising a waste heat recovery module, a conventional heat source module, a phase change energy storage module and an intelligent control center, wherein: The heat source outlet of the waste heat recovery module is connected to the heat supply pipe network, so as to convert the recovered industrial waste heat into usable heat energy and supply heat to the user end; The heat source outlets of the waste heat recovery module and the conventional heat source module are connected to the phase change energy storage module, so as to charge the energy storage module when the heat load is low and the waste heat is sufficient; The heat source outlets of the phase change energy storage module and the conventional heat source module are connected to the heat supply pipe network, so as to supply heat to the user end in cooperation with the phase change energy storage module and the conventional heat source when the heat load is high and the waste heat is insufficient; The intelligent control center is connected to the waste heat recovery module, the conventional heat source module, and the phase change energy storage module, respectively, to collect data in real time and issue control commands.

[0006] Preferably, the waste heat recovery module includes a high-efficiency heat exchanger and a filtration and purification device, wherein the high-efficiency heat exchanger is connected to the industrial waste heat outlet through the filtration and purification device; and the heat source outlet of the high-efficiency heat exchanger is connected to the heat source inlet of the phase change energy storage module.

[0007] Preferably, the filtration and purification device includes a coarse filter, a fine filter, and an adsorption material layer.

[0008] Preferably, the phase change energy storage module includes multiple sets of energy storage units arranged in each heating area, and the multiple sets of energy storage units are arranged in a matrix in parallel; the multiple sets of energy storage units are filled with phase change materials with different phase change temperatures; each set of energy storage units includes multiple storage tanks, and the multiple storage tanks are connected in series.

[0009] Preferably, the storage tanks placed in the same group are filled with phase change materials with the same phase change temperature; each storage tank has a spirally wound heat exchange coil in its inner cavity; and each storage tank has multiple temperature sensors in its inner cavity, which are evenly distributed along the height of the storage tank.

[0010] Preferably, the intelligent control center includes: The data acquisition unit is used to acquire historical heat load data, future weather data, user behavior data, and waste heat resource data. The AI ​​prediction module is used to predict hourly heat load within a set time period; The optimization scheduling module is used to generate the optimal heating scheduling strategy based on the predicted heat load and real-time collected system operation data. The scheduling strategy is to coordinate the operation status of the waste heat recovery module, the conventional heat source module and the phase change energy storage module to realize intelligent peak shaving of the heating system.

[0011] Secondly, the present invention provides a smart heating method based on AI-predicted peak shaving, comprising the following steps: Based on the acquired historical heat load data, future meteorological data, user behavior habits, and waste heat resource fluctuation patterns, an LSTM (Long Short-Term Memory) network is used to predict the hourly heat load demand within a set time period. Based on the predicted heat load and real-time collected system operation data, the optimal heating scheduling strategy is generated.

[0012] Preferably, the optimal heating scheduling strategy includes: When the waste heat output is greater than or equal to 60% of the predicted heat load, the waste heat recovery module is used to supply heat to users, and the conventional heat source module and phase change energy storage module are shut down. When the waste heat output is 30%-60% of the predicted heat load, the waste heat recovery module and the conventional heat source module are used together to supply heat to the user. When the waste heat output is less than 30% of the predicted heat load, the waste heat recovery module, conventional heat source module and phase change energy storage module are used in combination to supply heat to users.

[0013] Preferably, an optimal heating scheduling strategy is generated based on the predicted heat load and real-time collected system operation data. The specific method is as follows: Based on the predicted heat load and real-time collected system operation data, the optimal scheduling strategy is solved by using a set objective function and a genetic algorithm.

[0014] Preferably, the set objective function is: minimum total cost + waste heat utilization rate ≥70% + energy storage efficiency ≥90%.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention provides an AI-based intelligent heating system for predictive peak shaving. By using industrial waste heat as the basic heat source, it constructs a multi-energy complementary intelligent heating system. Its core benefits are reflected in a significant improvement in energy utilization efficiency, system economy, and operational stability. Firstly, the system achieves efficient recovery and value reconstruction of industrial waste heat, a low-grade energy source, transforming previously wasted heat energy into a stable and reliable heating source. This directly reduces dependence on purchased energy, thereby reducing energy costs and environmental pollution. The introduction of a phase change energy storage module is a key innovation. As the system's "heat bank," it effectively solves the mismatch between waste heat supply and user demand in terms of time and intensity. Specifically, it stores excess heat during periods of surplus waste heat (such as production periods or nighttime) and releases it during periods of insufficient waste heat or peak demand (such as daytime or periods of extreme cold), thus greatly improving the availability of unstable waste heat resources and avoiding energy waste. The parallel design of the conventional heat source module and the energy storage module ensures reliable backup power under extreme conditions or maximum load. The dynamic scheduling by the intelligent control center ensures efficient coordination among the three heat sources. Based on real-time data, it prioritizes the use of waste heat, calls upon energy storage as needed, and activates the conventional heat source on demand, achieving peak shaving and valley filling of heat and precise on-demand distribution. This not only guarantees stable heating quality at the user end but also avoids frequent start-ups or inefficient operation of the conventional heat source, extending equipment lifespan and further reducing operating energy consumption and carbon emissions. Ultimately, while maximizing the value of free waste heat resources, the system minimizes the consumption and cost of conventional energy through energy storage buffering and intelligent optimization control, forming a highly efficient district heating solution that integrates energy saving, economy, reliability, and environmental protection. Attached Figure Description

[0016] Figure 1This is a schematic diagram of the system structure according to an embodiment of the present invention. Detailed Implementation

[0017] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0018] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0019] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0020] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0021] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0022] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0023] Example 1 This embodiment provides an AI-based predictive peak-shaving smart heating system. Based on the traditional "heat source-pipeline-user" architecture, it adds a waste heat recovery module and a phase change energy storage module. Through an intelligent control center, it achieves coordinated regulation of the entire system, forming a closed-loop system of "waste heat supplementing heat source + conventional heat source + phase change energy storage buffer + AI precise scheduling".

[0024] Specifically, it includes a waste heat recovery module, a conventional heat source module, a phase change energy storage module, and an intelligent control center, among which: The heat source outlet of the waste heat recovery module is connected to the heating network to convert the recovered industrial waste heat into usable heat energy and supply heat to users. The heat source outlets of the waste heat recovery module and the conventional heat source module are connected to the phase change energy storage module to charge the energy storage module when the heat load is low and the waste heat is sufficient. The heat source outlets of the phase change energy storage module and the conventional heat source module are connected to the heating network, so that the phase change energy storage module and the conventional heat source can work together to provide heat when the heat load is high and the waste heat is insufficient. The intelligent control center is connected to the waste heat recovery module, the conventional heat source module, and the phase change energy storage module, respectively, to collect data in real time and issue control commands.

[0025] This embodiment constructs a multi-energy complementary intelligent heating system by using industrial waste heat as the basic heat source. Its core benefits are reflected in the significant improvement of energy utilization efficiency, system economy, and operational stability. Firstly, the system achieves efficient recovery and value reconstruction of industrial waste heat, a low-grade energy source, transforming previously wasted heat energy into a stable and reliable heating source. This directly reduces dependence on purchased energy, thereby reducing energy costs and environmental pollution. The introduction of a phase change energy storage module is a key innovation. As the system's "heat bank," it effectively solves the mismatch between waste heat supply and user demand in terms of time and intensity. Specifically, it stores excess heat during periods of surplus waste heat (such as during production or at night) and releases it during periods of insufficient waste heat or peak demand (such as during the day or in cold weather), thus greatly improving the availability of unstable waste heat resources and avoiding energy waste. The parallel design of the conventional heat source module and the energy storage module ensures reliable backup power under extreme conditions or maximum load. The dynamic scheduling by the intelligent control center ensures efficient coordination among the three heat sources. Based on real-time data, it prioritizes the use of waste heat, calls upon energy storage as needed, and activates the conventional heat source on demand, achieving peak shaving and valley filling of heat and precise on-demand distribution. This not only guarantees stable heating quality at the user end but also avoids frequent start-ups or inefficient operation of the conventional heat source, extending equipment lifespan and further reducing operating energy consumption and carbon emissions. Ultimately, while maximizing the value of free waste heat resources, the system minimizes the consumption and cost of conventional energy through energy storage buffering and intelligent optimization control, forming a highly efficient district heating solution that integrates energy saving, economy, reliability, and environmental protection.

[0026] Example 2 Based on Example 1, this example provides a smart heating system based on AI prediction and peak shaving, wherein the waste heat recovery module serves as a "green supplementary heat source" to solve the dependence of traditional systems on fossil fuels.

[0027] Specifically, it includes a high-efficiency heat exchanger, a filtration and purification device, and a double-layer insulated pipe, wherein the high-efficiency heat exchanger is connected to the industrial waste heat outlet through the filtration and purification device.

[0028] The heat source outlet of the high-efficiency heat exchanger is connected to the heat source inlet of the phase change energy storage module via a double-layer insulated pipe.

[0029] In this embodiment, the high-efficiency heat exchanger adopts a novel microchannel heat exchange technology, which increases the heat exchange area by 30% and the heat transfer efficiency by 40% compared with the traditional heat exchanger. For example, when treating 400°C waste gas in a chemical industrial park, it can heat the circulating water from 30°C to 90°C, with a waste heat extraction rate of over 85%. The filtration and purification device includes a coarse filter, a fine filter, and an adsorption material layer to prevent impurities from clogging the heat exchanger or corroding the pipes, thereby extending the equipment's lifespan.

[0030] The inner layer of the double-layer insulated pipe is made of 304 stainless steel (high thermal conductivity), and the outer layer is wrapped with nano-aerogel insulation material. The heat loss is reduced by 50% compared with traditional rock wool insulation, ensuring that the temperature drop during the transportation of residual heat is ≤5℃ / km.

[0031] Example 3 Based on Example 1, this example provides a smart heating system based on AI prediction and peak shaving, wherein the phase change energy storage module acts as an energy buffer hub to balance heat load fluctuations and waste heat supply fluctuations.

[0032] Specifically, this includes multiple sets of energy storage units arranged in each heating area, with the multiple sets of energy storage units arranged in a matrix in parallel.

[0033] Multiple energy storage units are filled with phase change materials with different phase change temperatures.

[0034] Each energy storage unit includes multiple storage tanks connected in series. The storage tanks in the same group are filled with phase change materials with the same phase change temperature.

[0035] Each of the storage tanks is provided with a spirally wound heat exchange coil inside its cavity.

[0036] Each of the storage tanks is equipped with multiple temperature sensors inside its cavity, which are evenly distributed along the height of the storage tank.

[0037] In this embodiment, the inlet and outlet of multiple energy storage units are connected to the main insulation pipe, and the inlet and outlet of the main insulation pipe are connected to the inlet and outlet of the waste heat recovery module and the conventional heat source module.

[0038] The main insulated pipe is equipped with a flow control valve and a temperature sensor.

[0039] The working process of this embodiment: When the outlet temperature of the waste heat recovery module is ≥80℃, the phase change material temperature is ≤65℃, and the return water temperature of the heating network is ≤50℃, the waste heat recovery module is used to supply heat to the phase change energy storage module. When the water supply temperature of the heating network is ≤55℃, the phase change material temperature is ≥75℃, and the outlet temperature of the waste heat recovery module is ≤60℃, the phase change energy storage module is used to supply heat to the heating network.

[0040] Example 4 Based on Example 1, this example provides a smart heating system based on AI-predicted peak shaving, wherein the smart control center includes: The data acquisition unit is used to acquire historical data, meteorological data, user behavior data, and waste heat resource data; The AI ​​prediction module is used to predict hourly heat load within a set time period; The optimization scheduling module is used to generate the optimal heating scheduling strategy based on the predicted heat load and real-time collected system operation data; The scheduling strategy involves the coordinated control of the operating status of the waste heat recovery module, the conventional heat source module, and the phase change energy storage module to achieve intelligent peak shaving of the heating system.

[0041] In this embodiment, the AI ​​prediction module, based on historical heat load data, future meteorological data, user behavior habits, and waste heat resource fluctuation patterns, uses an LSTM long short-term memory network to predict the hourly heat load demand within a set time period.

[0042] The optimization scheduling module, based on the predicted hourly heat load demand within a set time period and the real-time collected system operation data, uses a set objective function and combines it with a genetic algorithm to solve for the optimal scheduling strategy.

[0043] The set objective function is "lowest total cost + waste heat utilization rate ≥70% + energy storage efficiency ≥90%".

[0044] In this embodiment, the scheduling strategy is to coordinate the operation of the waste heat recovery module, the conventional heat source module, and the phase change energy storage module to achieve intelligent peak shaving of the heating system. Specifically: When the waste heat output is greater than or equal to 60% of the predicted heat load, the waste heat recovery module is used to supply heat to users, and the conventional heat source module and phase change energy storage module are shut down. When the waste heat output is 30%-60% of the predicted heat load, the waste heat recovery module and the conventional heat source module are used together to supply heat to the user. When the waste heat output is less than 30% of the predicted heat load, the waste heat recovery module, conventional heat source module and phase change energy storage module are used in combination to supply heat to users.

[0045] Example 5 This embodiment provides a smart heating method based on AI-predicted peak shaving, which includes the following steps: Based on historical heat load data, future meteorological data, user behavior habits, and waste heat resource fluctuation patterns, an LSTM (Long Short-Term Memory) network is used to predict hourly heat load demand within a set time period.

[0046] Based on the predicted heat load and real-time collected system operation data, the optimal heating scheduling strategy is generated.

[0047] This embodiment achieves a fundamental shift in heating systems from passive response to proactive prediction by fusing multi-source data and applying the LSTM deep learning algorithm. Its beneficial effects are concentrated in the dual improvement of prediction accuracy and scheduling efficiency: This method integrates multi-dimensional information such as historical load, weather forecasts, user habits, and waste heat fluctuations, leveraging the excellent time-series data processing capabilities of the LSTM network to accurately capture the complex nonlinear changing patterns of heat demand, thereby generating high-precision hourly heat load forecasts. This provides a forward-looking decision-making basis for system scheduling. Based on this accurate prediction, the system can anticipate future heat gaps or surpluses and combine this with real-time operational data. Dynamically generating optimal scheduling strategies optimizes the coordinated operation of modules such as waste heat recovery, phase change energy storage, and conventional heat sources. For example, it can store heat in advance before peak demand, maximize energy storage during periods of abundant waste heat, and pre-activate conventional heat sources during periods of low cost, thereby significantly improving the overall energy efficiency and economy of the system. This prediction-based proactive scheduling mode not only effectively avoids the problem of instantaneous supply and demand imbalance under traditional control methods and reduces peak consumption and operating costs of conventional energy, but also ensures stable heating temperatures by smoothing the load curve, improving user comfort and extending equipment lifespan, thus achieving a unified optimization of the heating system's safety, economy, and comfort.

[0048] Example 6 Based on Example 5, this example provides a smart heating method based on AI-predicted peak shaving, wherein the optimal heating scheduling strategy includes: When the waste heat output is greater than or equal to 60% of the predicted heat load, the waste heat recovery module is used to supply heat to users, and the conventional heat source module and phase change energy storage module are shut down. When the waste heat output is 30%-60% of the predicted heat load, the waste heat recovery module and the conventional heat source module are used together to supply heat to the user. When the waste heat output is less than 30% of the predicted heat load, the waste heat recovery module, conventional heat source module and phase change energy storage module are used in combination to supply heat to users.

[0049] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A smart heating system based on AI-predictive peak shaving, characterized in that, It includes a waste heat recovery module, a conventional heat source module, a phase change energy storage module, and an intelligent control center, among which: The heat source outlet of the waste heat recovery module is connected to the heating network to convert the recovered industrial waste heat into usable heat energy and supply heat to users. The heat source outlets of the waste heat recovery module and the conventional heat source module are connected to the phase change energy storage module to charge the energy storage module when the heat load is low and the waste heat is sufficient. The heat source outlets of the phase change energy storage module and the conventional heat source module are connected to the heating network, so that when the heat load is high and the waste heat is insufficient, the phase change energy storage module and the conventional heat source work together to supply heat to the user end. The intelligent control center is connected to the waste heat recovery module, the conventional heat source module, and the phase change energy storage module, respectively, to collect data in real time and issue control commands.

2. The intelligent heating system based on AI prediction and peak shaving according to claim 1, characterized in that, The waste heat recovery module includes a high-efficiency heat exchanger and a filtration and purification device. The high-efficiency heat exchanger is connected to the industrial waste heat outlet via the filtration and purification device. The heat source outlet of the high-efficiency heat exchanger is connected to the heat source inlet of the phase change energy storage module.

3. The intelligent heating system based on AI prediction and peak shaving according to claim 2, characterized in that, The filtration and purification device includes a coarse filter, a fine filter, and an adsorption material layer.

4. The intelligent heating system based on AI prediction and peak shaving according to claim 1, characterized in that, The phase change energy storage module includes multiple sets of energy storage units arranged in each heating area, and the multiple sets of energy storage units are arranged in a matrix in parallel; the multiple sets of energy storage units are filled with phase change materials with different phase change temperatures; each set of energy storage units includes multiple storage tanks, and the multiple storage tanks are connected in series.

5. A smart heating system based on AI-predicted peak shaving according to claim 4, characterized in that, The storage tanks in the same group are filled with phase change materials with the same phase change temperature; each storage tank has a spirally wound heat exchange coil in its inner cavity; each storage tank has multiple temperature sensors in its inner cavity, which are evenly distributed along the height of the storage tank.

6. A smart heating system based on AI-predicted peak shaving according to claim 1, characterized in that, The intelligent control center includes: The data acquisition unit is used to acquire historical heat load data, future weather data, user behavior data, and waste heat resource data. The AI ​​prediction module is used to predict hourly heat load within a set time period; The optimization scheduling module is used to generate the optimal heating scheduling strategy based on the predicted heat load and real-time collected system operation data. The scheduling strategy is to coordinate the operation status of the waste heat recovery module, the conventional heat source module and the phase change energy storage module to realize intelligent peak shaving of the heating system.

7. A smart heating method based on AI-predicted peak shaving, characterized in that, Includes the following steps: Based on the acquired historical heat load data, future meteorological data, user behavior habits, and waste heat resource fluctuation patterns, an LSTM (Long Short-Term Memory) network is used to predict the hourly heat load demand within a set time period. Based on the predicted heat load and real-time collected system operation data, the optimal heating scheduling strategy is generated.

8. A smart heating method based on AI-predicted peak shaving according to claim 7, characterized in that, Optimal heating scheduling strategies include: When the waste heat output is greater than or equal to 60% of the predicted heat load, the waste heat recovery module is used to supply heat to users, and the conventional heat source module and phase change energy storage module are shut down. When the waste heat output is 30%-60% of the predicted heat load, the waste heat recovery module and the conventional heat source module are used together to supply heat to the user. When the waste heat output is less than 30% of the predicted heat load, the waste heat recovery module, conventional heat source module and phase change energy storage module are used in combination to supply heat to users.

9. A smart heating method based on AI-predicted peak shaving according to claim 7, characterized in that, Based on predicted heat load and real-time collected system operation data, an optimal heating scheduling strategy is generated. The specific method is as follows: Based on the predicted heat load and real-time collected system operation data, the optimal scheduling strategy is solved by using a set objective function and a genetic algorithm.

10. A smart heating method based on AI-predicted peak shaving according to claim 9, characterized in that, The set objective function is "lowest total cost + waste heat utilization rate ≥70% + energy storage efficiency ≥90%".

Images