Intelligent control method of multi-heat-source coupling heat supply system

Abstract

The intelligent control method comprises the steps that a system architecture of the multi-heat-source coupling heat supply system is constructed, and the system architecture comprises a composite heat source module, an intelligent energy storage unit and an edge computing and internet-of-things platform; constructing a heat source energy efficiency dynamic evaluation matrix based on meteorological data and system monitoring data; constructing a multi-objective optimization model of the system, and solving the multi-objective optimization model in combination with the heat source energy efficiency dynamic evaluation matrix and an optimization algorithm to obtain an optimal solution; and dynamically distributing the output of each heat source according to the optimal solution. Controlling the system to operate in combination with multiple operation modes according to the external environment parameters and the actual operation parameters of the system; continuously optimizing related parameters of the system by adopting a reinforcement learning algorithm according to historical operation data and a reward function of the system; according to the scheme, the energy efficiency, flexibility, reliability and adaptability of the heat supply system are improved.

Description

Technical Field

[0001] This application relates to the technical field of heating systems, and in particular, to an intelligent control method for a multi-source coupled heating system. Background Art

[0002] Under the background of global climate change and energy structure transformation, the new direction of green development pursued by countries together is that, as a key area of energy consumption, the heating industry's energy conservation, emission reduction and efficient operation are crucial. The multi-source coupled heating system has become the development trend in the heating field by virtue of the advantage of integrating multiple heat sources.

[0003] However, the current system still faces many challenges in practical applications. Traditional heating systems mostly rely on a single heat source, such as coal-fired boilers and gas boilers. In this mode, the energy utilization efficiency is low, the flexibility is poor, and it is difficult to make full use of renewable energy. With the increasingly stringent requirements for energy structure adjustment and energy conservation and emission reduction, the traditional mode can no longer meet the development needs of the industry. Although multi-source combined heating has been applied in some areas, there are obvious deficiencies in the control method, specifically as follows:

[0004] 1. On the one hand, the heat source switching strategy is too single. Most existing systems only switch heat sources based on simple temperature or load thresholds and cannot adapt to complex and changeable actual working conditions. For example, at low loads, it is impossible to accurately judge and deactivate heat sources with high fuel prices, resulting in high operating costs. When the efficiencies of each heat source are different, it is also difficult to reasonably arrange the operation sequence of heat sources to achieve overall energy conservation. On the other hand, the energy distribution lacks rationality. Due to the lack of comprehensive analysis of real-time meteorological data, load changes, and the energy efficiency of each heat source, etc., the energy distribution often shows unreasonable phenomena. In actual operation, the output of some heat sources may be too large or too small, which not only causes energy waste but also affects the heating effect;

[0005] 2. The existing system has insufficient ability to accurately perceive and dynamically adjust the real-time state of the system. Lack of effective sensor networks and data analysis means, unable to collect environmental parameters and equipment status in real time and accurately, and it is difficult to establish an accurate dynamic evaluation matrix of heat source energy efficiency. When facing load fluctuations, weather changes, etc., it is impossible to adjust the output of each heat source in a timely and effective manner, resulting in the energy efficiency, stability and economy of the system being difficult to reach the optimal. Summary of the Invention

[0006] This application proposes an intelligent control method for a multi-source coupled heating system to at least solve one of the technical problems in the related technologies to a certain extent. The technical solution of this application is as follows:

[0007] An embodiment of this application proposes an intelligent control method for a multi-source coupled heating system, including:

[0008] Build the system architecture of a multi-heat-source coupled heating system, where the system architecture includes a composite heat source module, an intelligent energy storage unit, and an edge computing and Internet of Things platform;

[0009] Based on meteorological data and system monitoring data, build a dynamic evaluation matrix of heat source energy efficiency; and build a multi-objective optimization model of the system, and solve the multi-objective optimization model by combining the dynamic evaluation matrix of heat source energy efficiency and an optimization algorithm to obtain an optimal solution; and dynamically allocate the output of each heat source according to the optimal solution; where the dynamic evaluation matrix of heat source energy efficiency is used to quantify the real-time COP value, carbon emission factor, and operating cost of each heat source in the system;

[0010] According to external environmental parameters and actual operating parameters of the system, control the operation of the system in combination with a multi-operation mode control system;

[0011] Adopt a reinforcement learning algorithm to continuously optimize system-related parameters according to the historical operating data and reward function of the system to achieve intelligent control of the multi-heat-source coupled heating system.

[0012] In some implementation manners, the method further includes:

[0013] Obtain system-related vibration signals and thermodynamic monitoring parameters;

[0014] Based on the system-related vibration signals and thermodynamic monitoring parameters, predict the component life of system-related equipment through an equipment health assessment model to obtain a component life prediction result;

[0015] Dynamically adjust the maintenance strategy of system equipment according to the component life prediction result.

[0016] In some implementation manners, the composite heat source module integrates multiple heat sources of the system through a modular interface, and the multiple heat sources include low-grade heat sources, renewable energy sources, and standby heat sources; the composite heat source module adopts a dual-loop coupling structure, including a main loop and a secondary loop, the main loop directly extracts low-grade heat sources, the secondary loop improves the heat energy grade through a heat pump, and the COP value of the heat pump is dynamically adjusted according to the real-time temperature and flow of each heat source; heat exchange is realized between the main loop and the secondary loop through a plate heat exchanger.

[0017] In some implementation manners, the intelligent energy storage unit includes a composite energy storage device coupling phase change materials and a hot water storage tank, the composite energy storage device is equipped with a pressure compensation system, the pressure compensation system dynamically adjusts the internal pressure through a PID controller, and the PID controller automatically adjusts the internal pressure of the pressure compensation system according to the temperature fluctuation of each heat source.

[0018] In some implementation manners, the assembly method of the composite energy storage device includes:

[0019] Fill the phase change material into the hot water storage tank, and coat a nano-material coating on the phase change material; the phase change material is a composite material of paraffin and graphene.

[0020] In some implementation manners, the method for constructing the edge computing and Internet of Things platform includes:

[0021] Deploy a distributed sensor network inside the system, and the distributed sensor network is used to collect external environment parameters, system monitoring parameters, and system device status in real time;

[0022] Connect the distributed sensor network to the edge computing nodes of the distributed architecture, so as to implement local data preprocessing and control instruction generation through the edge computing nodes of the distributed architecture.

[0023] In some implementation manners, the constructing of the heat source energy efficiency dynamic evaluation matrix based on meteorological data and system monitoring data includes:

[0024] Obtain meteorological data and system monitoring data;

[0025] According to the meteorological data and system monitoring data, combine a machine learning model and a physical heat balance equation to obtain a heating load prediction result;

[0026] Based on the heating load prediction result and meteorological data, quantify the real-time COP value, carbon emission factor, and operating cost of each heat source to obtain a heat source energy efficiency dynamic evaluation matrix.

[0027] In some implementation manners, the controlling the system operation in combination with a multi-operation mode according to external environment parameters and system actual operation parameters includes:

[0028] When the external temperature is lower than the temperature lower limit threshold and the heating load prediction result for consecutive n hours exceeds the first output threshold of the system rated output, the system automatically switches to the extreme mode and controls the heat pump and the standby heat source to operate in coordination;

[0029] When it is in the low electricity price period, the system automatically switches to the economic mode, preferentially uses electric heating energy storage, and starts the air source heat pump during the period when the renewable energy power generation is greater than the second threshold of the heating load;

[0030] When the conditions of the extreme mode and the economic mode are not met, the system switches to the basic mode and controls the system operation according to the priority order of each heat source; the priority order of each heat source is low-grade heat source, renewable energy, intelligent energy storage unit, and standby heat source, wherein the charge and discharge threshold of the intelligent energy storage unit is dynamically set.

[0031] In some implementation manners, the reward function is defined as follows:

[0032] R = 0.4·ΔCOP + 0.3·ΔCost + 0.3·Satisfaction,

[0033] where ΔCOP is the energy efficiency improvement rate, ΔCost is the cost savings rate, and Satisfaction is the user satisfaction index, which is comprehensively calculated based on the user's room temperature feedback and complaint rate.

[0034] In some implementation manners, the device health assessment model adopts a hidden Markov model.

[0035] The intelligent control method for a multi-source coupled heating system provided by this application realizes the intelligent control of the multi-source coupled heating system by constructing a system architecture, adopting a dynamic energy efficiency optimization algorithm, multiple operating modes, and an adaptive learning mechanism, aiming to improve the energy efficiency, flexibility, reliability, and adaptability of the heating system to better meet the heating demands in different scenarios and achieve iterative optimization of the system performance. This solution rationally distributes the output of each heat source by adopting a dynamic energy efficiency optimization algorithm, improves the comprehensive energy efficiency ratio of the system, realizes multi-energy complementarity and real-time perception, and enhances the comprehensive utilization rate of energy; this solution sets multiple operating modes and automatically switches the operating mode according to different working conditions, greatly improving the flexibility and reliability of the system in dealing with different scenarios and meeting diverse heating demands;

[0036] The additional aspects and advantages of this application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of this application. Description of the Drawings

[0037] The above and / or additional aspects and advantages of this application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0038] Figure 1 is a schematic flowchart of an intelligent control method for a multi-source coupled heating system provided by an embodiment of this application. Detailed Embodiments

[0039] The embodiments of this application will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain this application and should not be construed as a limitation of this application.

[0040] The intelligent control method, device, and equipment for a multi-source coupled heating system according to an embodiment of this application will be described below with reference to the drawings.

[0041] Figure 1It is a schematic flowchart of an intelligent control method for a multi - heat - source coupled heating system provided by an embodiment of the present application. As Figure 1 shown, the intelligent control method for the multi - heat - source coupled heating system includes the following steps:

[0042] Step S101, construct the system architecture of the multi - heat - source coupled heating system, where the system architecture includes a composite heat source module, an intelligent energy storage unit, and an edge computing and Internet of Things platform.

[0043] The system architecture of the multi - heat - source coupled heating system constructed in this step is used for the basic support layer to achieve multi - energy complementarity and real - time perception. The system architecture includes a composite heat source module, an intelligent energy storage unit, and an edge computing and Internet of Things platform.

[0044] As an implementation, the composite heat source module integrates multiple heat sources of the system through modular interfaces. The multiple heat sources include low - grade heat sources, renewable energy sources, and standby heat sources. The composite heat source module adopts a double - loop coupling structure, including a main loop and a secondary loop. The main loop directly extracts low - grade heat sources, and the secondary loop improves the heat energy grade through a heat pump. The COP (Coefficient of Performance) value of the heat pump is dynamically adjusted according to the real - time temperature and flow of each heat source. Heat exchange is achieved between the main loop and the secondary loop through a plate heat exchanger.

[0045] Among them, COP is a key indicator to measure the energy efficiency of the heat pump, which is defined as the ratio of the heat output by the heat pump per unit time to the power it consumes.

[0046] As an example, low - grade heat sources include sewage sources, surface water, and industrial waste heat, etc., and their temperature range is between 5 - 35 °C; renewable energy sources include solar energy and air energy, etc., and standby heat sources include electric heating and biomass boilers. Among them, electric heating refers to a heating method that uses electric energy to convert into heat energy for heating; while a biomass boiler is a boiler that uses biomass energy (such as biomass fuels like straw and wood chips) as fuel. The dynamic adjustment range of the COP value of the heat pump is 2.5 - 4.0, and the heat exchange efficiency of the plate heat exchanger is ≥92%. The COP value of the heat pump is dynamically adjusted by real - time monitoring the temperature and flow of each heat source to ensure efficient heat energy conversion.

[0047] As an implementation, the composite heat source module supports modular expansion. The single - module heating capacity is 1 - 5 MW, and seamless switching is achieved through a redundant control algorithm during expansion, enhancing the flexibility and scalability of the system.

[0048] As an implementation, the intelligent energy storage unit includes a composite energy storage device in which a phase change material is coupled with a hot water storage tank. The composite energy storage device is equipped with a pressure compensation system, and the pressure compensation system dynamically adjusts the internal pressure through a PID controller. The PID controller automatically adjusts the internal pressure of the pressure compensation system according to the temperature fluctuations of each heat source.

[0049] Thus, the parameters of the PID controller of the pressure compensation system can be set so that it can automatically adjust the internal pressure according to the temperature fluctuations of each heat source.

[0050] As an example, the intelligent energy storage unit can select a hot water storage tank of appropriate specifications, fill the phase change material into the hot water storage tank, and coat a nano-material coating on the phase change material; the phase change material is a composite of paraffin and graphene, with a phase change temperature of 45 - 55 °C, and the energy storage density is increased to 180 - 220 kJ / kg; the thermal conductivity of the nano-material coating ≤ 0.05 W / (m·K). Set the parameters of the PID controller of the pressure compensation system so that the pressure regulation range is 0.1 - 0.6 MPa, which can adapt to the heat source temperature fluctuation of ±15 °C, ensuring the stable operation of the energy storage system of the heating system.

[0051] Thus, the intelligent energy storage unit dynamically adjusts the internal pressure through an integrated pressure compensation system, and can effectively reduce the heat loss of the hot water storage tank by coating a nano-material coating.

[0052] As an implementation, the construction method of the edge computing and Internet of Things platform includes: deploying a distributed sensor network inside the system, and the distributed sensor network is used to collect external environment parameters, system monitoring parameters, and system device status in real time; connecting the distributed sensor network to the edge computing nodes of the distributed architecture to realize local data preprocessing and control instruction generation through the edge computing nodes of the distributed architecture.

[0053] Exemplarily, the external environment parameters include temperature, humidity, solar radiation, etc., and the system device status includes heat pump speed and valve opening, etc. It can be required that the local data processing delay ≤ 50 ms, and the data upload frequency is dynamically adjusted to 1 - 10 Hz according to the load fluctuation. The edge computing and Internet of Things platform implemented in this way realizes the rapid preprocessing of local data and the timely generation of control instructions, reduces the burden on the central processor, and improves the response speed and real-time performance of the system.

[0054] Step S102, based on the meteorological data and system monitoring data, construct a dynamic evaluation matrix of heat source energy efficiency; and construct a multi-objective optimization model of the system, combine the dynamic evaluation matrix of heat source energy efficiency and the optimization algorithm to solve the multi-objective optimization model to obtain the optimal solution; and dynamically allocate the output of each heat source according to the optimal solution.

[0055] Among them, the dynamic evaluation matrix of heat source energy efficiency is used to quantify the real-time COP value, carbon emission factor, and operating cost of each heat source in the heating system.

[0056] This step is used to implement the dynamic energy efficiency optimization algorithm, and this dynamic energy efficiency optimization algorithm is used as the core decision-making layer to achieve the real-time optimal energy distribution of the heating system. That is, according to the meteorological data and system monitoring data, the output of each heat source is calculated through the dynamic energy efficiency optimization algorithm; and the system is adjusted according to the calculated output of each heat source.

[0057] As an implementation method, meteorological data and system monitoring data are obtained. According to the meteorological data and system monitoring data, combined with the machine learning model and the physical heat balance equation, the heating load prediction result is obtained; based on the heating load prediction result and meteorological data, the real-time COP value, carbon emission factor, and operating cost of each heat source are quantified to obtain the dynamic evaluation matrix of heat source energy efficiency.

[0058] As an example, the system monitoring data includes outdoor temperature data, indoor temperature data, solar radiation data, etc. The real-time meteorological data is obtained from the meteorological station API with high accuracy. The meteorological data includes weather-related information such as air temperature, humidity, wind speed, wind direction, and air pressure; the outdoor temperature data and indoor temperature data are collected by sensors, reflecting the temperature conditions of the indoor and outdoor environments; the solar radiation data is also collected by sensors.

[0059] This solution is based on real-time meteorological data and system monitoring data, combined with the machine learning model and the physical heat balance equation, to establish a dynamic evaluation matrix of heat source energy efficiency to quantify the real-time COP value, carbon emission factor (kgCO2 / kWh), and operating cost (yuan / kWh) of each heat source. Among them, the load prediction combines the machine learning model and the physical heat balance equation, and the physical heat balance equation is as follows:

[0060] Q load =α·T out +β·E=T in +γ·S sol +∈,

[0061] Among them, Q load is the load prediction, T out is the outdoor temperature, T in is the indoor temperature, S sol is the solar radiation.

[0062] In a multi-heat-source coupled heating system, load forecasting is jointly completed by a machine learning model and a physical heat balance equation. The physical heat balance equation constructs the relationship between load forecasting and factors such as outdoor temperature, indoor temperature, and solar radiation from a physical perspective. The machine learning model, on the other hand, mines the complex non-linear relationships between multiple factors based on the historical relevant data of the system to optimize the forecasting results and control the forecasting error within 5%. By combining the obtained load forecasting results with real-time meteorological data, it is used to quantify the real-time COP values, carbon emission factors, and operating costs of each heat source, and then construct a dynamic evaluation matrix of heat source energy efficiency to provide key data for real-time optimal energy allocation, thereby ensuring the efficient, economical, and environmentally friendly operation of the system.

[0063] As an example, for the dynamic evaluation matrix of heat source energy efficiency, in a heating system, there are three heat sources: solar energy, gas, and electric heating. On a certain day when the temperature is low and the sunlight is insufficient, the COP value of the solar heat source may be low, the COP value of the gas heat source is moderate, and the COP value of the electric heating heat source is not high either; in terms of carbon emissions, solar energy has almost no emissions, gas has certain emissions, and electric heating has relatively high emissions; in terms of operating costs, solar energy mainly includes equipment costs, gas is fuel procurement costs, and electric heating is electricity costs.

[0064] It should be noted that as another implementation method, load forecasting can be directly obtained through a machine learning model based on meteorological data and system monitoring data.

[0065] As an example, the objectives of the multi-objective optimization model can be set as improving energy utilization efficiency, reducing operating costs, and reducing carbon emissions. On the premise of meeting the heating demand, these objectives need to be balanced. For example, give priority to using the solar heat source, and reasonably match the gas and electric heating heat sources for the insufficient part.

[0066] As a way of implementation, the particle swarm optimization algorithm is used to solve the multi-objective optimization model to obtain the optimal solution.

[0067] Among them, the formula of the objective function of the multi-objective optimization model is as follows:

[0068] minJ = ω1·C cost + ω2·C carbon + ω3·C stability ,

[0069] Among them, C cost is the operating cost, including energy consumption costs and equipment maintenance costs; C carbon is the carbon emission, calculated based on the carbon emission factors of each heat source, covering the carbon emissions of fossil energy and electricity; C stabilityis the system stability index, quantified by the variance of the pipeline network pressure fluctuation; ω1, ω2, and ω3 are weight coefficients, and the weights are dynamically adjusted through the analytic hierarchy process to adapt to different operating scenarios and requirements.

[0070] This solution achieves the optimal solution by dynamically allocating the output of each heat source to optimize the comprehensive performance of the heating system.

[0071] Step S103: According to the external environmental parameters and the actual operating parameters of the system, the system operation is controlled in combination with the multi-operation mode.

[0072] It can be understood that during the operation of the heating system, according to different scenarios and multi-operation modes, a suitable operation mode is selected. The multi-operation mode is used in the scenario adaptation layer to improve the flexibility and reliability of the system.

[0073] As an implementation method, the method of controlling the system operation in combination with the multi-operation mode includes:

[0074] When the external temperature is lower than the temperature lower limit threshold and the heating load prediction result for consecutive n hours exceeds the first output threshold of the system rated output, the system automatically switches to the extreme mode to control the coordinated operation of the heat pump and the standby heat source;

[0075] When it is in the low electricity price period, the system automatically switches to the economic mode, preferentially uses the electric heating energy storage, and starts the air source heat pump during the period when the renewable energy power generation is greater than the second threshold of the heating load;

[0076] When the conditions of the extreme mode and the economic mode are not met, the system switches to the basic mode, and the system operation is controlled according to the priority order of each heat source; the priority order of each heat source is the low-grade heat source, renewable energy, intelligent energy storage unit, and standby heat source, where the charge and discharge threshold of the intelligent energy storage unit is dynamically set.

[0077] As an example, the operation modes include:

[0078] 1) Basic mode: The priority order is low-grade heat source > renewable energy > intelligent energy storage unit > standby heat source, where the charge and discharge threshold of the intelligent energy storage unit is dynamically set, the state of charge SOC range is 30% - 80%, and the compensation for load fluctuation is ±15%.

[0079] The basic mode gives priority to using low-grade heat sources and renewable energy, which can give full play to the advantages of clean energy. The intelligent energy storage unit adjusts dynamically according to the load changes to ensure the stability and continuity of heat supply. The intelligent energy storage unit adjusts its energy storage strategy according to the real-time load changes of the system. The intelligent energy storage unit will adjust its energy storage strategy according to the real-time load changes of the system. In the basic mode, it is clearly mentioned that the charge-discharge threshold of the energy storage unit is dynamically set, with its SOC range being 30%-80% and it can compensate for load fluctuations of ±15%. This means that when the real-time load of the system increases, the energy storage unit will discharge at an appropriate threshold according to its own state of charge and other conditions to supplement energy to meet the load demand; when the real-time load decreases and there is surplus energy, the energy storage unit will charge at the corresponding threshold. Through this dynamic adjustment, the stability and continuity of heat supply are ensured, fully reflecting that it will adjust the energy storage strategy according to the real-time load changes of the system.

[0080] 2) Extreme mode: When the external temperature is lower than -10°C and the predicted load value exceeds 80% of the system's rated output for 3 consecutive hours, it automatically switches to the coordinated operation of the heat pump and the standby heat source.

[0081] When the external temperature is lower than -10°C and the predicted load value exceeds 80% of the system's rated output for 3 consecutive hours, the system automatically switches to the extreme mode. Exemplarily, the heat pump and the standby heat source operate in a 7:3 ratio. Through the control logic, it is ensured that the heat supply temperature fluctuation ≤ ±0.5°C to meet the heat supply demand in extreme weather and ensure the comfort and heat supply safety of users.

[0082] The control logic here refers to: when the external temperature is lower than -10°C and the predicted load value exceeds 80% of the system's rated output for 3 consecutive hours, the system automatically switches to the extreme mode, and the heat pump and the standby heat source operate in a 7:3 ratio. During this process, in order to meet the heat supply demand in extreme weather and ensure the comfort and heat supply safety of users, the system will take measures to control the heat supply temperature fluctuation within the range of ≤ ±0.5°C. For example, a series of means such as power regulation of the heat pump and the standby heat source and flow control of the heat supply pipeline network are used to maintain the stability of the heat supply temperature.

[0083] 3) Economic mode: Give priority to using electric heating energy storage during the low electricity price period from 23:00 to 7:00, and start the air source heat pump when the new energy power generation > 30% of the load; the new energy power generation here refers to renewable energy.

[0084] Give priority to using electric heating energy storage during the low electricity price period (23:00 - 7:00), and start the air source heat pump when the new energy power generation > 30% of the load. That is, when in the low electricity price period or when there is an oversupply of new energy power generation, the system switches to the economic mode, making full use of low-cost electricity and new energy for energy storage and heat supply.

[0085] The air source heat pump here is a device that uses air energy for heat transfer. It mainly includes components such as a compressor, an evaporator, a condenser, and a throttling device. Its working principle is to absorb heat from the air through the evaporator, convert low-temperature heat energy into high-temperature heat energy, and then release the heat to the object or space that needs to be heated through the condenser to achieve functions such as heating and hot water supply. In this process, it is indeed necessary to control the operation of the air source heat pump, such as controlling the start and stop of the compressor and adjusting the refrigerant flow rate, to ensure its efficient and stable use of air energy. However, the air source heat pump is not just about control. It also includes multiple links such as the collection, conversion, and transmission of air energy, and is a complete energy conversion system. Therefore, the air source heat pump is a device that uses air energy in renewable energy.

[0086] Through the multi-operation mode switching strategy, the charge-discharge efficiency of the energy storage system can be ≥90%, and by reasonably using off-peak electricity and new energy, the system operation cost is reduced by 40%, effectively reducing the system operation cost and improving the economy of energy utilization.

[0087] Step S104, use the reinforcement learning algorithm to continuously optimize the system-related parameters according to the historical operation data of the system and the reward function.

[0088] In this step, an adaptive learning mechanism and a continuous evolution layer are established to achieve system performance iteration.

[0089] As an implementation method, the reinforcement learning algorithm adopts a deep Q-network (DQN) structure, with an input layer of 50 dimensions and an output layer of 10 dimensions. By analyzing the historical operation data, the reward function of the reinforcement learning algorithm is defined by comprehensively considering the energy efficiency improvement rate, cost savings rate, and user satisfaction index as follows:

[0090] R = 0.4·ΔCOP + 0.3·ΔCost + 0.3·Satisfaction,

[0091] where ΔCOP is the energy efficiency improvement rate, ΔCost is the cost savings rate, and Satisfaction is the user satisfaction index, which is comprehensively calculated based on the user's room temperature feedback and complaint rate.

[0092] As an example, the continuously optimized system-related parameters include the charge-discharge threshold of the intelligent energy storage unit and the heat pump start-stop logic parameters, etc.

[0093] This solution optimizes parameters such as the charge-discharge threshold of the system energy storage and the heat pump start-stop logic according to the system historical operation data combined with reinforcement learning, and continuously improves the operation efficiency and performance of the system.

[0094] The intelligent control method of the embodiment of the present application further includes the following steps: acquiring vibration signals related to the system and thermodynamic monitoring parameters; predicting the component life of system-related devices through an equipment health assessment model based on the vibration signals related to the system and the thermodynamic monitoring parameters to obtain a component life prediction result; and dynamically adjusting the maintenance strategy of the system devices according to the component life prediction result.

[0095] In this solution, an equipment health assessment model of the system is established. The equipment health assessment model uses a hidden Markov model to predict the remaining life of each component of the system-related devices based on vibration signals and thermodynamic monitoring parameters; and dynamically adjusts the equipment maintenance strategy according to the predicted remaining life of each component.

[0096] As an example, the vibration signals are collected by an acceleration sensor with an accuracy of ±0.1g. The thermodynamic parameters include superheat and differential pressure. The hidden Markov model is used to predict the remaining life of the components, and the prediction error is ≤15%.

[0097] This solution can dynamically adjust the maintenance strategy to 80% of the equipment life according to the prediction result, perform maintenance in advance, reduce the probability of equipment failure, extend the service life of the equipment, and reduce the maintenance cost of the system.

[0098] It should be noted that there is interaction and cooperation between step S103 and step S104. During the actual operation of the system, step S103 switches between multiple operation modes based on the external environment and the actual situation of the system to ensure the stable and efficient operation of the heating system in different scenarios. In step S104, the reinforcement learning algorithm optimizes the system parameters by analyzing historical data. These parameter optimizations may affect the threshold settings of the multiple operation mode switching in step S103, such as the charge and discharge thresholds of the energy storage unit and the switching conditions of heat sources in different modes, making the multiple operation modes more reasonable. At the same time, in step S104, the equipment health assessment model predicts the component life and adjusts the maintenance strategy according to the prediction result. This process will affect the selection of the system operation mode in step S103. For example, in an extreme mode, if the life of a key component is approaching the end, the heat source operation combination may be adjusted in advance to prevent equipment failure from affecting the heating effect. Therefore, step S103 and step S104 are interrelated and jointly act on the optimized operation of the entire system.

[0099] The intelligent control method of the multi-source coupled heating system in the embodiment of the present application realizes the intelligent control of the multi-source coupled heating system through constructing a system architecture, adopting a dynamic energy efficiency optimization algorithm, multiple operation modes and an adaptive learning mechanism, realizes multi-energy complementarity and real-time perception, and improves the energy utilization efficiency; through the dynamic energy efficiency optimization algorithm, according to real-time meteorological data, load prediction and physical heat balance equation, this solution constructs a dynamic evaluation matrix of heat source energy efficiency, and uses the particle swarm optimization algorithm to solve the multi-objective function, reasonably allocates the output of each heat source, and the comprehensive energy efficiency of the system is increased by 15%-20% compared with the traditional fixed strategy, realizes multi-energy complementarity and real-time perception, fully excavates the potential of low-grade heat sources, renewable energy, etc., and improves the comprehensive utilization rate of energy; through multiple operation modes, this solution automatically switches the operation mode according to different working conditions. In the basic mode, clean energy is preferentially utilized, and the energy storage unit dynamically compensates for load fluctuations. In the extreme mode, the heat pump and the standby heat source operate in coordination at a specific ratio to ensure the stability of the heating temperature fluctuation in extreme weather. In the economic mode, valley electricity and new energy are reasonably utilized to reduce the operation cost, improve the flexibility and reliability of the system to cope with different scenarios, and ensure stable heating in extreme weather to meet diverse heating needs; through the adaptive learning mechanism, this solution enables the system to continuously optimize its performance, improve the energy utilization rate and reduce the cost; through the equipment health assessment model in the adaptive learning mechanism, based on vibration signals and thermodynamic parameters, this solution uses the hidden Markov model to predict the remaining life of components, and according to the prediction results, dynamically adjusts the equipment maintenance strategy when it reaches a certain percentage of the equipment life in advance, effectively reducing the probability of equipment failure, extending the service life of the equipment, and reducing the system maintenance cost, which has significant economic and social benefits.

[0100] To clearly illustrate the above embodiments, specific examples are now used for illustration. The intelligent control method of the multi-source coupled heating system of the present application includes the following steps:

[0101] In the heating project of a certain area, first, the system architecture of the multi-source coupled heating system is built. According to the heat source distribution and heating demand in this area, composite heat source modules are installed, connecting the sewage source, nearby surface water, and surrounding industrial waste heat to the main circuit. Solar panels and air-source heat pumps are set as renewable energy access points, and electric heating and biomass boilers are equipped as backup heat sources. Pipe connections and equipment installations are carried out according to the double-loop coupling structure to ensure the correct installation of plate heat exchangers and the stable operation of heat pumps. At the same time, modular expansion interfaces and parameters of redundant control algorithms are set. For the intelligent energy storage unit, a hot water storage tank of appropriate specifications is selected, phase change materials are filled into the hot water storage tank, and a nano-material coating is applied. A pressure compensation system is installed, and the parameters of the PID controller are set so that it can automatically adjust the internal pressure according to the temperature fluctuation of the heat source. Edge computing and the Internet of Things platform are deployed. Distributed sensors are reasonably arranged in the area and connected to the edge computing nodes. The distributed architecture parameters of the edge computing nodes are set to ensure that the local processing delay and data upload frequency meet the requirements.

[0102] During the system operation, the dynamic energy efficiency optimization algorithm runs continuously. It obtains meteorological data in real time through the meteorological station API, inputs this data together with data such as indoor temperature and solar radiation collected by the sensor network into the load prediction model to obtain the load prediction result. Based on these data, a dynamic evaluation matrix of heat source energy efficiency is established, and the particle swarm optimization algorithm is used to solve the multi-objective function to adjust the output of each heat source in real time.

[0103] The multi-operation modes are automatically switched according to the actual operation situation. Under normal weather conditions, the system is in the basic mode, preferentially using low-grade heat sources and renewable energy, and the energy storage unit charges and discharges according to the load fluctuation; when encountering extremely cold weather with a temperature below -10°C and a continuously high load, the system automatically switches to the extreme mode, and the heat pump and the backup heat source work together. When the electricity price is at a low valley or there is an oversupply of new energy power generation, the system switches to the economic mode to make full use of low-cost electricity and new energy for energy storage and heating.

[0104] The system performance is continuously optimized through the adaptive learning mechanism. The reinforcement learning algorithm is used to continuously optimize the charge and discharge thresholds of the energy storage and the start-stop logic parameters of the heat pump according to the historical operation data and the reward function. The equipment health assessment model predicts the remaining life of each component of the equipment through vibration signals and thermodynamic monitoring parameters. When the predicted life approaches 80%, maintenance work is arranged in a timely manner.

[0105] In addition, regularly evaluate and optimize the system. Based on the system operation data, analyze the operation efficiency and performance indicators of each module, and optimize and adjust the heat pump control parameters of the composite heat source module, the phase change material performance of the intelligent energy storage unit, the data transmission efficiency between edge computing and the Internet of Things platform, etc. At the same time, according to the actual operation situation and user feedback, optimize the parameters of the dynamic energy efficiency optimization algorithm, the thresholds of multiple operation modes, and the reward function of the adaptive learning mechanism, etc., to continuously improve the overall performance of the system and user satisfaction.

[0106] In the description of the foregoing embodiments, the descriptions referring to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0107] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0108] The steps of any process or method shown in the flowchart or described in other ways herein may be executed not in the order shown or discussed, including in a substantially simultaneous manner according to the involved functions or in the reverse order, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0109] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. An intelligent control method for a multi-heat source coupled heating system, characterized in that: Includes the following: Constructing a system architecture of a multi-heat source coupled heating system, the system architecture comprising a composite heat source module, an intelligent energy storage unit, and an edge computing and Internet of Things platform; Based on meteorological data and system monitoring data, a dynamic evaluation matrix of heat source energy efficiency is constructed; and a multi-objective optimization model of the system is constructed, and the multi-objective optimization model is solved by combining the dynamic evaluation matrix of heat source energy efficiency and the optimization algorithm to obtain the optimal solution; and the output of each heat source is dynamically allocated according to the optimal solution; wherein the dynamic evaluation matrix of heat source energy efficiency is used to quantify the real-time COP value, carbon emission factor and operating cost of each heat source in the system; According to the external environment parameters and the actual operating parameters of the system, the system operates in combination with multiple operating modes; A reinforcement learning algorithm is used to continuously optimize system-related parameters based on the system's historical operating data and reward function to achieve intelligent control of the multi-heat source coupled heating system.

2. The method according to claim 1, characterized in that The method further comprises: Obtain system-related vibration signals and thermodynamic monitoring parameters; Based on the system-related vibration signals and thermodynamic monitoring parameters, the life of components of system-related equipment is predicted through an equipment health assessment model to obtain component life prediction results; According to the component life prediction results, the maintenance strategy of the system equipment is dynamically adjusted.

3. The method according to claim 1, characterized in that The composite heat source module integrates multiple heat sources of the system through a modular interface, and the multiple heat sources include low-grade heat sources, renewable energy and backup heat sources; the composite heat source module adopts a dual-loop coupling structure, including a main loop and a sub-loop, the main loop directly extracts low-grade heat sources, and the sub-loop improves the thermal energy grade through a heat pump, and the COP value of the heat pump is dynamically adjusted according to the real-time temperature and flow of each heat source; heat exchange is achieved between the main loop and the sub-loop through a plate heat exchanger.

4. The method according to claim 1, characterized in that: The intelligent energy storage unit includes a composite energy storage device coupled with a phase change material and a hot water storage tank. The composite energy storage device is equipped with a pressure compensation system. The pressure compensation system dynamically adjusts the internal pressure through a PID controller. The PID controller automatically adjusts the internal pressure of the pressure compensation system according to the temperature fluctuation of each heat source.

5. The method according to claim 4, characterized in that The assembly method of the composite energy storage device comprises: The phase change material is filled into the hot water storage tank, and a nano material coating is coated on the phase change material; the phase change material is a composite material of paraffin and graphene.

6. The method according to claim 1, characterized in that The method for constructing the edge computing and Internet of Things platform includes: Deploy a distributed sensor network in the system, wherein the distributed sensor network is used to collect external environmental parameters, system monitoring parameters and system equipment status in real time; The distributed sensor network is connected to the edge computing nodes of the distributed architecture to implement local data preprocessing and control instruction generation through the edge computing nodes of the distributed architecture.

7. The method according to claim 1, characterized in that The heat source energy efficiency dynamic evaluation matrix is ​​constructed based on meteorological data and system monitoring data, including: Obtain meteorological data and system monitoring data; According to the meteorological data and system monitoring data, combined with the machine learning model and the physical heat balance equation, a heating load prediction result is obtained; Based on the heating load prediction results and meteorological data, the real-time COP value, carbon emission factor and operating cost of each heat source are quantified to obtain a dynamic evaluation matrix of heat source energy efficiency.

8. The method according to claim 1, characterized in that The control system operates in combination with multiple operation modes according to the external environment parameters and the actual operation parameters of the system; including: When the external temperature is lower than the lower temperature threshold and the heating load forecast result for n consecutive hours exceeds the first output threshold of the system rated output, the system automatically switches to the extreme mode and controls the heat pump to operate in coordination with the backup heat source; When the electricity price is low, the system automatically switches to economic mode, giving priority to the use of electric heating energy storage, and starts the air energy heat pump during the second threshold period when the renewable energy generation is greater than the heating load; When the conditions of extreme mode and economic mode are not met, the system switches to basic mode and controls the system operation according to the priority order of each heat source; the priority order of each heat source is low-grade heat source, renewable energy, smart energy storage unit and backup heat source, wherein the charge and discharge thresholds of the smart energy storage unit are dynamically set.

9. The method according to claim 1, characterized in that: The reward function is defined as follows: R=0.4·ΔCOP+0.3·ΔCost+0.3·Satisfaction, Among them, ΔCOP is the energy efficiency improvement rate, ΔCost is the cost saving rate, and Satisfaction is the user satisfaction index, which is calculated based on user room temperature feedback and complaint rate.

10. The method according to claim 2, characterized in that The equipment health evaluation model adopts a hidden Markov model.

Images