Clean energy heat supply facility cooperative control method and system

Selecting the heating mode through dual learning layer and particle swarm optimization algorithm, and adjusting the equipment with the PID controller, the problems of heating demand fluctuation in the existing technology and the combination of heating of multiple equipment are solved, and the clean energy heating system is improved Efficiency and stability reduce operating costs.

CN119002239AInactive Publication Date: 2024-11-22TIANJIN THERMAL CO
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411471571.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-22
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing clean energy heating regulation technology has failed to effectively respond to the volatility of heating demand and the combined heating between multiple clean energy equipment, resulting in low thermal efficiency, high operating costs, flexibility and poor economic benefits.

Method used

The dual learning layer (sliding average model and autoregressive heteroscedastic model) is used to learn historical heating data, combine the particle swarm optimization algorithm to select the heating mode, and adjust the heating equipment according to the real-time operating parameters through the PID controller to realize the heating facilities collaborative control.

Benefits of technology

It significantly improves the overall efficiency and energy utilization of the heating system, reduces operating costs, enhances the flexibility, stability and reliability of the system, and can flexibly respond to fluctuations and changes under different environmental conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119002239A_ABST
    Figure CN119002239A_ABST
Patent Text Reader

Abstract

The invention provides a clean energy heat supply facility cooperative control method and system. The method comprises the steps that historical heat supply data are collected; double learning layers are established, the historical heat supply data are learned through the double learning layers, and fusion features are obtained; a heat supply mode is selected according to the fusion features through a particle swarm optimization algorithm, wherein the heat supply mode comprises gas boiler heat supply, heat and power cogeneration heat supply and gas and heat and power cogeneration mixed heat supply; heat supply is conducted according to the selected heat supply mode, and real-time operation parameters of heat supply equipment are collected; and the heat supply equipment is controlled through a PID controller according to the real-time operation parameters, so that cooperative control over the heat supply equipment is completed. According to the method, the periodicity and volatility of heat supply work are considered at the same time, the prediction precision of heat supply facilities for heat supply demands can be improved, the flexibility and adaptability of heat supply are enhanced, and the energy utilization efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of coordinated application of heating facilities, and in particular to a method and system for coordinated control of clean energy heating facilities. Background Art

[0002] At present, clean energy heating technology has gradually become an important choice for heating with its high efficiency and cleanliness. Clean energy heating technology not only realizes the cascade utilization of energy, but also improves the comprehensive utilization efficiency of energy.

[0003] Current clean energy heating control technology generally considers the heat load demand for heating through deep learning, and controls the equipment operating parameters and valve flow according to the output characteristics. It does not involve the volatility of heating demand, and does not consider the combined heating between multiple clean energy heating equipment. This can easily lead to insufficient matching between production capacity and demand, resulting in reduced thermal efficiency, increased operating costs, and poor flexibility and economic benefits. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the related art. To this end, the present invention provides a clean energy heating facility coordinated control method and system.

[0005] The present invention provides a clean energy heating facility coordinated control method, comprising: S1: Collect historical heating data; S2: establishing a dual learning layer, learning the historical heating data through the dual learning layer, and obtaining fusion features; S3: selecting a heating mode according to the fusion characteristics by using a particle swarm optimization algorithm, wherein the heating mode includes gas boiler heating, cogeneration heating, and gas and cogeneration heating; S4: Providing heating according to the selected heating mode and collecting real-time operating parameters of the heating equipment; S5: The heating equipment is controlled according to the real-time operating parameters by a PID controller to complete the coordinated control of the heating facilities.

[0006] According to a clean energy heating facility collaborative control method provided by the present invention, the dual learning layer in step S2 includes: A first learning layer, wherein the first learning layer is a sliding average model; The second learning layer is an autoregressive conditional heteroskedasticity model.

[0007] According to a clean energy heating facility coordinated control method provided by the present invention, step S2 further comprises: S21: inputting the historical heating data into the dual learning layer; S22: learning the historical heating data through the first learning layer to obtain periodic features; S23: learning the periodic characteristics through the second learning process to obtain a fluctuation characteristic; S24: performing feature splicing on the periodic feature and the fluctuation feature to obtain a fusion feature.

[0008] According to a clean energy heating facility coordinated control method provided by the present invention, step S3 further comprises: S31: Encode multiple heating modes and corresponding parameter configurations to obtain a search space; S32: Establishing a fitness function according to the fusion feature; S33: Initializing a particle swarm, wherein a plurality of particles in the particle swarm search the search space according to the fitness function and output an optimal heating mode.

[0009] According to a coordinated control method for clean energy heating facilities provided by the present invention, the parameter configuration in step S31 includes the heating power of the gas boiler, the heating power of the cogeneration, and the heat-to-electricity ratio of the cogeneration heating group.

[0010] According to a method for coordinated control of clean energy heating facilities provided by the present invention, in step S4, the real-time operating parameters are the supply and return water pressure difference and the circulation pump frequency of the heating equipment.

[0011] According to a clean energy heating facility coordinated control method provided by the present invention, step S5 specifically includes: When the heating mode is gas boiler heating, adjusting the operating power of the gas boiler; When the heating mode is cogeneration heating, adjusting the operating power of the heating equipment of the cogeneration equipment and the heat-to-electricity ratio of the heating equipment; When the heating mode is mixed heating of gas and cogeneration, the heating ratio of the gas boiler and the cogeneration equipment in the heating equipment, the operating power of the gas boiler, the operating power of the heating equipment of the cogeneration equipment, and the heat-to-electricity ratio of the heating equipment are adjusted.

[0012] The present invention also provides a clean energy heating facility coordinated control system, comprising: The first acquisition module: used to collect historical heating data; Learning module: used for learning the historical heating data through the established double learning layer to obtain fusion features; Selection module: used for selecting heating modes including gas boiler heating, cogeneration heating, and gas and cogeneration heating according to the fusion characteristics through a particle swarm optimization algorithm; The second acquisition module is used to provide heat according to the selected heating mode and collect real-time operating parameters of the heating equipment; Control module: used to control the heating equipment according to the real-time operating parameters through a PID controller to achieve coordinated control of heating facilities.

[0013] The present invention provides a method and system for collaborative control of clean energy heating facilities. By establishing a network based on a double learning layer to process historical heating data, the periodic characteristics and volatility characteristics of the historical heating data are learned respectively. Subsequently, a variety of heating modes are established, including gas boiler heating alone, combined heat and power peak-shaving first station heating alone, and gas boiler and combined heat and power peak-shaving first station mixed heating. The heating mode is selected according to the periodic characteristics and volatility characteristics obtained through learning. In addition, the parameters of the heating ratio and heating power are adjusted according to the real-time operating parameters during the heating process. Not only is the overall efficiency and energy utilization rate of the heating system significantly improved through a data-driven optimization method, it helps to reduce the operating cost of the heating system and improve economic benefits, but it can also flexibly respond to fluctuations under different environmental conditions, improve the adaptability and flexibility of the heating system, and also enhance the overall stability and reliability of the system and reduce the possibility of failures. In general, the present invention shows significant beneficial effects in improving heating efficiency, reducing operating costs, enhancing the flexibility of heating facilities, enhancing system stability and reliability, improving heating quality, and promoting the use of clean energy.

[0014] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of a method for coordinated control of clean energy heating facilities provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the structure of a clean energy heating facility collaborative control system provided by an embodiment of the present invention.

[0017] Reference numerals: 100, first acquisition module; 200, learning module; 300, selection module; 400, second acquisition module; 500, control module. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0019] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of the present invention. 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, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0020] In order to better understand the present invention, the terms appearing in the present invention are first explained below.

[0021] Cogeneration, combined heat and power (CHP) is the use of heat engines or power stations to simultaneously generate electricity and useful heat. It refers to a production method in which a power plant not only produces electricity but also uses the steam produced by a steam turbine generator to provide heat to users. In other words, it is a process in which electricity and heat are produced simultaneously, which saves fuel compared to the production of electricity and heat separately.

[0022] The present invention aims to provide a method and device that can effectively improve the efficiency and stability of clean energy heating facilities in practical applications, thereby promoting the development of clean energy heating collaborative application technology.

[0023] Combine the following Figure 1 to Figure 2 Embodiments of the present invention are described.

[0024] like Figure 1 As shown, the present invention provides a method for coordinated control of clean energy heating facilities, comprising: S1: Collect historical heating data.

[0025] In step S1, the heating demand in the heating area including different time periods and the changes in heat load at different times of the day are first collected. In addition, the scope of heating coverage and the number of users need to be collected. These data combined can reflect the seasonal, cyclical and sudden changes in heating demand, which can be used for learning in the subsequent step S2 to more accurately evaluate the potential factors in the historical heating data.

[0026] S2: Establishing a dual learning layer, learning the historical heating data through the dual learning layer to obtain fusion features.

[0027] Wherein, the dual learning layer in step S2 includes: A first learning layer, wherein the first learning layer is a sliding average model; The second learning layer is an autoregressive conditional heteroskedasticity model.

[0028] Furthermore, the established dual learning layer integrates the MA model and the ARCH model. The MA model predicts future values ​​by averaging the data of several past time points, which can smooth short-term fluctuations, while the ARCH model is used to analyze the volatility of time series and can better describe the volatility aggregation phenomenon in the data. The dual learning layer established by the present invention can make full use of the advantages of the MA model in time series smoothing and prediction, and the expertise of the ARCH model in capturing the volatility of time series.

[0029] Wherein, step S2 further comprises: S21: inputting the historical heating data into the dual learning layer; S22: learning the historical heating data through the first learning layer to obtain periodic features; S23: learning the periodic characteristics through the second learning process to obtain a fluctuation characteristic; S24: performing feature splicing on the periodic feature and the fluctuation feature to obtain a fusion feature.

[0030] The establishment of the dual learning layer is through a series structure, that is, the way the MA model is sequentially connected to the ARCH model, and also includes a fully connected layer. The specific learning process is to first select the appropriate sliding average model order according to the characteristics of the historical heating data, input the preprocessed historical heating data into the MA model, and perform model training. The smoothed heating data features are extracted from the output of the MA model. These features reflect the long-term trend and cyclical changes of the heating data. Then, based on the features extracted by the first learning layer, an ARCH model is established. The features extracted by the first learning layer are used as input to train the ARCH model. The fluctuation characteristics of the heating data are extracted from the output of the ARCH model. These features quantify the degree of fluctuation of the historical heating data. Finally, the features extracted from the two-layer network are spliced ​​dimension by dimension to obtain the final fusion features.

[0031] Specifically, the expression of fusion features is: ; in, To fusion features, For splicing operation, is the input historical heating data sequence, is the periodic feature of the first learning layer, is the fluctuation feature of the second learning layer.

[0032] The obtained fused feature is a new vector whose dimension is the sum of the output dimension of the MA model and the output dimension of the ARCH model. Since the outputs of the two models are one-dimensional time series and have the same length after preprocessing, the fused feature is a two-dimensional matrix, in which each row corresponds to a time point in the original data and each column corresponds to a feature (i.e., MA feature or ARCH feature).

[0033] S3: Selecting a heating mode according to the fusion characteristics by using a particle swarm optimization algorithm, wherein the heating mode includes gas boiler heating, cogeneration heating, and gas and cogeneration heating.

[0034] Wherein, step S3 further comprises: S31: Encode multiple heating modes and corresponding parameter configurations to obtain a search space; The parameter configuration in step S31 includes the heating power of the gas boiler, the heating power of the cogeneration, and the heat-to-electricity ratio of the cogeneration heating group.

[0035] Furthermore, since the heating mode itself is not a continuously adjustable parameter but a discrete option, in step S31, the problem is first converted into a form that can approximate the optimal solution through continuous parameter adjustment, that is, the problem is simplified to the problem of selecting different heating modes and their corresponding parameters, and it is assumed that each mode has one or more adjustable parameters.

[0036] So in order to apply the PSO algorithm, in step S31, each particle is regarded as a potential heating mode configuration, including the selected heating mode and the parameter settings under this mode. The position vector of the particle will contain these parameters, and the velocity vector will guide the movement of the particle in the search space.

[0037] S32: Establishing a fitness function according to the fusion feature; Further, in step S32, a fitness function is constructed by using the periodic characteristics and fluctuation characteristics learned in step S2, and the fitness function is used to evaluate the performance of each heating mode and its parameter configuration. In the problem of heating mode selection in this embodiment, the fitness function should be able to quantify the performance of different heating modes in terms of meeting heating demand, reducing operating costs, energy efficiency, etc.

[0038] Specifically, the periodic characteristics and fluctuation characteristics are first used as input variables, combined with the heating mode and its parameter configuration, and the performance of the heating system is predicted through a machine learning algorithm. The prediction result will be used as the output value of the fitness function to evaluate the quality of the current particle (i.e., the current heating mode).

[0039] S33: Initializing a particle swarm, wherein a plurality of particles in the particle swarm search the search space according to the fitness function and output an optimal heating mode.

[0040] In step S33, the size of the particle swarm is first set, and then the position of each particle is randomly initialized, and the speed of the particle is zero, and then the fitness of the particle is calculated, and then the global optimal solution is initialized as the position of the particle with the highest current fitness and the corresponding fitness, and the individual optimal solution of each particle is initialized as its current position and the corresponding fitness, and the iterative update begins.

[0041] For each particle, the expression for updating the particle's velocity is: ; in, For the moment, is the particle index value, For the updated The particle speed at time, is the inertia weight, Before update The particle speed at time, and is the learning factor, and for Random numbers in the interval, For the The optimal solution for each particle is is the global optimal solution, for The position of the particle at the time.

[0042] For each particle, the expression for updating the particle's position is: ; in, For the updated The position of the particle at the time.

[0043] According to the above-mentioned updated particle speed and position, iteration is performed, the new fitness of the particles is continuously calculated, and finally the global optimal solution, that is, the optimal heating mode and its parameter configuration, is output.

[0044] S4: Provide heating according to the selected heating mode and collect real-time operating parameters of the heating equipment.

[0045] Wherein, in step S4, the real-time operating parameters are the supply and return water pressure difference and the circulation pump frequency of the heating equipment.

[0046] Furthermore, the operating parameters collected in step S4 are actually parameters corresponding to the flow control mode on the boiler side of the heating facility, that is, pressure difference control and given frequency control, respectively. Therefore, the collected parameters are the supply and return water pressure difference and the circulation pump frequency. The pressure difference control is to set the pressure difference between the supply and return water on the boiler side, and to feed back the actual measured pressure difference. The given frequency control is to set the frequency of the circulation pump on the boiler side, and to feed back the actual frequency.

[0047] S5: The heating equipment is controlled according to the real-time operating parameters by a PID controller to complete the coordinated control of the heating facilities.

[0048] Wherein, step S5 specifically includes: When the heating mode is gas boiler heating, adjusting the operating power of the gas boiler; Furthermore, the PID controller can determine whether the current system needs to adjust the operating power of the gas boiler to maintain a constant pressure difference or meet the heating demand based on the changes in the supply and return water pressure difference, and then change the operating power of the gas boiler by adjusting the fuel supply of the gas boiler or adjusting the combustion efficiency. Specifically, based on the preset PID control parameters, the target power value that needs to be adjusted is obtained by calculation and sent to the gas boiler control system for execution.

[0049] When the heating mode is cogeneration heating, adjusting the operating power of the heating equipment of the cogeneration equipment and the heat-to-electricity ratio of the heating equipment; Furthermore, in addition to considering the supply and return water pressure difference, the control of the cogeneration heating facilities also needs to consider the heat-to-electricity ratio. The PID controller controls the operating power and heat-to-electricity ratio of the heating equipment at the same time by adjusting the steam flow, turbine load or generator output of the cogeneration equipment according to the supply and return water pressure difference and the power demand.

[0050] In addition, it is necessary to balance the production of electricity and heat by adjusting the heat-to-electricity ratio to ensure that while meeting the heating demand, the electricity demand can also be met or the optimal energy efficiency ratio is achieved. In this embodiment, a linear programming algorithm is used, that is, the model of the cogeneration system is simplified to a linear relationship, and linear programming can be used to find the optimal heat-to-electricity ratio.

[0051] When the heating mode is mixed heating of gas and cogeneration, the heating ratio of the gas boiler and the cogeneration equipment in the heating equipment, the operating power of the gas boiler, the operating power of the heating equipment of the cogeneration equipment, and the heat-to-electricity ratio of the heating equipment are adjusted.

[0052] In the mixed heating mode, the PID controller needs to consider the operating status and parameters of the gas boiler and the cogeneration equipment at the same time. By comparing the supply and return water pressure difference, the circulation pump frequency and the preset heating demand, the PID controller calculates the proportion of heating load that the gas boiler and the cogeneration equipment should bear respectively, that is, the heating ratio, and then coordinates the operating power and heat-to-electricity ratio of the two according to the adjustment methods of the above-mentioned gas boiler and cogeneration heating modes.

[0053] like Figure 2 As shown, the present invention also provides a clean energy heating facility coordinated control system, comprising: The first collection module 100 is used to collect historical heating data; Learning module 200: used to learn the historical heating data through the established dual learning layer to obtain fusion features; Selection module 300: for selecting a heating mode including gas boiler heating, cogeneration heating, and gas and cogeneration heating according to the fusion characteristics through a particle swarm optimization algorithm; The second acquisition module 400 is used to provide heat according to the selected heating mode and collect real-time operating parameters of the heating equipment; Control module 500: used to control the heating equipment according to the real-time operating parameters through a PID controller to achieve coordinated control of heating facilities.

[0054] Furthermore, the above-mentioned virtual control module also needs to be connected to the controller part of the heating facility, specifically, the power output by the control module is sent to the electrical control device of the heating facility.

[0055] The specific implementation method is to concentrate the PLC control and data monitoring of the boiler room and the cogeneration peak-shaving first station on a computing device. The device is equipped with three heating control modes, namely direct heating of the boiler room, direct heating of the cogeneration peak-shaving first station, and matching heating of the boiler room and the cogeneration peak-shaving first station.

[0056] When direct heating from the boiler room is selected, electrical control can be performed by receiving the control parameters of the above-mentioned control module, and a certain boiler can be selected to start. When direct heating from the boiler room is selected, it is necessary to close the electric butterfly valve of the cogeneration water supply and return main pipe, close the valve of the plate heat exchanger inlet and outlet on the boiler side, and open the boiler inlet and outlet valves.

[0057] Similarly, when direct heating is selected for the first station of cogeneration peak-shaving, electrical control is performed by receiving the control parameters of the above-mentioned control module, and the electric butterfly valve of the cogeneration supply and return water main is automatically opened. When direct heating is selected for the first station of cogeneration peak-shaving, it is necessary to stop the boiler, close the boiler inlet and outlet valves, and open the valve of the plate heat exchanger inlet and outlet on the boiler side.

[0058] When choosing the boiler room-cogeneration peak-shaving first station to match the heating supply, you can choose to start a certain boiler, the boiler will start automatically, and the electric butterfly valve of the cogeneration supply and return water main will open automatically. By selecting the number of boilers to start and the control of the cogeneration peak-shaving flow, matching and adjusting, the heating is completed together. When choosing the boiler room-cogeneration peak-shaving first station to match the heating supply, it is necessary to open the inlet and outlet valves of the starting boiler and the valves in and out of the plate heat exchanger on the boiler side, that is, part of the boiler side flow enters the boiler to be heated, and the other part of the boiler side flow enters the plate heat exchanger to be heated by the peak-shaving flow on the thermal power side.

[0059] The present invention provides a method and system for collaborative control of clean energy heating facilities. Through a dual learning layer, namely, a sliding average model and an autoregressive conditional heteroskedasticity model, historical heating data are learned, which can more accurately capture the periodicity, seasonality and volatility characteristics of the heating data, thereby improving the prediction accuracy and response speed of the heating system to heating demand. Secondly, a particle swarm optimization algorithm is adopted, which can automatically select the optimal heating mode, namely, gas boiler heating, cogeneration heating, and mixed heating, based on the fusion characteristics obtained by learning, to ensure that while meeting the heating demand, energy utilization efficiency is maximized and operating costs are reduced. The PID controller is also used to dynamically adjust the heating equipment according to real-time operating parameters, thereby realizing collaborative control between the gas boiler and the cogeneration equipment, and improving the stability and reliability of the entire heating system.

[0060] The present invention provides a method and system for collaborative control of clean energy heating facilities, which generally support multiple heating modes and their flexible switching, and can automatically adjust heating strategies and parameters according to changes in external environment and internal demand, thereby enhancing the flexibility and adaptability of the system, reducing unnecessary energy waste, improving energy utilization efficiency, and reducing operating costs, thereby bringing significant economic benefits to heating companies.

[0061] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for coordinated control of clean energy heating facilities, characterized in that: include: S1: Collect historical heating data; S2: establishing a dual learning layer, learning the historical heating data through the dual learning layer, and obtaining fusion features; S3: selecting a heating mode according to the fusion characteristics by using a particle swarm optimization algorithm, wherein the heating mode includes gas boiler heating, cogeneration heating, and gas and cogeneration heating; S4: Providing heating according to the selected heating mode and collecting real-time operating parameters of the heating equipment; S5: The heating equipment is controlled according to the real-time operating parameters by a PID controller to complete the coordinated control of the heating facilities.

2. A clean energy heating facility coordinated control method according to claim 1, characterized in that: The dual learning layer in step S2 includes: A first learning layer, wherein the first learning layer is a sliding average model; The second learning layer is an autoregressive conditional heteroskedasticity model.

3. A clean energy heating facility coordinated control method according to claim 2, characterized in that: Step S2 further comprises: S21: inputting the historical heating data into the dual learning layer; S22: learning the historical heating data through the first learning layer to obtain periodic features; S23: learning the periodic characteristics through the second learning process to obtain a fluctuation characteristic; S24: performing feature splicing on the periodic feature and the fluctuation feature to obtain a fusion feature.

4. A clean energy heating facility coordinated control method according to claim 1, characterized in that: Step S3 further comprises: S31: Encode multiple heating modes and corresponding parameter configurations to obtain a search space; S32: Establishing a fitness function according to the fusion feature; S33: Initializing a particle swarm, wherein a plurality of particles in the particle swarm search the search space according to the fitness function and output an optimal heating mode.

5. A clean energy heating facility coordinated control method according to claim 4, characterized in that: The parameter configuration in step S31 includes the heating power of the gas boiler, the heating power of the cogeneration, and the heat-to-electricity ratio of the cogeneration heating group.

6. A clean energy heating facility coordinated control method according to claim 1, characterized in that: In step S4, the real-time operating parameters are the supply and return water pressure difference and the circulation pump frequency of the heating equipment.

7. A clean energy heating facility coordinated control method according to claim 1, characterized in that: Step S5 specifically includes: When the heating mode is gas boiler heating, adjusting the operating power of the gas boiler; When the heating mode is cogeneration heating, adjusting the operating power of the heating equipment of the cogeneration equipment and the heat-to-electricity ratio of the heating equipment; When the heating mode is mixed heating of gas and cogeneration, the heating ratio of the gas boiler and the cogeneration equipment in the heating equipment, the operating power of the gas boiler, the operating power of the heating equipment of the cogeneration equipment, and the heat-to-electricity ratio of the heating equipment are adjusted.

8. A clean energy heating facility collaborative control system, used to execute a clean energy heating facility collaborative control method according to any one of claims 1 to 7, characterized in that: include: The first acquisition module: used to collect historical heating data; Learning module: used for learning the historical heating data through the established double learning layer to obtain fusion features; Selection module: used for selecting heating modes including gas boiler heating, cogeneration heating, and gas and cogeneration heating according to the fusion characteristics through a particle swarm optimization algorithm; The second acquisition module is used to provide heat according to the selected heating mode and collect real-time operating parameters of the heating equipment; Control module: used to control the heating equipment according to the real-time operating parameters through a PID controller to achieve coordinated control of heating facilities.

Citation Information

Patent Citations

  • Replenishment quantity prediction method and device, computer equipment and storage medium

    CN113283671A

  • Zone-side-oriented energy consumption optimization control method

    CN113328443A

  • Industrial boiler operation optimization method based on ensemble learning

    CN113887130A

  • Heat supply system coordination control method based on air source heat pump and building heat exchanger unit

    CN116576498A

  • Multi-source remote sensing image analysis method and system

    CN117523418A