Heat supply energy efficiency self-optimizing method and system

Abstract

The invention discloses a heat supply energy efficiency self-optimizing method and system. The method comprises the steps that an efficiency model of a heat pump unit is established; acquiring real-time monitoring data of the heat pump unit, and updating the efficiency model according to the real-time monitoring data; optimizing control input of the updated efficiency model in a future period of time according to a pre-constructed MPC algorithm; and defining multiple targets of operation of the heat pump unit, and searching control input meeting the requirements of the multiple targets through a pre-constructed optimization algorithm. The starting-up combination of the heat pump unit can be automatically optimized under different conditions, energy efficiency maximization and cost minimization are achieved, and stable operation of a heat supply system is guaranteed.

Description

Technical Field

[0001] The invention relates to a method and system for self-optimizing heating energy efficiency, and belongs to the field of industrial automation and intelligent control. Background Art

[0002] There are many types of heat pumps in the current heating system, such as water-cooled, air-cooled, magnetically suspended and screw-type, each with a different working efficiency curve. Due to changes in load, weather and other factors, it is necessary to intelligently control the startup combination of different models to adapt to these changes and achieve optimal energy efficiency. Summary of the invention

[0003] The present invention provides a method and system for self-optimization of heating energy efficiency, which solves the problems disclosed in the background technology and can automatically optimize the startup combination of heat pump units under different conditions, maximize energy efficiency, minimize costs, and ensure stable operation of the heating system.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for self-optimization of heating energy efficiency, comprising: Establish the efficiency model of heat pump unit; Acquire real-time monitoring data of the heat pump unit, and update the efficiency model according to the real-time monitoring data; Optimize the control input of the updated efficiency model in the future period according to the pre-built MPC algorithm to obtain the optimized control input; Define the multi-objective operation of the heat pump unit, and use the pre-built multi-objective optimization algorithm to find the control input that meets the multi-objective requirements among the optimized control inputs.

[0005] Furthermore, the efficiency model is: = · + ; in, is the efficiency of the j-th type unit, is the power of the ith performance parameter, and is the coefficient corresponding to the j-th type of unit, is the error term.

[0006] Furthermore, the real-time monitoring data of the heat pump unit are obtained, including power input Pj, outlet water temperature Toutj, ambient temperature Tenv and flow rate Fj.

[0007] Furthermore, the method for updating the efficiency model according to the real-time monitoring data includes: Establish a database to store real-time data, use exponential smoothing method to perform preliminary analysis, and update the predicted efficiency of the efficiency model: ; in, It's time The predicted efficiency of the j-th type unit is: is the actual observation efficiency, is the smoothing constant, 0< <1.

[0008] Furthermore, the method for updating the efficiency model according to the real-time monitoring data includes: Use the ID3 algorithm to build a decision tree model to analyze real-time monitoring data and dynamically update the coefficients of the efficiency model: =f(Pj,Toutj,Tenv,Fj;θ); Among them, f represents the decision tree model and θ represents the model parameters.

[0009] Furthermore, the MPC algorithm is: ; in, is the stage cost function, is the final cost function, is the system status, is the control input, is the prediction time domain.

[0010] Furthermore, the stage cost function Used to evaluate the system performance under each control input u(t), ; in, is the weight of energy consumption cost, is the weight of the output bias, To control the weight of the effort.

[0011] Furthermore, the final cost function Used to evaluate the long-term performance of the system state at the end of the prediction horizon: ; in, is the stability weight, is the weight of energy efficiency.

[0012] Furthermore, the multi-objectives of the heat pump unit operation are defined, and the method of finding the control input that meets the multi-objective requirements through the pre-built optimization algorithm is as follows: The multiple objectives that define the operation of the heat pump unit include: minimizing energy consumption, maximizing energy efficiency, and stabilizing the outlet water temperature; Select genetic algorithm for multi-objective optimization; Set weights for different goals to balance their priorities: w=[ w 1, w 2,wi…, wm ]; Among them, wi is the weight of the i-th target, and m is the total number of units; Find the optimal control input that meets multiple objectives.

[0013] The second aspect of the present invention also provides a heating energy efficiency self-optimization system, comprising: Efficiency models, used to predict the energy efficiency of heat pump units; A real-time monitoring module, used to obtain real-time monitoring data of the heat pump unit and update the efficiency model according to the real-time monitoring data; An MPC algorithm module is used to optimize the control input of the updated efficiency model in the future according to the MPC algorithm; The multi-objective optimization module is used to define the multi-objectives of the heat pump unit operation and find the control input that meets the multi-objective requirements through the optimization algorithm.

[0014] The beneficial effects achieved by the present invention are: 1. Application of self-optimization algorithm: This system can dynamically adjust the startup combination of heat pump units according to real-time data and prediction models through self-optimization algorithm, so as to achieve energy efficiency optimization. This adaptive adjustment mechanism significantly reduces the dependence on manual operation.

[0015] 2. Improved automation level: The system improves the automation level through real-time monitoring and continuous updating of machine learning models, enabling the heating system to respond to environmental changes and load demands more intelligently.

[0016] 3. Enhanced operating efficiency: Through the model predictive control (MPC) algorithm and multi-objective optimization control strategy, the system can achieve refined control of the heat pump unit, optimize energy consumption and energy efficiency, and ensure the stability of the outlet water temperature.

[0017] 4. Flexibility and scalability: The system design takes into account the adaptability to different operating environments and conditions. It has good flexibility and scalability and can adapt to the needs of various heating scenarios.

[0018] 5. Environmental adaptability: The system can adapt to different operating environments, including different climatic conditions and load requirements, and achieve optimal energy efficiency in various environments through intelligent control strategies.

[0019] 6. Cost-effectiveness: By optimizing the startup combination and operating efficiency of the heat pump unit, the system helps to reduce energy consumption and operating costs, while improving energy utilization efficiency, achieving a win-win situation in economic and environmental benefits.

[0020] Through the above beneficial effects, the present invention not only improves the intelligence level of the heating system, but also provides an effective solution for achieving energy conservation and emission reduction and improving energy utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a schematic diagram of the process of the method for self-optimization of heating energy efficiency of the present invention; Figure 2 It is a simulation schematic diagram of the efficiency model in the present invention; Figure 3 It is a closed-loop control schematic diagram of the present invention; Figure 4 It is a schematic diagram of the MPC algorithm flow of the present invention; Figure 5 Schematic diagram of the multi-objective optimization algorithm of the present invention. DETAILED DESCRIPTION

[0022] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention. Example

[0023] like Figure 1 As shown, this embodiment provides a method for self-optimizing heating energy efficiency, comprising the following steps: Collect the performance parameters of the 𝑗th type of unit: power Pij ,in i From 1 to 𝑛.

[0024] Perform data cleansing, including: Outlier Removal: Use the IQR (interquartile range) method to identify and handle outliers.

[0025] Missing value imputation: Use mean or median to fill missing data.

[0026] Data standardization: Z-score standardization method was used to make the data have zero mean and unit variance.

[0027] For the 𝑗th type of unit, the following nonlinear efficiency model is established: = · + ; in, and It is the coefficient corresponding to the j-th type of unit and needs to be determined through data fitting.

[0028] The model parameters are estimated using nonlinear least squares. This method aims to minimize the error term The weighted sum of squares, that is, the optimization objective function: S = ,in, is the observed efficiency value of the j-th type of unit, and m is the total number of units.

[0029] Select the Levenberg-Marquardt optimization algorithm, which combines the features of gradient descent and Gauss-Newton optimization and is suitable for nonlinear problems.

[0030] The parameter update in the Levenberg-Marquardt algorithm is performed by the following formula: = − , where x is the parameter vector [ , ,..., , ], is the Jacobian matrix, is the regularization parameter, is the identity matrix, is the residual vector.

[0031] Use simulation software (such as MATLAB / Simulink) to input different power Pij values ​​according to the determined parameter values ​​and run the simulation model.

[0032] The performance metric is defined as the root mean square error (RMSE) to quantify the difference between the model prediction and the actual observation: RMSE = ,in, is the efficiency value predicted by the model.

[0033] Use cross-validation methods, such as k-fold cross-validation, to assess the generalization ability of the model.

[0034] If the system contains multiple types of units, the efficiency models of each type of unit need to be superimposed to form a comprehensive efficiency model. The superposition principle is based on the fact that the sum of the efficiencies of all units is equal to the total efficiency of the system.

[0035] For all units, calculate the efficiency contribution of each type of unit, and then sum them up to get the total system efficiency: = ).

[0036] like Figure 2As shown, in the simulation software, the power distribution of the entire system is input according to the superimposed efficiency model to perform system-level simulation.

[0037] Real-time monitoring of the following points: power input Pj, water outlet temperature Toutj, ambient temperature Tenv, flow rate Fj.

[0038] Establish a database to store real-time data, and use exponential smoothing methods to perform preliminary analysis and update forecast efficiency: ; in, It's time The predicted efficiency of the j-th type unit is: is the actual observation efficiency, is the smoothing constant (0< <1).

[0039] Use the ID3 algorithm to build a decision tree model to predict and adjust the efficiency model: Select key features that affect efficiency based on real-time monitoring data.

[0040] Including normalization, noise removal, etc.

[0041] The ID3 algorithm decision tree model is used to analyze real-time monitoring data and dynamically update the coefficients of the efficiency model: =f(Pj,Toutj,Tenv,Fj;θ); Among them, f represents the decision tree model and θ represents the model parameters.

[0042] Based on the updated efficiency model and the outlet water temperature feedback, the model predictive control (MPC) algorithm is used to dynamically adjust the startup combination: the MPC algorithm is designed to optimize the control inputs in the future period to achieve the desired system performance.

[0043] like Figure 3 As shown, a closed-loop control system is implemented to automatically adjust the operating parameters of the heat pump unit according to the real-time monitoring data and the prediction results of the efficiency model: adjust the input power, change the flow rate or switch the heat pump unit to respond to environmental changes and load demands.

[0044] like Figure 4 As shown in the figure, a model predictive control (MPC) algorithm is designed to achieve dynamic adjustment of the heat pump unit. The MPC algorithm optimizes the control input in the future based on the prediction model and current operating conditions to achieve the desired system performance. The objective function is defined as: ,in, is the stage cost function, is the final cost function, is the system status, is the control input, is the prediction time domain.

[0045] Apply the MPC algorithm to the system and dynamically adjust the startup combination of the units based on real-time data and prediction models. The specific steps include: Collect current system status and control input data.

[0046] Use the MPC algorithm to calculate the optimal sequence of future control inputs.

[0047] Apply the calculated optimal control input to the heat pump unit.

[0048] System Status Including the operating parameters of the heat pump unit, such as power input, water outlet temperature, ambient temperature and flow rate.

[0049] Control Input Includes adjustable parameters, such as the on / off status of the heat pump unit, power setting, flow control, etc.

[0050] The stage cost function 𝐿 is used to evaluate each control input The system performance under the condition of , usually includes energy consumption, deviation cost and control effort, etc.: ; in, , and are the weights of energy cost, output deviation and control effort respectively.

[0051] Final cost function Used to evaluate the long-term performance of the system state at the end of the prediction horizon: ; in, and are the weights of stability and energy efficiency respectively.

[0052] Using real-time monitoring data, the MPC algorithm continuously performs optimization calculations, generates control instructions, and ensures optimal system performance through feedback adjustments.

[0053] Regularly evaluate the performance of the MPC algorithm, including optimization accuracy, computational efficiency, and system response speed, and make necessary adjustments based on the evaluation results.

[0054] like Figure 5 As shown in the figure, multiple objectives of heat pump unit operation are defined, including minimizing energy consumption, maximizing energy efficiency, stabilizing outlet water temperature, etc.

[0055] A genetic algorithm is selected for multi-objective optimization, which is suitable for dealing with complex problems with multiple conflicting objectives.

[0056] Set weights for different goals to balance their priorities:

[0057] in, It is The weight of the target, and wi ≥0 and .

[0058] Run the optimization algorithm to find the optimal startup combination that meets multiple objectives. The optimization process includes: Individual chromosome representations are determined, each chromosome representing a potential combination of unit startup and parameter settings.

[0059] Design the algorithm fitness function, combine the target weight and system performance indicators, and evaluate the fitness of each individual.

[0060] The population is iteratively optimized through selection, crossover and mutation operations, gradually approaching the optimal solution.

[0061] Apply the optimization results to the actual control strategy to achieve refined adjustments: adjust the operating parameters of the heat pump unit, such as input power, flow rate, etc., according to the optimization results.

[0062] Regularly evaluate system performance after implementing optimization strategies, including energy consumption, energy efficiency, and outlet water temperature stability: collect performance data and use statistical methods to analyze optimization effects.

[0063] Based on performance evaluation results and user feedback, the control strategy is continuously optimized iteratively: adjusting target weights, optimizing algorithm parameters, and improving control logic.

[0064] Design an adaptive adjustment mechanism to enable the system to automatically adjust the optimization strategy according to real-time data and environmental changes: realize self-learning and self-adaptation of the algorithm, and improve the robustness and adaptability of the system. Example

[0065] This embodiment provides a heating energy efficiency self-optimization system, including: Efficiency models, used to predict the energy efficiency of heat pump units; A real-time monitoring module, used to obtain real-time monitoring data of the heat pump unit and update the efficiency model according to the real-time monitoring data; An MPC algorithm module is used to optimize the control input of the updated efficiency model in the future according to the MPC algorithm; The multi-objective optimization module is used to define the multi-objectives of the heat pump unit operation and find the control input that meets the multi-objective requirements through the optimization algorithm.

[0066] The testing, verification and iteration methods of this system are as follows: Simulation test: Before actual deployment, test the stability and performance of the system through a simulated environment.

[0067] Field testing: Deploy the system in a real environment for field testing and adjustments.

[0068] Performance evaluation: Collect test data and evaluate system performance to ensure that design requirements are met.

[0069] Iterative optimization: Continuously iterate and optimize the system based on test results and user feedback.

[0070] The maintenance and upgrade methods of this system are as follows: Regular maintenance: Check system components regularly to ensure they are functioning properly.

[0071] Software upgrade: System software is updated regularly based on technological development and user needs.

[0072] User feedback collection: Establish a user feedback mechanism to continuously collect user opinions for system improvement.

[0073] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

[0074] A computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by a computing device, the computing device executes a method for self-optimizing heating energy efficiency.

[0075] A computing device includes one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing a method for self-optimization of heating energy efficiency.

[0076] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0080] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the scope of the claims of the present invention to be approved.

Claims

1. A method for self-optimization of heating energy efficiency, characterized in that: include: Establish the efficiency model of heat pump unit; Acquire real-time monitoring data of the heat pump unit, and update the efficiency model according to the real-time monitoring data to obtain an updated efficiency model; Optimizing the control input of the updated efficiency model for a period of time in the future according to a pre-built MPC algorithm to obtain an optimized control input; Define the multi-objective operation of the heat pump unit, and use the pre-built multi-objective optimization algorithm to find the control input that meets the multi-objective requirements among the optimized control inputs.

2. The method for self-optimization of heating energy efficiency according to claim 1, characterized in that: The efficiency model is: = · + ; in, is the efficiency of the j-th type unit, is the power of the ith performance parameter, and is the coefficient corresponding to the j-th type of unit, is the error term.

3. The method for self-optimization of heating energy efficiency according to claim 1, characterized in that: The real-time monitoring data of the heat pump unit include power input Pj, water outlet temperature Toutj, ambient temperature Tenv and flow rate Fj.

4. The method for self-optimization of heating energy efficiency according to claim 1, characterized in that: The method for updating the efficiency model according to the real-time monitoring data includes: Establish a database to store real-time monitoring data, use exponential smoothing method to perform preliminary analysis, and update the predicted efficiency of the efficiency model: ； in, It's time The predicted efficiency of the j-th type unit is: is the actual observation efficiency, is the smoothing constant, 0< <1.

5. The method for self-optimization of heating energy efficiency according to claim 3, characterized in that: The method for updating the efficiency model according to the real-time monitoring data includes: Use the ID3 algorithm to build a decision tree model to analyze real-time monitoring data and dynamically update the coefficients of the efficiency model: =f(Pj,Toutj,Tenv,Fj;θ); in, is the actual observation efficiency, f represents the decision tree model, and θ represents the model parameters.

6. The method for self-optimization of heating energy efficiency according to claim 1, characterized in that: The MPC algorithm is: ； in, is the stage cost function, is the final cost function, is the system status, is the control input, is the prediction time domain.

7. The method for self-optimization of heating energy efficiency according to claim 6, characterized in that: The stage cost function 𝐿 is used to evaluate the system performance under each step of control input u(t), ； in, is the weight of energy consumption cost, is the weight of the output bias, To control the weight of the effort.

8. The method for self-optimization of heating energy efficiency according to claim 6, characterized in that: Final cost function Used to evaluate the long-term performance of the system state at the end of the prediction horizon: ； in, is the stability weight, is the weight of energy efficiency.

9. The method for self-optimization of heating energy efficiency according to claim 1, characterized in that: Define the multi-objective operation of the heat pump unit, and use the pre-built multi-objective optimization algorithm to find the control input that meets the multi-objective requirements in the optimized control input: The multiple objectives that define the operation of the heat pump unit include: minimizing energy consumption, maximizing energy efficiency, and stabilizing the outlet water temperature; Select genetic algorithm for multi-objective optimization; Set weights for different goals to balance their priorities: in=[ w 1, w 2,wi…, wm ]; Among them, wi is the weight of the i-th target, and m is the total number of units; Find the optimal control input that meets multiple objectives.

10. A heating energy efficiency self-optimization system, characterized in that: include: Efficiency model, used to provide feedback on the energy efficiency of the heat pump unit; A real-time monitoring module, used to obtain real-time monitoring data of the heat pump unit and update the efficiency model according to the real-time monitoring data; An MPC algorithm module is used to optimize the control input of the updated efficiency model in the future according to the MPC algorithm; The multi-objective optimization module is used to define the multi-objectives of the heat pump unit operation and find the control input that meets the multi-objective requirements through the optimization algorithm.

Images