Energy-saving control method and device for refrigerating system and refrigerating system
By coupling the water-cooled and air-cooled systems to optimize parameter prediction, the problem of insufficient prediction accuracy in central air-conditioning group control is solved, and the energy-saving potential and the operating efficiency of the refrigeration system are improved.
Patent Information
- Application Number
- CN202310656460.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-05
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2043-06-05
AI Technical Summary
The existing central air conditioner group control energy-saving strategies have strong dependence on the prediction of refrigeration loads, and there are situations of overcooling or overheating, and the accuracy of prediction and control is poor, which affects the efforts to explore energy-saving potential.
By obtaining the mechanism model and comfort model associated with water-cooling systems and air-cooling systems, the model is coupled to obtain the fitness function, determine the boundary conditions and optimize parameters through heuristic algorithms to improve parameter prediction accuracy, and achieve global optimal energy saving and Comfort target.
The accuracy of the parameter prediction of the refrigeration system is improved, the energy-saving potential of the group control strategy is released, and the precise reflection and optimization of the operating conditions of the refrigeration system is achieved.
Smart Images

Figure CN119085079A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of refrigeration systems, for example, to an energy-saving control method and device for a refrigeration system, and a refrigeration system. Background Art
[0002] At present, building energy conservation is a hot issue in the context of dual carbon. The energy conservation of central air conditioners is a nonlinear optimization problem. Due to the variable operating conditions of central air conditioners and the uncertainty of the health of air conditioners, it is difficult to use a purely theoretical method to solve the optimal parameters for the energy conservation of central air conditioners.
[0003] To address the above issues, relevant technologies adopt the following group control strategy: preset conditional logic, real-time parameter detection through high-precision sensors, and corresponding logical judgments are executed according to a preset schedule to trigger a standardized process of increasing or decreasing the start and stop of machines.
[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:
[0005] The group control strategy adopted by related technologies is highly dependent on the prediction of cooling load, and there is a possibility of overcooling or overheating. The accuracy of predictive control is poor, which affects the exploration of energy-saving potential.
[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention
[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.
[0008] The embodiments of the present disclosure provide an energy-saving control method, device and refrigeration system for a refrigeration system, so as to improve the accuracy of parameter prediction and release the energy-saving potential of a group control strategy.
[0009] In some embodiments, the method includes: obtaining a mechanism model associated with a water cooling system and a comfort model associated with an air cooling system; coupling the mechanism model and the comfort model to obtain a fitness function; determining boundary conditions, and importing the boundary conditions into the fitness function to optimize parameters through a heuristic algorithm to obtain predicted parameters; and outputting the predicted parameters to the execution end.
[0010] In some embodiments, the device includes: a processor and a memory storing program instructions, and the processor is configured to execute the aforementioned energy-saving control method for a refrigeration system when running the program instructions.
[0011] In some embodiments, the refrigeration system includes: a refrigeration host; a water cooling system; an air cooling system; and, the energy-saving control device for the refrigeration system as described above is installed on the refrigeration host.
[0012] The energy-saving control method, device and refrigeration system for a refrigeration system provided by the embodiments of the present disclosure can achieve the following technical effects:
[0013] The disclosed embodiment obtains a mechanism model associated with the water cooling system and a comfort model associated with the air cooling system, respectively. The mechanism model and the comfort model are then coupled to obtain a fitness function. The energy-saving target of the water cooling system and the comfort target of the air cooling system can be considered globally to achieve global optimization. Then, the disclosed embodiment determines the boundary conditions, imports the fitness function of the boundary condition value, optimizes the parameters through a heuristic algorithm to obtain the predicted parameters, and outputs the predicted parameters to the execution end. In this way, for two different types of systems, their respective models are coupled to obtain a fitness function that accurately reflects the operating conditions of the refrigeration system, and the heuristic algorithm is used to accurately obtain the predicted parameters, thereby improving the accuracy of the parameter prediction executed by the execution end and releasing the energy-saving potential of the group control strategy.
[0014] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:
[0016] Figure 1 is a schematic diagram of an energy-saving control method for a refrigeration system provided by an embodiment of the present disclosure;
[0017] Figure 2 is a schematic diagram of another energy-saving control method for a refrigeration system provided by an embodiment of the present disclosure;
[0018] Figure 3 is a schematic diagram of another energy-saving control method for a refrigeration system provided by an embodiment of the present disclosure;
[0019] Figure 4 is a schematic diagram of another energy-saving control method for a refrigeration system provided by an embodiment of the present disclosure;
[0020] Figure 5 is a schematic diagram of another energy-saving control method for a refrigeration system provided by an embodiment of the present disclosure;
[0021] Figure 6 is an application schematic diagram provided by an embodiment of the present disclosure;
[0022] Figure 7 It is a schematic diagram of an energy-saving control device for a refrigeration system provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0023] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.
[0024] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.
[0025] Unless otherwise stated, the term "plurality" means two or more.
[0026] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.
[0027] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.
[0028] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.
[0029] The embodiment of the present disclosure provides a refrigeration system, including a water cooling system and an air cooling system. The water cooling system realizes refrigeration by performing heat exchange treatment on the input chilled water. The energy consumption of the water cooling system is much higher than that of the air cooling system. Therefore, the embodiment of the present disclosure is aimed at the water cooling system, and a mechanism model is constructed with energy saving as the goal. As an example, the optimization goal of the water cooling system is to minimize the power of the refrigeration host under the condition of meeting the preset cooling capacity conditions.
[0030] The air cooling system achieves cooling or heating by heat exchange with the air in the environment. The energy consumption of the air cooling system is much lower than that of the water cooling system. Therefore, the present disclosure implements the air cooling system and constructs a comfort model with comfort as the goal.
[0031] Based on the above refrigeration system, combined with Figure 1 As shown, the embodiment of the present disclosure provides an energy-saving control method for a refrigeration system, comprising:
[0032] S11, the processor obtains a mechanism model associated with the water cooling system and a comfort model associated with the air cooling system.
[0033] S12, processor coupling mechanism model and comfort model, obtain fitness function.
[0034] S13, the processor determines boundary conditions, and imports the boundary conditions into the fitness function to optimize parameters through a heuristic algorithm to obtain prediction parameters.
[0035] In this step, the heuristic algorithm includes a simulated annealing algorithm, a genetic algorithm or a particle swarm algorithm.
[0036] S14, the processor outputs the prediction parameters to the execution end.
[0037] The energy-saving control method for a refrigeration system provided by an embodiment of the present disclosure is adopted. The embodiment of the present disclosure obtains a mechanism model associated with a water cooling system and a comfort model associated with an air cooling system, respectively. Then the mechanism model and the comfort model are coupled to obtain a fitness function. The energy-saving target of the water cooling system and the comfort target of the air cooling system can be considered globally to achieve global optimization. Then, the embodiment of the present disclosure determines the boundary conditions, imports the fitness function of the boundary condition value, optimizes the parameters through a heuristic algorithm to obtain the predicted parameters, and outputs the predicted parameters to the execution end. In this way, for two different types of systems, their respective models are coupled to obtain a fitness function that accurately reflects the operating conditions of the refrigeration system, and the heuristic algorithm is used to accurately obtain the predicted parameters, thereby improving the accuracy of the parameter prediction executed by the execution end and releasing the energy-saving potential of the group control strategy.
[0038] It should be noted that the execution subject of the embodiment of the present disclosure may be configured in the refrigeration system, or may be configured in a server that is in communication with the refrigeration system, and the embodiment of the present disclosure does not make any specific limitation on this.
[0039] Optionally, the processor couples the mechanism model and the comfort model to obtain a fitness function, including:
[0040] calculate
[0041] Among them, TC and TP represent the comfort model and mechanism model respectively. qk TP qk They represent thermal comfort constant and total power constant respectively, fitness represents fitness function, and δ represents correction coefficient.
[0042] Thus, in order to realize the linkage optimization of the water cooling system and the air cooling system, the embodiment of the present disclosure couples the mechanism model and the comfort model, thereby realizing the linkage energy saving of the water cooling system and the air cooling system. In addition, in order to prevent the fitness function from having a denominator of zero when a better value is not obtained during the coupling process, the embodiment of the present disclosure sets a correction coefficient δ. In this way, the embodiment of the present disclosure can obtain a fitness function that accurately reflects the operating conditions of the refrigeration system by coupling the respective models, which is beneficial to improving the accuracy of the parameter prediction executed by the execution end and is beneficial to tapping the energy-saving potential of the refrigeration system.
[0043] Optionally, δ is 0.001%. It is understandable that δ may also be any other value less than 0.01%.
[0044] Optionally, combined Figure 2 As shown, the processor obtains a mechanism model associated with the water cooling system, including:
[0045] S21, the processor constructs a mapping relationship between the water cooling parameters of the cooling device and the power of the refrigeration host to obtain a benchmark mechanism model pool.
[0046] S22, the processor inputs the historical water cooling data of each cooling device into the benchmark mechanism model training corresponding to the benchmark mechanism model pool to obtain an alternative mechanism model. In this step, the water cooling data includes operating parameter data and control parameter data. Correspondingly, the historical water cooling data includes historical operating parameter data and historical control parameter data. Among them, the operating parameter data is obtained by collecting water cooling parameters by sensors.
[0047] S23, the processor selects the alternative mechanism model as the mechanism model when the alternative mechanism model meets the error accuracy.
[0048] In this way, the embodiment of the present disclosure constructs a mapping relationship between the water cooling parameters of the cooling device and the power of the refrigeration host. After obtaining the benchmark mechanism model pool, the historical water cooling data of each cooling device is input into the benchmark mechanism model training corresponding to the benchmark mechanism model pool to obtain an alternative mechanism model, thereby achieving full learning of the historical water cooling data. When the alternative mechanism model meets the error accuracy, the alternative mechanism model is selected as the mechanism model. In this way, the embodiment of the present disclosure achieves the purpose of constructing a mechanism model with energy saving as the goal for the water cooling system, which is conducive to improving the accuracy of subsequent parameter prediction.
[0049] Optionally, the processor determines that the candidate mechanism model satisfies the error accuracy in the following manner:
[0050] The processor obtains the current error of the candidate mechanism model.
[0051] The current error is less than or equal to the error precision.
[0052] Optionally, the processor inputs historical water cooling data of each cooling device into the benchmark mechanism model training corresponding to the benchmark mechanism model pool to obtain the candidate mechanism model, including:
[0053] When the model training is not incremental training, the processor extracts full data and test data from the historical water cooling data, and uses the benchmark mechanism model corresponding to the benchmark mechanism model pool to perform model training on the full data and test data respectively.
[0054] When the model training is incremental training, the processor randomly selects a target number of target historical water cooling data from the historical water cooling data, and inputs them into the model training of the benchmark mechanism model corresponding to the benchmark mechanism model pool.
[0055] In this way, for the mechanism model, after the amount of data accumulates to a certain extent, the full amount of data is used for model training. However, new data will be continuously generated later, and these new data carry the latest working condition information of the water cooling system. Therefore, it is necessary to include new data in model training. However, if new data is input into the benchmark mechanism model model training corresponding to the benchmark mechanism model pool each time, it will cause a waste of computing power and poor applicability in actual engineering. For this reason, in the embodiment of the present disclosure, when the model training is not incremental training, that is, when the model training is performed for the first time, the processor extracts full data and test data from the historical water cooling data respectively, and inputs full data and test data into the benchmark mechanism model for model training respectively, and disrupts full data and test data during the iteration process of the model training process. Ensure sufficient learning of historical water cooling data. In the embodiment of the present disclosure, when the model training is incremental training, that is, the historical water cooling data includes the latest data, the processor randomly selects a target number of target historical water cooling data from the historical water cooling data, and inputs it into the benchmark mechanism model model training corresponding to the benchmark mechanism model pool. In this way, the embodiments of the present disclosure perform differentiated model training for full data and incremental data, saving computing resources and improving deployability.
[0056] As an example, when the model training is not incremental training, the total amount of data M of full data and test data extracted by the processor from the historical water cooling data.
[0057] In the case where the model training is incremental training, the processor randomly selects a target number of target historical water cooling data from the historical water cooling data, and inputs them into the benchmark mechanism model training corresponding to the benchmark mechanism model pool, including:
[0058] The target number is N×M. N≥3. Preferably, N is 5, 7 or 10. It is understandable that the specific value of N can also be determined according to the requirements of model training. The embodiments of the present disclosure are not specifically limited to this.
[0059] Optionally, the processor randomly selects a target number of target historical water cooling data from the historical water cooling data, and inputs the target historical water cooling data into the benchmark mechanism model pool for model training, including: the processor performs model training on the target historical water cooling data using a K-Fold verification method based on the benchmark mechanism model. In this way, the reliability of model training can be improved.
[0060] Optionally, the cooling device includes a cooling host, a freezing pump, a cooling pump, and a cooling tower. The processor constructs a mapping relationship between the water cooling parameters of the cooling device and the power of the cooling host to obtain a benchmark mechanism model pool, including:
[0061] The processor constructs a corresponding relationship between the chilled water outlet temperature, the cooling water inlet temperature, the cooling capacity of the refrigeration host, and the power of the refrigeration host to obtain a first benchmark mechanism model.
[0062] The processor constructs a correspondence between the operating frequency of the freezing pump, the operating frequency of the cooling pump, the wind speed of the cooling tower, the operating frequency of the cooling tower, the outdoor ambient temperature and humidity, and the power of the refrigeration host to obtain a second benchmark mechanism model.
[0063] The processor constructs a corresponding relationship between the freezing flow rate and the freezing water temperature difference of the freezing pump and the cooling capacity of the refrigeration host to obtain a third reference mechanism model.
[0064] The processor constructs a corresponding relationship between the cooling flow rate of the cooling pump, the cooling water temperature difference and the cooling amount to obtain a fourth reference mechanism model.
[0065] The reference mechanism model pool includes a first reference mechanism model, a second reference mechanism model, a third reference mechanism model and a fourth reference mechanism model. The cooling capacity is the sum of the cooling capacity and the power of the refrigeration host.
[0066] Thus, for the refrigeration host, the main factors affecting its power include the chilled water outlet temperature, the cooling water inlet temperature and the refrigeration capacity of the refrigeration host. To this end, the embodiment of the present disclosure constructs the corresponding relationship between the chilled water outlet temperature, the cooling water inlet temperature and the refrigeration capacity and power of the refrigeration host. In addition, since the cooling tower will be affected by the external convective heat exchange intensity, in addition to the respective operating frequencies of the freezing pump, the cooling pump and the cooling tower, the wind speed of the cooling tower and the outdoor environmental temperature and humidity will also affect the power of the refrigeration host. Therefore, the embodiment of the present disclosure constructs the corresponding relationship between the operating frequency of the freezing pump, the operating frequency of the cooling pump, the wind speed of the cooling tower, the operating frequency of the cooling tower and the outdoor environmental temperature and humidity and the power of the refrigeration host. At the same time, from the perspective of energy conservation, there is an energy correlation between the refrigeration capacity of the refrigeration host and the freezing flow and the freezing water temperature difference. At the same time, there is also an energy relationship between the cooling capacity and the cooling flow of the cooling pump and the cooling water temperature difference. Therefore, the embodiment of the present disclosure constructs the corresponding relationship between the freezing flow rate and the freezing water temperature difference of the freezing pump and the cooling capacity of the refrigeration host, and constructs the corresponding relationship between the cooling flow rate and the cooling water temperature difference of the cooling pump and the cooling capacity. In summary, the embodiment of the present disclosure establishes a mapping relationship between the water cooling parameters of the cooling device and the power of the refrigeration host according to the correlation between different types of water cooling parameters and the correlation between different cooling devices, so as to obtain a benchmark mechanism model pool.
[0067] Optionally, the processor constructs a mapping relationship between the water cooling parameters of the cooling device and the power of the refrigeration host to obtain a reference mechanism model pool, further comprising:
[0068] The processor constructs a correspondence between the operating frequency of the freezing pump, the switch combination state of the freezing pump and the freezing flow rate of the freezing pump to obtain a fifth reference mechanism model.
[0069] The processor constructs a corresponding relationship between the operating frequency of the cooling pump, the switch combination state of the cooling pump and the cooling flow rate of the cooling pump to obtain a sixth reference mechanism model.
[0070] Among them, the benchmark mechanism model pool includes a first benchmark mechanism model, a second benchmark mechanism model, a third benchmark mechanism model, a fourth benchmark mechanism model, a fifth benchmark mechanism model and a sixth benchmark mechanism model.
[0071] In this way, in addition to the correlation between the above-mentioned different types of water cooling parameters and the correlation between different cooling devices, there is also a constraint relationship between the parameters of the freezing pump and the cooling pump. Specifically, there is a correlation between the freezing flow of the freezing pump and its operating frequency and its switch combination state. There is a correlation between the cooling flow of the cooling pump and its operating frequency and its switch combination state. Therefore, the embodiment of the present disclosure constructs the corresponding relationship between the operating frequency of the freezing pump, the switch combination state of the freezing pump and the freezing flow of the freezing pump, and the corresponding relationship between the operating frequency of the cooling pump, the switch combination state of the cooling pump and the cooling flow of the cooling pump for the freezing pump and the cooling pump. In this way, the benchmark mechanism model is further optimized.
[0072] In one embodiment, when the historical water cooling data includes the historical chilled water outlet temperature, the historical cooling water inlet temperature and the historical cooling capacity of the refrigeration host, the processor inputs the historical water cooling data of each cooling device into the benchmark mechanism model pool corresponding to the benchmark mechanism model training to obtain an alternative mechanism model, including: the processor inputs the historical chilled water outlet temperature, the historical cooling water inlet temperature and the historical cooling capacity of the refrigeration host into the first benchmark mechanism model training to obtain an alternative mechanism model corresponding to the aforementioned historical water cooling data.
[0073] In another embodiment, when the historical water cooling data includes the historical operating frequency of the refrigeration pump, the historical operating frequency of the cooling pump, the historical wind speed of the cooling tower, the historical operating frequency of the cooling tower and the historical outdoor ambient temperature and humidity, the processor inputs the historical water cooling data of each cooling device into the benchmark mechanism model pool corresponding to the benchmark mechanism model training to obtain an alternative mechanism model, including: the processor inputs the historical operating frequency of the refrigeration pump, the historical operating frequency of the cooling pump, the historical wind speed of the cooling tower, the historical operating frequency of the cooling tower and the historical outdoor ambient temperature and humidity into the second benchmark mechanism model to obtain an alternative mechanism model corresponding to the aforementioned historical water cooling data.
[0074] In another embodiment, when the historical water cooling data includes the historical refrigeration flow rate of the freezing pump and the historical temperature difference of the freezing water, the processor inputs the historical water cooling data of each cooling device into the benchmark mechanism model training corresponding to the benchmark mechanism model pool to obtain an alternative mechanism model, including: the processor inputs the historical refrigeration flow rate of the freezing pump and the historical temperature difference of the freezing water into the third benchmark mechanism model to obtain an alternative mechanism model corresponding to the aforementioned historical water cooling data.
[0075] When the historical water cooling data includes the historical cooling flow of the cooling pump and the historical temperature difference of the cooling water, or the historical water cooling data includes the historical operating frequency of the freezing pump, the historical on-off combination status of the freezing pump, or the historical water cooling data includes the historical operating frequency of the cooling pump, the historical on-off combination status of the cooling pump, the method for obtaining the alternative mechanism model can be referred to the previous description, and the embodiments of the present disclosure will not elaborate on this.
[0076] Optionally, combined Figure 3 As shown, the processor obtains a comfort model associated with the air cooling system, including:
[0077] S31, the processor obtains air cooling data of the air cooling system and obtains comfort rating information, the air cooling data including part or all of the unit set temperature, fresh air temperature, fresh air humidity, fresh air carbon dioxide concentration, indoor temperature, indoor humidity and indoor carbon dioxide concentration.
[0078] S32, the processor inputs the air cooling data and the comfort rating information into the baseline comfort model to obtain the comfort model.
[0079] In this step, the baseline comfort model can be a white box model or a black box model.
[0080] In this way, the purpose of building a comfort model with comfort as the goal is achieved, which is conducive to improving the accuracy of subsequent parameter predictions.
[0081] Optionally, the processor obtains comfort rating information, including: the processor obtains a database, and the database stores multiple evaluation indicators and weights corresponding to different evaluation indicators. As an example, the evaluation indicators include wind sensation coefficient, temporal uniformity, spatial uniformity, vertical temperature difference and PMV (Predicted Mean Vote). The weights corresponding to wind sensation, temporal uniformity, spatial uniformity, and vertical temperature difference are all 0.15, and the weight corresponding to PMV is 0.4.
[0082] Optionally, the processor obtains historical water cooling data or air cooling data, including:
[0083] The processor obtains data collected by different types of sensors and the data transmission type of each type of sensor.
[0084] When the data transmission type matches the standard type, the processor parses the data collected by the sensor to obtain data information and time information.
[0085] In this way, for the central air-conditioning refrigeration system, the refrigeration system is equipped with a variety of sensors, such as pipe temperature sensors, pressure sensors, air volume sensors, return air temperature sensors, return air humidity sensors, etc. With the long-term use of the refrigeration system, the refrigeration system will replace or add new sensors. The replaced or newly added sensors have different models, data transmission methods, and analysis methods from the original sensors. The information collected by the above-mentioned replaced or newly added sensors and the original sensors belongs to multi-source information. In order to reduce the difficulty of subsequent data call and processing, it is necessary to unify and integrate the multi-source information. To this end, the embodiment of the present disclosure obtains data collected by different types of sensors and their respective data transmission types, and when the data transmission type matches the standard type, it starts the data analysis operation to obtain data information and actual information, and performs data storage operations. In this way, it is conducive to subsequent data call and processing, and improves the speed of subsequent mechanism model and comfort model generation.
[0086] Optionally, when the data transmission type does not match the standard type, the processor stores the data transmission type in a standard rule base. The standard rule base includes the sensor type, data transmission type information, and manufacturer information of the sensor. It is understandable that the standard rule base may also include other information identifying sensor differences.
[0087] Optionally, the processor stores data information and time information, including: the processor stores data information and time information in a time series database according to the principle of time proximity. As an example, for the data returned at 12:45:41, the time information stored by the processor is 12:45:30. For the data returned at 12:45:52, the time information stored by the processor is 12:46:00. At the same time, the processor stores data information and time information, and also includes: the processor determines whether there are abnormal points or missing values in the data information. When the processor determines that there are abnormal points or missing values in the data information, the processor performs interpolation processing according to statistical principles. In this way, the neatness of the data in the time series database is guaranteed, which facilitates subsequent data calls.
[0088] Optionally, combined Figure 4 As shown, the processor determines the boundary conditions and imports the boundary conditions into the fitness function to optimize the parameters through the heuristic algorithm to obtain the prediction parameters, including:
[0089] S41, the processor obtains the predicted load at the next moment according to the control parameters input by the user.
[0090] S42, the processor determines a boundary condition.
[0091] S43, the processor optimizes the fitness function according to the predicted load at the next moment and the boundary conditions to obtain prediction parameters.
[0092] In this way, when the heuristic algorithm is used to predict the parameters of the refrigeration system, the principle is to optimize the parameters using the objective function, optimization parameters and boundary conditions. Based on this, the embodiment of the present disclosure first obtains the predicted load at the next moment according to the control parameters input by the user. Then the boundary conditions are determined. Finally, the fitness function is optimized according to the predicted load at the next moment and the boundary conditions to obtain the prediction parameters. In this way, the embodiment of the present disclosure uses the predicted load at the next moment as the input condition to achieve high-frequency regulation, which is more conducive to exploring the energy-saving potential of the group control strategy.
[0093] Optionally, the processor obtains the predicted load at the next moment according to the control parameters input by the user, including:
[0094] When the amount of cold data meets the data integrity condition, the processor predicts the load at the next moment using a single-index time series prediction algorithm. Optionally, the single-index time series prediction algorithm includes an AR (Auto-Regressive) algorithm, an MA (Moving Average) algorithm, and an ARIMA (Autoregressive Integrated Moving Average model) algorithm.
[0095] When the amount of cold data does not meet the data integrity condition, the processor predicts the load at the next moment using a deep neural network learning algorithm. Optionally, the deep neural network learning algorithm includes an LSTM (Long Short Term Memory) algorithm or an Informer algorithm.
[0096] When the amount of cold data is less than the upper limit threshold and greater than the lower limit threshold and there is missing data, the processor uses data clustering to predict the load at the next moment.
[0097] Among them, the cooling data includes historical water cooling data and air cooling data.
[0098] In this way, the accuracy of the load predicted directly affects the subsequent group control operations of the water cooling system and the air cooling system. To this end, the disclosed embodiment adopts different prediction strategies for different cooling data. When the data volume of the cooling data meets the data integrity condition, it indicates that the integrity of the cooling data is high. At this time, a deep neural network learning algorithm can be used for load prediction. When the data volume of the cooling data does not meet the data integrity condition, it indicates that the integrity of the cooling data is poor. At this time, a single indicator time series prediction algorithm can be used for load prediction. When the data volume of the cooling data is less than the upper limit threshold and greater than the lower limit threshold and there is missing data, data clustering can be used for load prediction. In this way, it is beneficial to improve the accuracy of load prediction.
[0099] Optionally, the processor determines whether the data volume of the cold data satisfies the data integrity condition in the following manner.
[0100] In the last H years, the amount of cooling data is greater than or equal to the upper limit threshold and is complete, with no missing data, and each cooling data has corresponding environmental parameters or device parameters. Where H is greater than or equal to 3 and less than or equal to 5.
[0101] Optionally, the processor determines that the data volume of the cold data does not satisfy the data integrity condition in the following manner.
[0102] In the last H years, the amount of cold data is less than the lower limit threshold and is incomplete.
[0103] Optionally, the processor determines that the amount of cold data is less than an upper quantity threshold and greater than a lower quantity threshold and there is missing data in the following manner:
[0104] In the last W years, the amount of cold data is less than the upper limit threshold and greater than the lower limit threshold, and there is missing data.
[0105] Wherein, W is greater than or equal to 1 and less than or equal to 3.
[0106] This will help improve the accuracy of load forecasting.
[0107] Optionally, combined Figure 5 As shown, the processor uses data clustering to predict the load at the next moment, including:
[0108] S51, the processor performs clustering processing on the daily cooling load sequence to obtain a daily reference load function, wherein the cooling load sequence represents the cooling capacity data with continuous time series.
[0109] S52: The processor obtains a daily environmental parameter aggregation value according to a daily reference load function.
[0110] S53, the processor builds an environmental model according to the daily environmental parameter aggregation values.
[0111] S54: The processor predicts the load at the next moment based on the environmental model.
[0112] In this way, for cold data with moderate data volume and missing data, the load at the next moment can be accurately predicted.
[0113] Optionally, the processor predicts the load at the next moment according to the environmental model, including:
[0114] The processor predicts the target load function for the day based on the environmental model.
[0115] The processor predicts the load at the next moment based on the target load function of the day.
[0116] Optionally, the execution end includes an edge executor. The processor outputs the prediction parameter to the execution end, including: the processor sends a control instruction to the edge executor so that the edge executor performs a corresponding control operation. The control instruction includes the prediction parameter. The edge executor includes an electronic device with execution capability. As an example, the edge executor is a host computer.
[0117] It should be noted that when the processor sends the control instruction to the edge executor, it also includes: the processor receives the correction plan sent by the professional. The processor corrects the prediction parameters according to the correction plan to obtain updated prediction parameters. In this way, by adding the correction strategy of the professional, the situation of inputting obviously abnormal prediction parameter values to the execution end is avoided.
[0118] In practical applications, such as Figure 6 As shown, the energy-saving control method for the refrigeration system specifically performs the following steps:
[0119] S101, the processor obtains historical operating parameter data and historical control parameter data, integrates the historical operating parameter data using a standard rule library, and stores the integrated historical operating parameter data and historical control parameter data in a time series database.
[0120] S102, the processor constructs a mapping relationship between the water cooling parameters of the cooling device and the power of the refrigeration host to obtain a benchmark mechanism model pool.
[0121] S103, the processor inputs the historical water cooling data of each cooling device into the reference mechanism model pool, uses the model training module to train the reference mechanism model corresponding to the water cooling data, obtains the alternative mechanism model, and selects the alternative mechanism model as the mechanism model when the alternative mechanism model meets the error accuracy. The historical water cooling data includes historical operation parameter data and historical control parameter data.
[0122] S104, the processor obtains air cooling data of the air cooling system and obtains comfort rating information, the air cooling data including part or all of the unit set temperature, fresh air temperature, fresh air humidity, fresh air carbon dioxide concentration, indoor temperature, indoor humidity and indoor carbon dioxide concentration.
[0123] S105, the processor inputs the air cooling data and the comfort rating information into the baseline comfort model to obtain the comfort model.
[0124] S106, the processor coupling mechanism model and the comfort model are used to obtain a fitness function (ie, an objective function).
[0125] S107, the processor determines the boundary conditions and obtains the predicted load at the next moment, and then optimizes the fitness function according to the optimization solver, the predicted load at the next moment and the boundary conditions to obtain the prediction parameters.
[0126] S108, the processor outputs the prediction parameters to the execution end.
[0127] Combination Figure 7 As shown, an embodiment of the present disclosure provides an energy-saving control device for a refrigeration system, including a processor (processor) 400 and a memory (memory) 401. Optionally, the device may also include a communication interface (Communication Interface) 402 and a bus 403. Among them, the processor 400, the communication interface 402, and the memory 401 can communicate with each other through the bus 403. The communication interface 402 can be used for information transmission. The processor 400 can call the logic instructions in the memory 401 to execute the energy-saving control method for the refrigeration system of the above embodiment.
[0128] In addition, the logic instructions in the memory 401 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.
[0129] The memory 401 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 400 executes the function application and data processing by running the program instructions / modules stored in the memory 401, that is, the energy-saving control method for the refrigeration system in the above embodiment is implemented.
[0130] The memory 401 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 401 may include a high-speed random access memory and may also include a non-volatile memory.
[0131] The embodiments of the present disclosure provide a refrigeration system, including: a refrigeration main unit, a water cooling system, an air cooling system, and the above-mentioned energy-saving control device for the refrigeration system. The energy-saving control device for the refrigeration system is installed in the refrigeration main unit. The installation relationship described here is not limited to placement inside the product, but also includes installation connections with other components of the product, including but not limited to physical connections, electrical connections, or signal transmission connections. It can be understood by those skilled in the art that the energy-saving control device for the refrigeration system can be adapted to a feasible product main body, thereby realizing other feasible embodiments.
[0132] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the energy-saving control method for a refrigeration system.
[0133] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.
[0134] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes, or a transient storage medium.
[0135] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.
[0136] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.
[0137] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.
[0138] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.
Claims
1. An energy-saving control method for a refrigeration system, characterized in that: include: Obtaining the mechanism model associated with the water cooling system and the comfort model associated with the air cooling system; Couple the mechanism model and the comfort model to obtain the fitness function; Determine boundary conditions and import them into the fitness function to optimize parameters through heuristic algorithms to obtain prediction parameters; Output the prediction parameters to the execution end.
2. The method according to claim 1, characterized in that The coupling mechanism model and the comfort model are used to obtain a fitness function, including: calculate Among them, TC and TP represent the comfort model and mechanism model respectively. qk TP qk They represent thermal comfort constant and total power constant respectively, fitness represents fitness function, and δ represents correction coefficient.
3. The method according to claim 1, characterized in that The obtaining of the mechanism model associated with the water cooling system comprises: Construct the mapping relationship between the water cooling parameters of the cooling device and the power of the refrigeration host to obtain the benchmark mechanism model pool; Inputting historical water cooling data of each cooling device into the benchmark mechanism model training corresponding to the benchmark mechanism model pool to obtain an alternative mechanism model; When the alternative mechanism model meets the error accuracy, the alternative mechanism model is selected as the mechanism model.
4. The method according to claim 3, characterized in that The inputting of historical water cooling data of each cooling device into the benchmark mechanism model corresponding to the benchmark mechanism model pool for model training to obtain the candidate mechanism model includes: When the model training is not incremental training, full data and test data are extracted from the historical water cooling data, and the benchmark mechanism model corresponding to the benchmark mechanism model pool is used to perform model training on the full data and the test data respectively; When the model training is incremental training, a target number of target historical water cooling data is randomly selected from the historical water cooling data and input into the model training of the benchmark mechanism model corresponding to the benchmark mechanism model pool.
5. The method according to claim 3, characterized in that: The cooling device includes a cooling host, a freezing pump, a cooling pump and a cooling tower. The mapping relationship between the water cooling parameters of the cooling device and the power of the cooling host is constructed to obtain a benchmark mechanism model pool, including: Constructing the corresponding relationship between the chilled water outlet temperature, the cooling water inlet temperature, the refrigeration capacity of the refrigeration host and the power of the refrigeration host to obtain the first benchmark mechanism model; Construct the corresponding relationship between the operating frequency of the refrigeration pump, the operating frequency of the cooling pump, the wind speed of the cooling tower, the operating frequency of the cooling tower, the outdoor environmental temperature and humidity, and the power of the refrigeration host to obtain the second benchmark mechanism model; The corresponding relationship between the freezing flow rate and the freezing water temperature difference of the freezing pump and the cooling capacity of the refrigeration host is constructed to obtain the third benchmark mechanism model; The corresponding relationship between the cooling flow rate of the cooling pump, the cooling water temperature difference and the cooling amount is constructed to obtain the fourth benchmark mechanism model.
6. The method according to claim 5, characterized in that The mapping relationship between the water cooling parameters of the cooling device and the power of the refrigeration host is constructed to obtain a benchmark mechanism model pool, and further includes: Constructing the corresponding relationship between the operating frequency of the freezing pump, the switch combination state of the freezing pump and the freezing flow rate of the freezing pump to obtain the fifth benchmark mechanism model; The corresponding relationship between the operating frequency of the cooling pump, the switch combination state of the cooling pump and the cooling flow rate of the cooling pump is constructed to obtain the sixth reference mechanism model.
7. The method according to claim 1, characterized in that The obtaining of the comfort model associated with the air cooling system comprises: Obtaining air cooling data of the air cooling system and comfort rating information, the air cooling data including part or all of the unit set temperature, fresh air temperature, fresh air humidity, fresh air carbon dioxide concentration, indoor temperature, indoor humidity and indoor carbon dioxide concentration; Input air cooling data and comfort rating information into the baseline comfort model to obtain a comfort model.
8. The method according to any one of claims 1 to 7, characterized in that: The step of determining boundary conditions and importing the boundary conditions into the fitness function to optimize parameters through a heuristic algorithm to obtain prediction parameters includes: According to the control parameters input by the user, the predicted load at the next moment is obtained; Determine boundary conditions; The fitness function is optimized according to the predicted load at the next moment and the boundary conditions to obtain the prediction parameters.
9. The method according to claim 8, characterized in that The step of obtaining the predicted load at the next moment according to the control parameters input by the user includes: When the amount of cold data meets the data integrity condition, the single-index time series prediction algorithm is used to predict the load at the next moment; When the amount of cold data does not meet the data integrity condition, a deep neural network learning algorithm is used to predict the load at the next moment; When the amount of cold data is less than the upper limit threshold and greater than the lower limit threshold and there is missing data, data clustering is used to predict the load at the next moment.
10. An energy-saving control device for a refrigeration system, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the energy-saving control method for a refrigeration system according to any one of claims 1 to 9 when running the program instructions.
11. A refrigeration system, characterized in that: include: Refrigeration host; Water cooling system; Air cooling system; as well as, The energy-saving control device for a refrigeration system according to claim 10 is installed in the refrigeration host.
Citation Information
Patent Citations
Comprehensive energy system double-layer optimization method based on dual-mode heat pump energy storage coordination
CN111768032A
Energy scheduling method of integrated energy system
CN114169800A
General reverse calculation method applied to high-end equipment material design optimization
CN114970307A
Chilled water energy-saving apparatus of cental air conditioner
CN1598426A
Low-cost commissioning method for the air-conditioning systems in existing large public buildings
US20210123625A1
