CN117355710A - Method and device for controlling refrigeration equipment - Google Patents
Method and device for controlling refrigeration equipment Download PDFInfo
- Publication number
- CN117355710A CN117355710A CN202180098385.8A CN202180098385A CN117355710A CN 117355710 A CN117355710 A CN 117355710A CN 202180098385 A CN202180098385 A CN 202180098385A CN 117355710 A CN117355710 A CN 117355710A
- Authority
- CN
- China
- Prior art keywords
- model
- refrigeration
- cooling load
- models
- controlling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005057 refrigeration Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 53
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 17
- 230000004044 response Effects 0.000 claims abstract description 8
- 238000001816 cooling Methods 0.000 claims description 50
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 2
- 238000012417 linear regression Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 9
- 238000005259 measurement Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 238000005265 energy consumption Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
- F24F11/47—Responding to energy costs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P80/00—Climate change mitigation technologies for sector-wide applications
- Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides a method and a device for controlling refrigeration equipment, comprising the following steps: training one or more models using historical data of the refrigeration equipment, and determining a model from the one or more models based on training results; controlling an outlet chilled water temperature of the refrigeration appliance based at least in part on the determined model; determining whether to retrain; and in response to determining to retrain, retrain the one or more models using updated historical data of the refrigeration equipment and determine an updated model from the one or more models based on the retraining results.
Description
The present invention relates generally to refrigeration in engineering, and more particularly to a method and apparatus for controlling a refrigeration appliance.
Nowadays, refrigeration systems are widely deployed in manufacturing factories and building buildings on a global scale, and the refrigeration systems generally consume a large amount of energy and electric power, which is not beneficial to achieving the aims of energy conservation, emission reduction, low carbon emission, carbon neutralization and the like. How to make a refrigeration system meet the refrigeration requirement while minimizing the consumption of energy is a long-standing problem in the engineering world.
Thanks to the development of digitization and sensor technology, numerous algorithms driven by data and digital building energy systems have been created, which make it easier to monitor, analyze and optimize the various energy consumption links in the manufacturing process, thus enabling to exhibit portions or links that can provide energy savings.
At present, a class of optimization methods based on data driven refrigeration systems are directed to studying accurate models based on energy behavior to control and schedule components in a building to minimize the energy consumption of the building. For example, a global optimization architecture based on a data-driven refrigeration equipment power prediction model, and a cooling load prediction control through building energy consumption simulation and global optimization, etc. Such methods may provide a degree of energy savings by using a power prediction model built for the primary components of the refrigeration system, performing a global optimization of the power to be used by each primary component with the objective of minimizing the total power consumption of the refrigeration system, while the quality of the optimization results is generally highly dependent on the prediction model used and the search space, subject to meeting constraints such as required cold loads.
It is desirable to provide a more efficient and simple and easy method of optimizing a refrigeration system that enables further improvements in energy savings.
Disclosure of Invention
The following presents a simplified summary of one or more embodiments in order to provide a basic understanding of such embodiments. This summary is not an extensive overview of all contemplated embodiments, and is intended to neither identify key or critical elements of all embodiments nor delineate the scope of any or all embodiments. Its sole purpose is to present some concepts of one or more embodiments in a simplified form as a prelude to the more detailed description that is presented later.
In one aspect of the present disclosure, there is provided a method for controlling a refrigeration appliance, comprising: training one or more models using historical data of the refrigeration equipment, and determining a model from the one or more models based on training results; controlling an outlet chilled water temperature of the refrigeration appliance based at least in part on the determined model; determining whether to retrain; and in response to determining to retrain, retrain the one or more models using updated historical data of the refrigeration equipment and determine an updated model from the one or more models based on the retraining results.
In another aspect of the present disclosure, an apparatus for controlling a refrigeration device is provided, comprising a memory; and at least one processor coupled to the memory and configured to: training one or more models using historical data of the refrigeration equipment, and determining a model from the one or more models based on training results; controlling an outlet chilled water temperature of the refrigeration appliance based at least in part on the determined model; determining whether to retrain; and in response to determining to retrain, retrain the one or more models using updated historical data of the refrigeration equipment and determine an updated model from the one or more models based on the retraining results.
In another aspect of the present disclosure, a computer program product for controlling a refrigeration appliance is provided, comprising processor executable computer code for: training one or more models using historical data of the refrigeration equipment, and determining a model from the one or more models based on training results; controlling an outlet chilled water temperature of the refrigeration appliance based at least in part on the determined model; determining whether to retrain; and in response to determining to retrain, retrain the one or more models using updated historical data of the refrigeration equipment and determine an updated model from the one or more models based on the retraining results.
In another aspect of the disclosure, a computer readable medium is provided storing computer code for controlling a refrigeration appliance, which when executed by a processor causes the processor to: training one or more models using historical data of the refrigeration equipment, and determining a model from the one or more models based on training results; controlling an outlet chilled water temperature of the refrigeration appliance based at least in part on the determined model; determining whether to retrain; and in response to determining to retrain, retrain the one or more models using updated historical data of the refrigeration equipment and determine an updated model from the one or more models based on the retraining results.
Other aspects or variations of the disclosure will become apparent upon consideration of the following detailed description and the accompanying drawings.
Fig. 1 illustrates an exemplary block diagram of a refrigeration system 100 in accordance with one or more aspects of the present disclosure;
FIG. 2 is a flow chart illustrating an exemplary method 200 for controlling a refrigeration appliance according to one or more aspects of the present disclosure;
FIG. 3 is a flow diagram illustrating an exemplary method 300 for training one or more models in accordance with one or more aspects of the present disclosure;
FIG. 4 is a flow diagram illustrating an exemplary method 400 of controlling an outlet chilled water temperature of a refrigeration appliance based at least in part on a determined model, in accordance with one or more aspects of the present disclosure;
FIG. 5 is a flow diagram illustrating an exemplary method 500 for determining whether to retrain in accordance with one or more aspects of the present disclosure;
fig. 6 illustrates an example of a hardware implementation of an apparatus 600 for controlling a refrigeration device according to one or more aspects of the present disclosure.
Various embodiments are now described with reference to the drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be evident, however, that such embodiment(s) may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to facilitate describing one or more embodiments.
Fig. 1 illustrates an exemplary block diagram of a refrigeration system 100. The refrigeration system 100 may include a chiller 102, a cooling tower 106 in the external circulation 101, and an indoor air cooling apparatus 104 in the internal circulation 103. The internal circulation 103 may push chilled water from the chiller 102 to the indoor space of the building for air cooling. Chilled water may absorb heat from the building and return to the chiller 102 at a higher temperature. The external circulation 101 may push condensed water from the chiller 102 to the cooling tower 106 outdoors, the cooling tower 106 releasing heat to the outdoor environment, such that the cold water is returned to the chiller 102. The external circulation 101 may run independently of the internal circulation 103. The heat exchange between the inner cycle 103 and the outer cycle 101 may be performed by the refrigerator 102.
In one aspect of the present disclosure, the refrigeration system 100 may also include one or more sensors and a database for collecting and maintaining monitoring data from the one or more sensors. The one or more sensors may be used to monitor one or more parameters for the chiller 102, including chilled water outlet temperature at the water outlet of the chiller 102, return water temperature at the return water outlet of the chiller 102, and cold water flow and/or velocity in the internal cycle 103 of the refrigeration system 100. In another aspect of the present disclosure, the refrigeration system 100 may also include and/or utilize a centralized data platform.
In other aspects of the present disclosure, the refrigeration system 100 may also include one or more additional or alternative components.
The present disclosure provides a method for controlling a refrigeration appliance using a data-driven model to control one or more parameters of the refrigeration appliance, and the model for controlling is not fixed, and may vary according to changes in the external environment (e.g., external temperature) and/or the indoor environment (e.g., line arrangement). Compared to prior art and methods based on global optimization, which typically involve building a power prediction model for each main component of the refrigeration system or simulating the performance of the building energy consumption, the method proposed by the present disclosure omits the building process of the complex power prediction model, instead uses a prediction model for the cooling load, and by virtue of the variability of the model, increases the adaptability to the environment, thereby further improving the energy saving effect for the refrigeration system.
Fig. 2 is a flow diagram illustrating an exemplary method 200 for controlling a refrigeration appliance according to one or more aspects of the present disclosure. The method 200 may be implemented, for example, in the refrigeration system 100 shown in fig. 1. At step 202, one or more models are trained using historical data of the refrigeration equipment to determine a model from the one or more models. At step 204, the outlet chilled water temperature of the refrigeration appliance is controlled based at least in part on the model determined at step 202. In one aspect of the present disclosure, control of the refrigeration appliance based on the model determined at step 202 is a real-time control and does not require human involvement. At step 206, a determination is made as to whether retraining is to be performed and in response to determining that retraining is to be performed, a return is made to step 202 in which the one or more models are retrained using updated historical data of the refrigeration appliance to determine an updated model from the one or more models, or in response to determining that retraining is not to be performed, a return is made to step 204 in which control of the refrigeration appliance continues using the determined model.
In one aspect of the present disclosure, the refrigeration apparatus in method 200 may include a chiller 102 as shown in fig. 1. In another aspect of the disclosure, the historical data may include an external temperature for one or more periods of time and an actual cooling load corresponding to the one or more periods of time. For example, the historical data may include the external temperature values recorded per hour for the previous month, and the cooling load actually provided by the refrigeration appliance recorded per hour for that month. In one aspect of the present disclosure, the cooling load actually provided by the refrigeration appliance may be derived based on measurements monitored by one or more sensors disposed in the refrigeration system 100, for example, based on one or more of the following: the temperature of the chilled water at the water outlet of the chiller 102, the return water temperature at the return water inlet of the chiller 102, and the cold water flow and/or velocity in the internal cycle 103 of the refrigeration system 100. In one or more aspects of the disclosure, the historical data may be updated in months, for example, once a month. In other aspects of the disclosure, the historical data may be updated at longer or shorter periods than a month, or may be updated aperiodically. In another aspect of the present disclosure, the data utilized in the method 200 (e.g., historical data including actual cooling load and external temperature, etc.) may be based on a centralized data platform included in and/or coupled to the refrigeration system 100.
Fig. 3 is a flow diagram illustrating an exemplary method 300 for training one or more models in accordance with one or more aspects of the present disclosure. For example, method 200 may perform method 300 at step 202. At step 302, data received from, for example, a database in the refrigeration system 100 is preprocessed to generate historical data. In one example, preprocessing may include downsampling measurements of one or more sensors collected in a database to obtain downsampled measurements. In another example, preprocessing may include format conversion of measurements of one or more sensors collected in a database. In one aspect of the present disclosure, historical data may be generated by preprocessing such that measurements from one or more sensors having the same sampling rate and/or format can be used.
At step 304, one or more models are trained using the historical data generated at step 302. The historical data may be used as a training set and/or test set for training the model. In one aspect of the present disclosure, the external temperature and the actual cooling load of the previous period may be used as input features of the model, and the cooling load of the next period predicted by the model may be used as output of the model. In one example, the one or more models may include support vector regression, stochastic regression prediction, decision tree regression, ridge regression, gaussian process regression, linear regression, adaboost regression, gradient boost regression, and the like. In another aspect of the disclosure, one or more models may be trained and evaluated based on time series cross-validation.
At step 306, a model is determined from the one or more models based on the training results obtained at step 304. For example, the model with the smallest error may be selected from one or more models. In one example, the metric for measuring error may include a mean absolute error percentage (MAPE), expressed as:
wherein y is i Is the actual value of the current,is the prediction result.
In one or more aspects of the present disclosure, the method 300 may also be used to determine an updated model. In one example, determining the updated model may include selecting a model that is different from the current model, e.g., updating from the current support vector regression model to a stochastic regression prediction model. In another example, determining an updated model may include updating model parameters without updating the type of model (e.g., still using the current support vector regression model).
Fig. 4 is a flow diagram illustrating an exemplary method 400 of controlling an outlet chilled water temperature of a refrigeration appliance based at least in part on a determined model, in accordance with one or more aspects of the present disclosure. Method 400 may be performed at step 204 of method 200. At step 402, the cold load for the next period is predicted and output by the determined model using the external temperature and the actual cold load for the previous period as inputs. In one aspect of the present disclosure, the model used in step 402 may be determined by the method 300. In another aspect of the present disclosure, the external temperature of the last hour and the actual cooling load provided by the chiller 102 may be utilized at the current time to predict the cooling load to be provided by the chiller 102 for the next hour.
At step 404, a control command is generated to fuzzy control a set point of an outlet chilled water temperature of a refrigeration device, such as the chiller 102, based on a comparison of the predicted next period of cooling load and the next period of actual cooling load. In one aspect of the present disclosure, it is desirable to maintain a certain amount of cooling load in the refrigeration system 100 to meet the refrigeration requirements within the manufacturing plant and/or the building. However, as the external temperature and other factors change, the amount of power that needs to be consumed to provide the same cooling load may change, which provides opportunities for power savings and improved energy savings. For example, when the next period of cooling load predicted by the determined model based on the previous period of external temperature and the actual cooling load is greater than the next period of actual cooling load, generating a control instruction to increase the set point of the outlet chilled water temperature of the chiller 102 for a further next period of time to save unnecessary power consumption; alternatively, when the next period of cooling load predicted by the determined model based on the previous period of external temperature and the actual cooling load is less than the next period of actual cooling load, a control instruction to reduce the set point of the outlet chilled water temperature of the chiller 102 for a further next period of time is generated to ensure that the refrigeration demand can be met.
At step 406, a setpoint for the outlet chilled water temperature for a further next period of the chiller 102 is adjusted based on the control instructions generated at step 404. For example, the temperature of the outlet chilled water of the chiller 102 for a further period of time may be adjusted by adjusting a Programmable Logic Controller (PLC) for an outlet chilled water temperature set point of the chiller 102. In one example, the temperature of the outlet chilled water of the chiller 102 for the next hour may be increased or decreased in steps of 0.25 ℃ (degrees celsius) according to the control instructions. In one aspect of the present disclosure, the temperature of the chilled water at the outlet of the chiller 102 may be initially set at a predetermined set point and the water temperature may be adjusted over a range (e.g., 8 ℃ to 12 ℃).
At step 408, the actual cooling load for each period is calculated using the measurements monitored by one or more sensors disposed in the refrigeration system 100 and the calculated actual cooling load is used as input to step 402 and step 404 in the next cycle for the next period.
In one aspect of the present disclosure, steps 402 through 408 may be repeated at predetermined cycles (e.g., every hour) to achieve real-time control of the chiller 102. In other aspects of the present disclosure, steps 402 through 408 may also be repeated in an aperiodic fashion.
Fig. 5 is a flowchart illustrating an example method 500 for determining whether to retrain in accordance with one or more aspects of the present disclosure. Method 500 may be performed at step 206 of method 200. At step 502, an error between the cooling load of one or more periods predicted by the determined model and the actual cooling load corresponding to the one or more periods is calculated. In one example, one or more predicted values of the cooling load for one or more time periods (e.g., per hour) at step 402 in method 400 are compared to one or more actual values of the cooling load measured by the sensor for the one or more time periods at step 408 in method 400 to calculate an error between the model predicted value and the actual measured value. The error may be expressed as a mean absolute error percentage (MAPE). In one example, the error may be calculated periodically, e.g., once a month. In another example, the error may also be calculated aperiodically.
At step 504, the calculated error is compared to an error threshold (e.g., 5%) to determine whether to retrain. For example, when the calculated error is greater than the error threshold, it is determined that retraining is to be performed, and when the calculated error is less than or equal to the error threshold, it is determined that retraining is not to be performed to continue using the model determined by method 300.
It is assumed that with the method 400 shown in fig. 4, the actual cooling load for the k-1 period derived via step 408 is 1 ton (RT) and the actual cooling load for the k period is 0.8 ton (RT) and is used as input for step 402 and step 404 in the next cycle (i.e., for the k+1 period). At step 402, the determined model is used to predict a cooling load of 1.1 tons (RT) for the k-1 period based on the actual cooling load of 1 tons (RT) for the k-1 period and the outside temperature for the k-1 period. At step 404, since the predicted 1.1 cold ton (RT) for k-period is greater than the actual cold load 0.8 cold ton (RT) for k-period, a control command is generated to increase the outlet chilled water temperature. At step 406, the outlet chilled water temperature for the k+1 period is increased in steps of 0.25C in accordance with the control command. At step 408, the actual cooling load for the k+1 period obtained is measured with the sensor to be 0.7 ton (RT), and 0.8 ton (RT) and 0.7 ton (RT) are used as inputs to step 402 and step 404 in the next cycle (i.e., for the k+2 period). At step 402, a cooling load of 1.2 tons (RT) for the k+1 period is predicted using the determined model based on 0.8 tons (RT) and the outside temperature for the k period. At step 404, since the predicted 1.2-ton (RT) for the k+1 period is greater than the actual cooling load 0.7-ton (RT) for the k+1 period, a control command is generated to raise the outlet chilled water temperature. At step 406, the outlet chilled water temperature for the k+2 period is increased in steps of 0.25C in accordance with the control command. At step 408, the actual cooling load of the obtained k+2 period is measured with a sensor to be 0.6 cold ton (RT). Returning again to step 402, based on the actual cold load of 0.7 tons (RT) for the k+1 period and the outside temperature for the k+1 period, a cold load of 1.3 tons (RT) for the k+2 period is predicted using the determined model. The above example can be represented by table 1.
TABLE 1
Period k-1 | Period k | Period k+1 | Period k+2 |
Predicted value of cold load | 1.1 | 1.2 | 1.3 | |
Actual value of the cold load | 1 | 0.8 | 0.7 | 0.6 |
As can be seen from table 1, the relative error percentage between the actual value (0.8) and the predicted value (1.1) for the k period is about 38% (i.e., (1.1-0.8)/0.8), and the relative error percentage between the actual value (0.7) and the predicted value (1.2) for the k+1 period is 71% (i.e., (1.2-0.7)/0.7). The error for both periods has exceeded an error threshold (e.g., 5%). If the average relative error percentage exceeds the error threshold over a certain period of time (e.g., one month), this may mean that the currently used model is either more error-prone to predictions from changes in external temperature, etc., or no longer suitable for the currently changing environment. For example, in the example in table 1, possible situations include a faster rise in external temperature, so that the required chilled water temperature needs to be continuously reduced in order to provide the required cooling load. However, the outlet chilled water temperature of the k+1 and k+2 periods is even raised due to the inadaptability of the currently used model. Thus, when the calculated average error MAPE is greater than the error threshold, it is determined that retraining is to be performed to determine a more appropriate model, as described in method 500 of FIG. 5.
In one aspect of the disclosure, according to the examples in table 1, the method 300 may use updated historical data, e.g., actual cooling loads 1, 0.8, 0.7, 0.6RT including periods k-1, k, k+1, and k+2 and external temperatures corresponding to those periods, to retrain one or more models so that the updated models are better able to accommodate recent environmental changes than currently used models (which have greater predictive and actual value errors, e.g., 38% and 71%).
According to one or more aspects of the present disclosure, by performing one or more of the methods 200, 300, 400, and/or 500, historical data and external temperatures for the refrigeration equipment itself may be used to provide predictions of the cooling load, as well as by retraining the model, enabling the model to adapt to changing environments.
Fig. 6 illustrates an example of a hardware implementation of an apparatus 600 for controlling a refrigeration device according to one or more aspects of the present disclosure. The apparatus 600 for controlling a refrigeration device may include a memory 610 and at least one processor 620. The processor 620 may be coupled to the memory 610 and configured to perform one or more of the methods 200, 300, 400, and/or 500 described above with reference to fig. 2, 3, 4, and 5. The processor 620 may be a general purpose processor or may be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or other such configuration. The memory 610 may store input data, output data, data generated by the processor 620, and/or instructions executed by the processor 620.
The various operations, models, and networks described in connection with the present disclosure may be implemented as hardware, software executed by a processor, firmware, or any combination thereof. According to one or more aspects of the present disclosure, a computer program product for controlling a refrigeration appliance may include processor executable computer code for performing one or more of the methods 200, 300, 400, and/or 500 described above with reference to fig. 2, 3, 4, and 5. According to other aspects of the present disclosure, a computer readable medium may store computer code for controlling a refrigeration appliance, which when executed by a processor may cause the processor to perform one or more of the methods 200, 300, 400, and/or 500 described above with reference to fig. 2, 3, 4, and 5. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. Any connection is properly termed a computer-readable medium.
The previous description of the disclosure is provided to enable any person skilled in the art to make or use the various embodiments. Various modifications to the embodiments described above will be readily apparent to those skilled in the art, and the basic principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Thus, the scope of the claims is not intended to be limited to the embodiments disclosed herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
- A method for controlling a refrigeration appliance, comprising:training one or more models using historical data of the refrigeration equipment, and determining a model from the one or more models based on training results;controlling an outlet chilled water temperature of the refrigeration appliance based at least in part on the determined model;determining whether to retrain; andin response to determining to retrain, retrain the one or more models using updated historical data of the refrigeration equipment, and determine an updated model from the one or more models based on the retraining results.
- The method of claim 1, wherein the historical data comprises an outside temperature of one or more time periods and an actual cooling load corresponding to the one or more time periods, and wherein the updated historical data comprises an outside temperature of one or more time periods subsequent to the one or more time periods and an actual cooling load corresponding to one or more time periods subsequent to the one or more time periods.
- The method of claim 1, wherein the controlling further comprises:fuzzy control of a set point of an outlet chilled water temperature of the refrigeration appliance is based on a comparison between a next period of cooling load predicted by the determined model and an actual cooling load of the next period.
- The method according to claim 1, wherein:based on an error between the cold load of one or more periods predicted by the determined model and an actual cold load corresponding to the one or more periods, it is determined whether to retrain.
- The method of claim 3, wherein,increasing a set point of an outlet chilled water temperature for a further next period of the refrigeration appliance when the next period of cooling load predicted by the determined model is greater than the actual cooling load for the next period; or alternativelyWhen the next period of cooling load predicted by the determined model is less than the actual cooling load for the next period, the set point of the outlet chilled water temperature for a further next period of the refrigeration appliance is reduced.
- The method of claim 4, wherein the error comprises a mean absolute error percent (MAPE) between a cold load of one or more periods predicted by the determined model and an actual cold load corresponding to the one or more periods; and wherein,when the MAPE is greater than a threshold, it is determined that retraining is to be performed, and when the MAPE is less than or equal to the threshold, it is determined that retraining is not to be performed to continue using the determined model.
- The method of claim 1, wherein the one or more models comprise one or more of:support vector regression, stochastic regression prediction, decision tree regression, ridge regression, gaussian process regression, linear regression, adaboost regression.
- An apparatus for controlling a refrigeration device, comprising:a memory; andat least one processor coupled to the memory and configured to perform the method of any one of claims 1 to 7.
- A computer program product for controlling a refrigeration device, comprising processor executable computer code for performing the method of any of claims 1 to 7.
- A computer readable medium storing computer code for controlling a refrigeration device, which when executed by a processor causes the processor to perform the method of any one of claims 1 to 7.
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2021/095676 WO2022246627A1 (en) | 2021-05-25 | 2021-05-25 | Method and apparatus for controlling refrigerating device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117355710A true CN117355710A (en) | 2024-01-05 |
Family
ID=84228829
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202180098385.8A Pending CN117355710A (en) | 2021-05-25 | 2021-05-25 | Method and device for controlling refrigeration equipment |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN117355710A (en) |
WO (1) | WO2022246627A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118037266A (en) * | 2024-01-31 | 2024-05-14 | 北京纪新泰富机电技术股份有限公司 | Method, apparatus, device and computer readable medium for generating maintenance scheme of refrigerator |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170255864A1 (en) * | 2016-03-05 | 2017-09-07 | Panoramic Power Ltd. | Systems and Methods Thereof for Determination of a Device State Based on Current Consumption Monitoring and Machine Learning Thereof |
US20190187635A1 (en) * | 2017-12-15 | 2019-06-20 | Midea Group Co., Ltd | Machine learning control of environmental systems |
CN108171379B (en) * | 2017-12-28 | 2021-12-17 | 无锡英臻科技有限公司 | Power load prediction method |
CN108317683A (en) * | 2018-01-19 | 2018-07-24 | 四川斐讯信息技术有限公司 | A kind of prediction technique and system of indoor temperature and humidity |
CN109945402A (en) * | 2019-03-07 | 2019-06-28 | 东南大学 | A kind of central air conditioning water system power-economizing method |
CN110569363A (en) * | 2019-08-02 | 2019-12-13 | 深圳众赢维融科技有限公司 | Decision flow component generation method and device, electronic equipment and storage medium |
CN110567101A (en) * | 2019-08-14 | 2019-12-13 | 南京南瑞继保工程技术有限公司 | Water chiller high-energy-efficiency control method based on support vector machine model |
CN112577161B (en) * | 2019-09-30 | 2022-05-27 | 北京国双科技有限公司 | Air conditioner energy consumption model training method and air conditioner system control method |
CN111932015B (en) * | 2020-08-12 | 2023-06-16 | 武汉中电节能有限公司 | Prediction method and system for regional cooling and heating cold and heat load |
-
2021
- 2021-05-25 CN CN202180098385.8A patent/CN117355710A/en active Pending
- 2021-05-25 WO PCT/CN2021/095676 patent/WO2022246627A1/en active Application Filing
Also Published As
Publication number | Publication date |
---|---|
WO2022246627A1 (en) | 2022-12-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106920006B (en) | Subway station air conditioning system energy consumption prediction method based on ISOA-LSSVM | |
CN108317670B (en) | Refrigeration system energy-saving control method and system based on machine learning | |
CN108151253B (en) | Automatic compensation method for air supply temperature of variable air volume air conditioner | |
Yu et al. | Online tuning of a supervisory fuzzy controller for low-energy building system using reinforcement learning | |
CN113039506B (en) | Causal learning-based data center foundation structure optimization method | |
US11774122B2 (en) | Building control system with adaptive online system identification | |
US20160283844A1 (en) | Load predictor for a cooling system | |
CN115309603A (en) | Data center energy consumption prediction optimization method, system, medium and computing device | |
CN112413831A (en) | Energy-saving control system and method for central air conditioner | |
Deng et al. | Optimal control of chilled water system with ensemble learning and cloud edge terminal implementation | |
CN117355710A (en) | Method and device for controlling refrigeration equipment | |
KR20180138371A (en) | Method for evaluating data based models and conducting predictive control of capsule type ice thermal storage system using the same | |
Biemann et al. | Data Center HVAC Control Harnessing Flexibility Potential via Real-Time Pricing Cost Optimization Using Reinforcement Learning | |
CN113757922B (en) | Deep learning-based air conditioning system energy-saving control method, device and equipment and computer medium | |
CN116045461B (en) | Energy-saving control method and device for air-cooled air conditioner based on water supply and return temperature adjustment | |
CN117013520A (en) | Flexible load adjustable power evaluation method based on incremental learning | |
CN116578134A (en) | Universal base station temperature control method and system based on reinforcement learning | |
Vasisht et al. | Co-Design of Commercial Building HVAC using Bayesian Optimization | |
Yu | Ai chiller: an open IoT cloud based machine learning framework for the energy saving of building HVAC system via big data analytics on the fusion of bms and environmental data | |
CN114282445A (en) | Circulating water system operation optimization method and related equipment | |
IT202100004994A1 (en) | METHOD AND SYSTEM OF CONTROL OF A FLUIDIC PLANT | |
Gauthier-Clerc et al. | Operating data of a specific Aquatic Center as a Benchmark for dynamic model learning: search for a valid prediction model over an 8-hour horizon | |
CN117408170B (en) | Energy-saving predictive control method suitable for water cooling system of data center | |
CN117970986B (en) | Temperature and humidity control method, device and medium of cold and hot system | |
CN117366810B (en) | Air conditioning system control method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |