Energy efficiency evaluation method, device, system, apparatus and storage medium
By building and training a model, the energy efficiency ratio is calculated using historical operating condition datasets of chiller units. This solves the problem that existing technologies cannot accurately evaluate the energy efficiency of chiller units in real time, and realizes real-time energy efficiency monitoring and evaluation without the need for a water flow meter, thus simplifying the energy efficiency evaluation process.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGDONG MIDEA WHITE HOME APPLIANCE TECH INNOVATION CENT CO LTD
- Filing Date
- 2022-12-12
- Publication Date
- 2026-07-10
AI Technical Summary
Existing technologies cannot accurately assess the energy efficiency of chiller units in real time, especially in refrigeration rooms with multiple chiller units where the energy efficiency of a single chiller unit cannot be obtained. Furthermore, traditional assessment methods require manual adjustment of operating conditions, leading to inaccurate assessments.
By acquiring historical operating condition datasets of chiller units, an initial model is constructed, an initial ideal current percentage is calculated, and the energy efficiency ratio is calculated in combination with the actual current percentage. Alternatively, the initial model can be trained to obtain an updated model, thereby achieving real-time energy efficiency assessment without the need for a water flow meter.
It enables real-time monitoring and evaluation of chiller unit energy efficiency without the need to install a water flow meter. The method is simple and quick, and can accurately obtain the current energy efficiency ratio of each chiller unit.
Smart Images
Figure CN116068304B_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of air conditioning technology, and in particular relates to an energy efficiency assessment method, apparatus, system, equipment and storage medium. Background Technology
[0002] Currently, obtaining the energy efficiency of air conditioning chiller units requires installing water flow meters and supply and return water temperature sensors on the chilled water pipes. After measuring the chiller unit's load, the energy efficiency is calculated by dividing the load by the power, enabling real-time monitoring of the chiller unit's energy consumption. If multiple chillers are installed in the chiller room, the water flow meter is often installed on the main chilled water pipe, monitoring the total chilled water flow, the total load of the chiller room, and the total energy efficiency, but not the energy efficiency of a single chiller unit.
[0003] The method for evaluating the energy efficiency of chiller units involves comparing their energy efficiency with national standards or the standards of the Air-Conditioning, Heating, and Refrigeration Institute (AHRI) in the United States. However, the energy efficiency of chiller units is closely related to their operating conditions. If the operating conditions of the chiller unit are inconsistent with those in the standard, this evaluation method is inaccurate. Alternatively, the operating conditions of the chiller unit can be adjusted to match those in the product catalog, and the current energy efficiency can be compared with the energy efficiency listed in the catalog. However, since the actual operating conditions of chiller units often differ from those in the product catalog, this method requires manual adjustment of the chiller unit's operating conditions and therefore cannot provide real-time evaluation of the chiller unit's energy efficiency. Summary of the Invention
[0004] This application aims to at least partially address one of the technical problems in the related art. Therefore, one objective of this application is to provide an energy efficiency assessment method, apparatus, system, device, and storage medium.
[0005] To address the aforementioned technical problems, embodiments of this application provide the following technical solutions:
[0006] An energy efficiency assessment method, comprising:
[0007] Obtain historical operating condition datasets and process the historical operating condition datasets to obtain target operating condition datasets;
[0008] Based on the target working condition dataset, the reference conditions are calculated.
[0009] If the reference conditions do not meet the preset conditions, the initial ideal current percentage is calculated based on the initial model, and the initial energy efficiency ratio is calculated based on the actual current percentage and the initial ideal current percentage.
[0010] If the reference value does not meet the preset conditions, the initial model is trained based on the target working condition dataset to obtain an updated model.
[0011] Optionally, the historical operating condition dataset includes first historical operating condition data of the condenser, second historical operating condition data of the evaporator, operating status data of the chiller unit, and cumulative operating time of the chiller unit.
[0012] Optionally, the step of calculating the reference conditions based on the target working condition dataset includes:
[0013] Based on the initial model, the target operating condition data is identified to obtain a first sub-reference condition; based on the cumulative operating time of the chiller unit, a second sub-reference condition is obtained; based on the operating status data of the chiller unit, a third sub-reference condition is obtained; wherein, the reference conditions include the first sub-reference condition, the second sub-reference condition, and the third sub-reference condition;
[0014] The first sub-reference condition is judged based on the first sub-preset condition; the second sub-reference condition is judged based on the second sub-preset condition; and the third sub-reference condition is judged based on the third sub-preset condition; wherein, the preset condition includes the first sub-preset condition, the second sub-preset condition, and the third sub-preset condition.
[0015] Optionally, if the reference condition does not meet the preset condition, it includes:
[0016] If any one of the following exists: the first sub-reference condition does not satisfy the first sub-preset condition, the second sub-reference condition does not satisfy the second sub-preset condition, or the third sub-reference condition does not satisfy the third sub-preset condition, then the reference condition does not satisfy the preset condition.
[0017] Optionally, if the reference condition does not meet the preset condition, it includes:
[0018] If the first sub-reference condition satisfies the first sub-preset condition, the second sub-reference condition satisfies the second sub-preset condition, and the third sub-reference condition satisfies the third sub-preset condition, then the reference condition does not satisfy the preset condition.
[0019] Optionally, training the initial model based on the training condition dataset to obtain an updated model includes:
[0020] The initial model is trained based on the training condition dataset to obtain a trained model;
[0021] The trained model is tested based on the test condition dataset to obtain the test accuracy of the trained model;
[0022] The training model is validated based on the test accuracy. If the validation is successful, the updated model is obtained based on the training model.
[0023] Optionally, the step of validating the trained model based on the test accuracy includes:
[0024] The test accuracy is compared with the accuracy threshold; at the same time, the initial accuracy of the initial model is obtained, and the absolute value of the difference between the initial accuracy and the test accuracy is obtained, and the absolute value of the difference is compared with the difference threshold.
[0025] If the test accuracy is greater than the accuracy threshold and the absolute value of the difference is less than the difference threshold, then the verification is successful.
[0026] Embodiments of this application also provide an energy efficiency assessment device, comprising:
[0027] The acquisition module is used to acquire historical working condition datasets and process the historical working condition datasets to obtain target working condition datasets.
[0028] The judgment module is used to calculate and obtain reference conditions based on the target working condition dataset;
[0029] The calculation module is used to calculate the initial ideal current percentage based on the initial model if the reference conditions do not meet the preset conditions, and to calculate the initial energy efficiency ratio based on the actual current percentage and the initial ideal current percentage.
[0030] An update module is used to train the initial model based on the target working condition dataset and obtain an updated model if the reference value does not meet the preset conditions.
[0031] Embodiments of this application also provide an energy efficiency assessment system, comprising:
[0032] The data acquisition unit and data evaluation unit are connected via communication.
[0033] The data acquisition unit is used to collect and acquire historical operating condition datasets;
[0034] The data evaluation unit is used to process the historical operating condition dataset to obtain the target operating condition dataset; calculate reference conditions based on the target operating condition dataset; if the reference conditions do not meet the preset conditions, calculate the initial ideal current percentage based on the initial model, and calculate the initial energy efficiency ratio based on the actual current percentage and the initial ideal current percentage; or if the reference value does not meet the preset conditions, train the initial model based on the target operating condition dataset to obtain an updated model.
[0035] Embodiments of this application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the method described above.
[0036] Embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the method described above.
[0037] The embodiments of this application have the following technical effects:
[0038] The above-mentioned technical solution of this application 1) enables real-time monitoring and evaluation of the energy efficiency of the chiller unit without the need to install a water flow meter. Specifically, the current energy efficiency ratio of the chiller unit can be calculated by the actual current percentage and the initial ideal current percentage. The method is simple and fast.
[0039] 2) Obtain the target operating condition dataset using the fault-free data from the initial commissioning of the chiller unit, and build an initial model based on the target operating condition dataset. The historical operating condition dataset includes the inlet water temperature data of the condenser, the inlet water temperature data of the evaporator, the outlet water temperature data of the evaporator, the operating status data of the chiller unit, and the cumulative operating time of the chiller unit. In addition, the initial ideal current percentage can be obtained by calculating the target operating condition dataset based on the initial model. Then, by combining the actual current percentage, the current energy efficiency ratio of the chiller unit can be obtained.
[0040] 3) Based on the historical operating data of each chiller unit, the real-time energy efficiency ratio of each chiller unit can be obtained.
[0041] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0042] Figure 1 This is a schematic diagram of the structure of an energy efficiency assessment system provided in an embodiment of this application;
[0043] Figure 2 This is a flowchart illustrating an energy efficiency assessment method provided in an embodiment of this application;
[0044] Figure 3 This is a schematic diagram of the structure of an energy efficiency assessment device provided in an embodiment of this application. Detailed Implementation
[0045] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0046] like Figure 1 As shown, embodiments of this application also provide an energy efficiency assessment system, including:
[0047] The data acquisition unit 101 and the data evaluation unit 1023 are connected by communication.
[0048] Data acquisition unit 101 is used to collect and acquire historical working condition datasets;
[0049] The data evaluation unit 1023 is used to process the historical operating condition dataset to obtain a target operating condition dataset; calculate reference conditions based on the target operating condition dataset; if the reference conditions do not meet the preset conditions, calculate the initial ideal current percentage based on the initial model, and calculate the initial energy efficiency ratio based on the actual current percentage and the initial ideal current percentage; or if the reference value does not meet the preset conditions, train the initial model based on the target operating condition dataset and obtain an updated model.
[0050] In an optional embodiment of this application, the data acquisition unit 101 is connected to the edge device 102, wherein the edge device 102 can be implemented based on a computer; the edge device 102 is provided with a data evaluation unit 1023 and a data display unit 1024, the first end of the data evaluation unit 1023 is connected to the data acquisition unit 101, and the second end of the data evaluation unit 1023 is connected to the data display unit 1024; specifically, after obtaining the historical operating condition dataset, the data acquisition unit 101 sends the historical operating condition dataset to the data evaluation unit 1023 of the edge device 102, and after obtaining the historical operating condition dataset, the data evaluation unit 1023 preprocesses and calculates the historical operating condition dataset to obtain the evaluation result, and sends the evaluation result to the data display unit 1024 for display; wherein the data display unit 1024 can be implemented based on a display screen or the like, enabling users to intuitively see the real-time energy efficiency status.
[0051] In an optional embodiment of this application, the edge device 102 further includes a data storage unit 1021 and a data preprocessing unit 1022, wherein the first end of the data storage unit 1021 is connected to the data acquisition unit 101, the second end of the data storage unit 1021 is connected to the first end of the data preprocessing unit 1022, and the second end of the data preprocessing unit 1022 is connected to the data evaluation unit 1023.
[0052] The data storage unit 1021 is used to receive the historical working condition dataset sent by the data acquisition unit 101, store the historical working condition dataset, and send the historical working condition dataset to the data preprocessing unit 1022 for preprocessing. After receiving the historical working condition dataset, the data preprocessing unit 1022 preprocesses the historical working condition dataset to obtain the target working condition dataset, and sends the target working condition dataset to the data evaluation unit 1023.
[0053] In an optional embodiment of this application, the data evaluation unit 1023 includes a model subunit 10231 and a calculation subunit 10232; wherein, the first end of the model subunit 10231 is connected to the second end of the data preprocessing module; the second end of the model subunit 10231 is connected to the first end of the calculation subunit 10232, and the second end of the calculation subunit 10232 is connected to the data display unit 1024;
[0054] Among them, the model subunit 10231 is used to build a model, obtain an initial model, and train the initial model to obtain an updated model; the initial model is used to calculate the ideal current percentage based on the target working condition dataset and send the ideal current percentage to the calculation subunit 10232; when the reference conditions obtained based on the target working condition dataset do not meet the preset conditions, the initial model is trained based on the target working condition dataset to obtain an updated model.
[0055] The calculation subunit 10232 is used to obtain the actual current percentage and calculate the initial energy efficiency ratio based on the actual current percentage and the ideal current percentage. Then, the initial energy efficiency ratio is sent to the data display unit 1024 for display.
[0056] The embodiments of this application can realize real-time monitoring and evaluation of the energy efficiency of the chiller unit without the need to install a water flow meter. Specifically, the current energy efficiency ratio of the chiller unit can be calculated by the actual current percentage and the initial ideal current percentage. The method is simple and fast.
[0057] like Figure 2 As shown, embodiments of this application also provide an energy efficiency assessment method, applicable to, for example... Figure 1 The system shown includes:
[0058] Step S21: Obtain historical working condition dataset and process the historical working condition dataset to obtain target working condition dataset;
[0059] In one optional embodiment of this application, a preset collection duration can be used to collect historical working condition data. That is, the total duration corresponding to the obtained historical working condition dataset is the collection duration, such as 2 hours, 3 hours, etc.
[0060] In one optional embodiment of this application, the historical operating condition dataset includes first historical operating condition data of the condenser, second historical operating condition data of the evaporator, operating status data of the chiller unit, and cumulative operating time of the chiller unit.
[0061] Specifically, the first historical operating data of the condenser includes the condenser's inlet water temperature; the second historical operating data of the evaporator includes the evaporator's inlet water temperature and outlet water temperature.
[0062] In an optional embodiment of this application, processing the historical working condition dataset to obtain the target working condition dataset includes:
[0063] Set a first threshold, a second threshold, a third threshold, and a fourth threshold;
[0064] The first threshold is used to filter the inlet water temperature of the condenser. If the inlet water temperature of the condenser does not meet the first threshold, the inlet water temperature data of the condenser that does not meet the first threshold will be removed.
[0065] The second threshold is used to filter the evaporator inlet water temperature. If the condenser inlet water temperature does not meet the second threshold, the evaporator inlet water temperature data that does not meet the second threshold will be removed.
[0066] Similarly, the third threshold is used to filter the outlet water temperature data of the evaporator, and the fourth threshold is used to filter the operating status data of the chiller unit. Based on the fourth threshold, the operating status data of the chiller unit in a stable operating state is retained.
[0067] The embodiments of this application, based on a first threshold, a second threshold, a third threshold, and a fourth threshold, preprocess historical working condition datasets to remove outliers and thereby obtain target working condition datasets; wherein, the specific values of the first threshold, the second threshold, the third threshold, and the fourth threshold can be adjusted according to actual needs, and the embodiments of this application do not impose specific limitations on this.
[0068] In addition, based on the historical operating data of each chiller unit, the real-time energy efficiency ratio of each chiller unit can be obtained.
[0069] Step S22: Based on the target working condition dataset, calculate and obtain the reference conditions;
[0070] In an optional embodiment of this application, the calculation of reference conditions based on the target working condition dataset includes:
[0071] Based on the initial model, the target operating condition data is identified to obtain a first sub-reference condition; based on the cumulative operating time of the chiller unit, a second sub-reference condition is obtained; based on the operating status data of the chiller unit, a third sub-reference condition is obtained; wherein, the reference conditions include the first sub-reference condition, the second sub-reference condition, and the third sub-reference condition;
[0072] The first sub-reference condition is judged based on the first sub-preset condition; the second sub-reference condition is judged based on the second sub-preset condition; and the third sub-reference condition is judged based on the third sub-preset condition; wherein, the preset condition includes the first sub-preset condition, the second sub-preset condition, and the third sub-preset condition.
[0073] In one optional embodiment of this application, the first sub-preset condition is that the initial model cannot identify the target operating condition dataset, that is, the initial model cannot perform calculations based on the target operating condition dataset; the second sub-preset condition is that the chiller unit is operating normally; and the third sub-preset condition is that the cumulative operating time of the chiller unit does not exceed 3 months.
[0074] Step S23: If the reference conditions do not meet the preset conditions, the initial ideal current percentage is calculated based on the initial model, and the initial energy efficiency ratio is calculated based on the actual current percentage and the initial ideal current percentage.
[0075] In an optional embodiment of this application, if the reference conditions do not meet the preset conditions, the following includes:
[0076] If any one of the following exists: the first sub-reference condition does not satisfy the first sub-preset condition, the second sub-reference condition does not satisfy the second sub-preset condition, or the third sub-reference condition does not satisfy the third sub-preset condition, then the reference condition does not satisfy the preset condition.
[0077] In an optional embodiment of this application, if any one of the following exists: the first sub-reference condition is that the initial model can identify the target operating condition dataset, the second sub-reference condition is that the chiller unit is operating normally, and the third sub-reference condition is that the cumulative operating time of the chiller unit does not exceed 3 months, it indicates that the reference condition does not meet the preset condition. Then, the initial ideal current percentage (that is, the current percentage corresponding to the normal operating state of the chiller unit) is calculated based on the initial model.
[0078] The current percentage is the ratio of the actual current of the chiller unit to the full-load current, which is used to reflect the power consumption level of the chiller unit.
[0079] In an optional embodiment of this application, the initial model can filter the target working condition dataset based on a preset grid. If all the data contained in the target working condition dataset can fall within the range of the grid, it indicates that the target working condition dataset can be identified by the initial model; conversely, if some data in the target working condition dataset falls outside the grid, it indicates that the target working condition dataset cannot be identified by the initial model.
[0080] In an optional embodiment of this application, if the first sub-reference condition is that the initial model can identify the target operating condition dataset, the second sub-reference condition is that the chiller unit is operating normally, and the third sub-reference condition is that the cumulative operating time of the chiller unit does not exceed 3 months, then it indicates that the reference conditions do not meet the preset conditions, and the initial ideal current percentage is calculated based on the initial model.
[0081] In an optional embodiment of this application, if the first sub-reference condition is that the initial model cannot identify the target operating condition dataset, the second sub-reference condition is that the chiller unit is operating normally, and the third sub-reference condition is that the cumulative operating time of the chiller unit does not exceed 3 months, then it indicates that the reference conditions do not meet the preset conditions, and the initial ideal current percentage is calculated based on the initial model.
[0082] In an optional embodiment of this application, if the first sub-reference condition is that the initial model cannot identify the target operating condition dataset, the second sub-reference condition is that the chiller unit is not operating normally, and the third sub-reference condition is that the cumulative operating time of the chiller unit does not exceed 3 months, it indicates that the reference conditions do not meet the preset conditions, and the initial ideal current percentage is calculated based on the initial model.
[0083] Furthermore, if the actual current percentage deviates from the initial ideal current percentage by more than 10%, it indicates that the chiller unit has a fault or that the performance of the chiller unit has deteriorated. Therefore, users can formulate corresponding maintenance plans based on the deviation ratio.
[0084] Furthermore, the final output of the embodiments of this application is:
[0085] [2-(actual current percentage / initial ideal current percentage)]*100% is used as the energy efficiency score of the chiller unit. The full score is 100 points. The smaller the score, the worse the energy efficiency of the chiller unit. This score is displayed based on the edge device 102.
[0086] The actual current percentage can be calculated based on the current operating data of the chiller unit using existing algorithms. This application will not elaborate on the existing algorithms.
[0087] For example, if the edge display device shows 50 minutes at time A and the edge device 102 shows 60 minutes at time B, then the energy efficiency of the chiller unit at time B is better than that of the chiller unit at time A.
[0088] In the embodiments of this application, a target operating condition dataset is obtained using fault-free data from the initial operation of the chiller unit, and an initial model is constructed based on the target operating condition dataset. The historical operating condition dataset includes condenser inlet water temperature data, evaporator inlet water temperature data, evaporator outlet water temperature data, chiller unit operating status data, and chiller unit cumulative operating time. Furthermore, by calculating the target operating condition dataset based on the initial model, an initial ideal current percentage can be obtained, and then combined with the actual current percentage, the current energy efficiency ratio of the chiller unit can be obtained.
[0089] Step S24: If the reference value does not meet the preset condition, then the initial model is trained based on the target working condition dataset, and an updated model is obtained.
[0090] In an optional embodiment of this application, if the reference condition does not meet the preset condition, the following includes:
[0091] If the first sub-reference condition satisfies the first sub-preset condition, the second sub-reference condition satisfies the second sub-preset condition, and the third sub-reference condition satisfies the third sub-preset condition, then the reference condition does not satisfy the preset condition.
[0092] In an optional embodiment of this application, if the first sub-reference condition is that the initial model cannot identify the target operating condition dataset, the second sub-reference condition is that the chiller unit is not operating normally, and the third sub-reference condition is that the cumulative operating time of the chiller unit exceeds 3 months, it indicates that the reference conditions meet the preset conditions. Then, the initial model is trained based on the target operating condition dataset, and an updated model is obtained.
[0093] In the embodiments of this application, the number of times the initial model is trained based on the target working condition dataset can be adjusted according to actual needs. The embodiments of this application do not impose specific limitations on this.
[0094] In an optional embodiment of this application, training the initial model based on the training condition dataset to obtain an updated model includes:
[0095] The initial model is trained based on the training condition dataset to obtain a trained model;
[0096] The trained model is tested based on the test condition dataset to obtain the test accuracy of the trained model;
[0097] The training model is validated based on the test accuracy. If the validation is successful, the updated model is obtained based on the training model.
[0098] In an optional embodiment of this application, a pre-defined division ratio can be used to divide the target working condition dataset according to the division ratio, thereby obtaining a training working condition dataset and a test working condition dataset respectively.
[0099] The division ratio can be set according to actual needs, and the embodiments of this application do not impose specific limitations on it.
[0100] In an optional embodiment of this application, the verification of the trained model based on the test accuracy includes:
[0101] The test accuracy is compared with the accuracy threshold; at the same time, the initial accuracy of the initial model is obtained, and the absolute value of the difference between the initial accuracy and the test accuracy is obtained, and the absolute value of the difference is compared with the difference threshold.
[0102] If the test accuracy is greater than the accuracy threshold and the absolute value of the difference is less than the difference threshold, then the verification is successful.
[0103] In one optional embodiment of this application, after training the initial model multiple times based on the training condition dataset, a training model can be obtained; then, the test condition dataset is input into the training model, and the calculation results are output; based on the calculation results, the test accuracy of the training model is determined.
[0104] The test accuracy is compared with an accuracy threshold; simultaneously, the initial accuracy of the initial model is obtained, which can be obtained based on the edge device 102; the difference between the test accuracy and the initial accuracy is calculated, and the absolute value of the difference is compared with a difference threshold.
[0105] If the test accuracy is not greater than the accuracy threshold and the absolute value of the difference is less than the difference threshold, the edge device 102 will not save the training model. Instead, it can return to continue training the initial model multiple times based on the training condition dataset until the test accuracy is greater than the accuracy threshold and the absolute value of the difference is less than the difference threshold. Then, the edge device 102 will save the training model and determine it as the update model, thus realizing the automatic update of the initial model.
[0106] If the test accuracy is greater than the accuracy threshold and the absolute value of the difference is not less than the difference threshold, the edge device 102 will not save the training model. Instead, it can return to continue training the initial model multiple times based on the training condition dataset until the test accuracy is greater than the accuracy threshold and the absolute value of the difference is less than the difference threshold. Then, the edge device 102 will save the training model and determine it as the update model, thus realizing the automatic update of the initial model.
[0107] If the test accuracy is not greater than the accuracy threshold and the absolute value of the difference is not less than the difference threshold, the edge device 102 will not save the training model. Instead, it can return to continue training the initial model multiple times based on the training condition dataset until the test accuracy is greater than the accuracy threshold and the absolute value of the difference is less than the difference threshold. Then, the edge device 102 will save the training model and determine it as the update model, thus realizing the automatic update of the initial model.
[0108] If the test accuracy is greater than the accuracy threshold and the absolute value of the difference is less than the difference threshold, the edge device 102 saves the training model and determines the training model as the update model, thus realizing the automatic update of the initial model.
[0109] In an optional embodiment of this application, the updated model can be used to calculate the updated target operating condition dataset and obtain the updated ideal current percentage.
[0110] Specifically, after obtaining the updated model, the updated historical working condition dataset can be re-acquired based on the preset collection time, and the above steps can be repeated to preprocess the updated historical working condition dataset to obtain the updated target working condition dataset.
[0111] The updated reference conditions are obtained based on the updated target working condition dataset, and the updated reference conditions are judged based on the preset conditions.
[0112] If the updated reference conditions do not meet the preset conditions, the updated target operating condition dataset is calculated based on the updated model to obtain the updated ideal current percentage, and the actual current percentage is obtained based on the edge device 102. Then, the updated energy efficiency ratio is calculated based on the actual current percentage and the updated ideal current percentage.
[0113] If the updated reference conditions meet the preset conditions, the updated target operating condition dataset is divided according to the preset division ratio to obtain the updated test operating condition dataset and the updated training operating condition dataset. The updated model is trained based on the updated test operating condition dataset to enable the continued updating of the updated model. By repeating the above steps, the historical operating condition dataset can be updated in time sequence, and the current energy efficiency ratio of the chiller unit can be obtained accordingly.
[0114] In one optional embodiment of this application, it is assumed that the accuracy threshold is 95% and the difference threshold is 5%.
[0115] After training the initial model based on the training condition dataset, the trained model is obtained. Based on the above steps, the test accuracy of the trained model is calculated. The test accuracy is compared with the accuracy threshold. At the same time, the initial accuracy is obtained, and the absolute value of the difference between the initial accuracy and the test accuracy is obtained.
[0116] If the test accuracy is not greater than 95% and the absolute value of the difference is less than 5%, the edge device 102 will not save the training model. Instead, it can return to continue training the initial model multiple times based on the training condition dataset. If the test accuracy is greater than 95% and the absolute value of the difference is less than 5%, the edge device 102 will save the training model and determine it as the update model, thus realizing the automatic update of the initial model.
[0117] If the test accuracy is greater than 95% and the absolute value of the difference is not less than 5%, the edge device 102 will not save the training model. Instead, it can return to continue training the initial model multiple times based on the training condition dataset. If the test accuracy is greater than 95% and the absolute value of the difference is less than 5%, the edge device 102 will save the training model and determine it as the update model, thus realizing the automatic update of the initial model.
[0118] If the test accuracy is not greater than 95% and the absolute value of the difference is not less than 5%, the edge device 102 will not save the training model. Instead, it can return to continue training the initial model multiple times based on the training condition dataset. If the test accuracy is greater than 95% and the absolute value of the difference is less than 5%, the edge device 102 will save the training model and determine it as the update model, thus realizing the automatic update of the initial model.
[0119] If the test accuracy is greater than 95% and the absolute value of the difference is less than 5%, the edge device 102 saves the training model, realizing the automatic update of the initial model.
[0120] It should be noted that the accuracy threshold and the difference threshold can be adjusted according to actual needs.
[0121] In an optional embodiment of this application, the chilled water load can be calculated first based on the flow rate, supply and return water temperature, and power of the chiller unit, using the flow rate and chilled water temperature difference. The energy efficiency ratio can then be calculated by dividing the load by the power.
[0122] In one optional embodiment of this application, 1) the measured energy efficiency of the chiller unit is compared with the standard to obtain the current energy efficiency evaluation result of the chiller unit.
[0123] 2) Collect operating data of the chiller unit, select operating data of chiller units with similar operating conditions in historical data, compare current energy efficiency with historical energy efficiency, and obtain the degree of energy efficiency degradation of the chiller unit.
[0124] 3) Compare the chiller unit's operating conditions with the product catalog to ensure they match the catalog. Measure the chiller unit's energy efficiency under these operating conditions and compare it with the data in the product catalog to obtain the chiller unit's current operating status.
[0125] like Figure 3 As shown, embodiments of this application also provide an energy efficiency assessment device 30, comprising:
[0126] The acquisition module 31 is used to acquire historical working condition datasets and process the historical working condition datasets to obtain target working condition datasets.
[0127] The judgment module 32 is used to calculate and obtain reference conditions based on the target working condition dataset;
[0128] The calculation module 33 is used to calculate the initial ideal current percentage based on the initial model if the reference conditions do not meet the preset conditions, and to calculate the initial energy efficiency ratio based on the actual current percentage and the initial ideal current percentage.
[0129] The update module 34 is used to train the initial model based on the target working condition dataset and obtain an updated model if the reference value does not meet the preset conditions.
[0130] Optionally, the historical operating condition dataset includes first historical operating condition data of the condenser, second historical operating condition data of the evaporator, operating status data of the chiller unit, and cumulative operating time of the chiller unit.
[0131] Optionally, the step of calculating the reference conditions based on the target working condition dataset includes:
[0132] Based on the initial model, the target operating condition data is identified to obtain a first sub-reference condition; based on the cumulative operating time of the chiller unit, a second sub-reference condition is obtained; based on the operating status data of the chiller unit, a third sub-reference condition is obtained; wherein, the reference conditions include the first sub-reference condition, the second sub-reference condition, and the third sub-reference condition;
[0133] The first sub-reference condition is judged based on the first sub-preset condition; the second sub-reference condition is judged based on the second sub-preset condition; and the third sub-reference condition is judged based on the third sub-preset condition; wherein, the preset condition includes the first sub-preset condition, the second sub-preset condition, and the third sub-preset condition.
[0134] Optionally, if the reference condition does not meet the preset condition, it includes:
[0135] If any one of the following exists: the first sub-reference condition does not satisfy the first sub-preset condition, the second sub-reference condition does not satisfy the second sub-preset condition, or the third sub-reference condition does not satisfy the third sub-preset condition, then the reference condition does not satisfy the preset condition.
[0136] Optionally, if the reference condition does not meet the preset condition, it includes:
[0137] If the first sub-reference condition satisfies the first sub-preset condition, the second sub-reference condition satisfies the second sub-preset condition, and the third sub-reference condition satisfies the third sub-preset condition, then the reference condition does not satisfy the preset condition.
[0138] Optionally, training the initial model based on the training condition dataset to obtain an updated model includes:
[0139] The initial model is trained based on the training condition dataset to obtain a trained model;
[0140] The trained model is tested based on the test condition dataset to obtain the test accuracy of the trained model;
[0141] The training model is validated based on the test accuracy. If the validation is successful, the updated model is obtained based on the training model.
[0142] Optionally, the step of validating the trained model based on the test accuracy includes:
[0143] The test accuracy is compared with the accuracy threshold; at the same time, the initial accuracy of the initial model is obtained, and the absolute value of the difference between the initial accuracy and the test accuracy is obtained, and the absolute value of the difference is compared with the difference threshold.
[0144] If the test accuracy is greater than the accuracy threshold and the absolute value of the difference is less than the difference threshold, then the verification is successful.
[0145] Embodiments of this application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the method described above.
[0146] Embodiments of this application also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the method described above.
[0147] Furthermore, other configurations and functions of the apparatus in the embodiments of this application are known to those skilled in the art, and will not be described in detail here to reduce redundancy.
[0148] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.
[0149] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0150] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0151] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.
[0152] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0153] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.
[0154] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.
[0155] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.
Claims
1. An energy efficiency assessment method, characterized in that, include: Obtain historical operating condition datasets and process the historical operating condition datasets to obtain target operating condition datasets; Based on the target working condition dataset, reference conditions are obtained; If the reference conditions do not meet the preset conditions, the initial ideal current percentage is calculated based on the initial model, and the initial energy efficiency ratio is calculated based on the actual current percentage and the initial ideal current percentage. If any one of the following conditions is met: the initial model can identify the target operating condition dataset, the chiller unit is operating normally, and the cumulative operating time of the chiller unit does not exceed 3 months, then the reference conditions do not meet the preset conditions. Alternatively, if the reference conditions meet the preset conditions, the initial model is trained based on the target working condition dataset, and an updated model is obtained. If the initial model cannot identify the target operating condition dataset, the chiller unit is not operating normally, or the cumulative operating time of the chiller unit exceeds 3 months, it indicates that the reference conditions meet the preset conditions.
2. The method according to claim 1, characterized in that, The historical operating condition dataset includes the first historical operating condition data of the condenser, the second historical operating condition data of the evaporator, the operating status data of the chiller unit, and the cumulative operating time of the chiller unit.
3. The method according to claim 1, characterized in that, The step of training the initial model based on the target working condition dataset and obtaining an updated model includes: The target working condition dataset is divided to obtain a training working condition dataset and a test working condition dataset. The initial model is trained based on the training dataset to obtain an updated model.
4. The method according to claim 3, characterized in that, The step of training the initial model based on the training condition dataset to obtain an updated model includes: The initial model is trained based on the training condition dataset to obtain a trained model; The trained model is tested based on the test condition dataset to obtain the test accuracy of the trained model; The training model is validated based on the test accuracy. If the validation is successful, the updated model is obtained based on the training model.
5. The method according to claim 4, characterized in that, The verification of the trained model based on the test accuracy includes: The test accuracy is compared with the accuracy threshold; at the same time, the initial accuracy of the initial model is obtained, and the absolute value of the difference between the initial accuracy and the test accuracy is obtained, and the absolute value of the difference is compared with the difference threshold. If the test accuracy is greater than the accuracy threshold and the absolute value of the difference is less than the difference threshold, then the verification is successful.
6. An energy efficiency assessment device, characterized in that, include: The acquisition module is used to acquire historical working condition datasets and process the historical working condition datasets to obtain target working condition datasets. The judgment module is used to obtain reference conditions based on the target working condition dataset; The calculation module is used to calculate the initial ideal current percentage based on the initial model if the reference conditions do not meet the preset conditions, and to calculate the initial energy efficiency ratio based on the actual current percentage and the initial ideal current percentage. If any one of the following conditions is met: the initial model can identify the target operating condition dataset, the chiller unit is operating normally, and the cumulative operating time of the chiller unit does not exceed 3 months, then the reference conditions do not meet the preset conditions. An update module is used to train the initial model based on the target working condition dataset and obtain an updated model, if the reference conditions meet preset conditions. If the initial model cannot identify the target operating condition dataset, the chiller unit is not operating normally, or the cumulative operating time of the chiller unit exceeds 3 months, it indicates that the reference conditions meet the preset conditions.
7. An energy efficiency assessment system, characterized in that, include: The data acquisition unit and data evaluation unit are connected via communication. The data acquisition unit is used to collect and acquire historical operating condition datasets; The data evaluation unit is used to process the historical working condition dataset to obtain the target working condition dataset; Based on the target working condition dataset, reference conditions are obtained; If the reference conditions do not meet the preset conditions, the initial ideal current percentage is calculated based on the initial model, and the initial energy efficiency ratio is calculated based on the actual current percentage and the initial ideal current percentage. If any one of the following conditions is met: the initial model can identify the target operating condition dataset, the chiller unit is operating normally, and the cumulative operating time of the chiller unit does not exceed 3 months, then the reference conditions do not meet the preset conditions. If the reference conditions do not meet the preset conditions, the initial model is trained based on the target working condition dataset to obtain an updated model. If the initial model cannot identify the target operating condition dataset, the chiller unit is not operating normally, or the cumulative operating time of the chiller unit exceeds 3 months, it indicates that the reference conditions meet the preset conditions.
8. An electronic device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1 to 5.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the method as described in any one of claims 1 to 5.