Error analysis and model correction method and system for water pump energy consumption model of central air conditioner

Abstract

The invention relates to the technical field of energy-saving control, in particular to a central air conditioner water pump energy consumption model error analysis and model correction method and system.The method comprises the steps that the rated power and the frequency ratio of a water pump are obtained, and a water pump theoretical energy consumption model is constructed according to the rated power and the frequency ratio; main working condition factors influencing model calculation errors are determined, wherein the main working condition factors comprise at least one of the number of running water pumps and the running frequency of the water pumps; in a working condition range covered by the main working condition factors, performing error analysis based on differences between model calculation results in all samples and actual energy consumption; and constructing a model error correction coefficient based on the error analysis result, and correcting the model calculation result according to the model error correction coefficient to obtain a corrected water pump energy consumption value. By implementing the method, the energy consumption of the water pump of the central air conditioner can be evaluated more efficiently and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving control, and in particular to a method and system for error analysis and model correction of a central air-conditioning water pump energy consumption model. Background Art

[0002] Energy-saving renovation of central air-conditioning systems in public buildings has been recognized by more and more industry insiders and owners. As a commercial behavior, energy-saving renovation requires a full evaluation of the benefits of project implementation. Before deciding whether to implement energy-saving renovation of the central air-conditioning system of an existing building, it is usually necessary to analyze the operating status of the existing system and calculate the energy consumption of the system. Most existing buildings lack sub-item metering data for the energy consumption of each device in the central air-conditioning system, and usually require energy consumption models to be calculated based on the specific operating parameters of each device. In actual projects, energy consumption theoretical models or empirical models are often used to perform simple and rough calculations on the energy consumption of each device in the existing central air-conditioning system, and to estimate the energy-saving potential of the system.

[0003] The energy consumption of water pumps in central air-conditioning systems accounts for about 15% to 40% of the total system energy consumption. The accuracy of its energy consumption calculation directly affects the results of system energy efficiency diagnosis and energy-saving evaluation. Existing central air-conditioning water pump energy consumption evaluation models, such as theoretical models, are specifically based on strict physical laws and mathematical formulas to accurately describe the operating characteristics of water pumps. However, although the water pump theoretical energy consumption model is simple to calculate, the result deviation is large. Although the existing model correction method can improve the calculation accuracy of the water pump theoretical model, the correction process is relatively cumbersome and it is difficult to widely promote and apply it in actual engineering. Therefore, it is urgent to introduce an accurate, efficient and universal central air-conditioning water pump energy consumption evaluation model and its correction method, which can fully utilize existing data resources, reduce dependence on a large amount of measured data, and maintain high calculation accuracy and practicality. Summary of the invention

[0004] In order to achieve more efficient and accurate evaluation of the energy consumption of central air-conditioning water pumps, the purpose of the present invention is to provide a central air-conditioning water pump energy consumption model error analysis and model correction method and system, the technical scheme adopted is as follows:

[0005] In a first aspect, the present application discloses a method for error analysis and model correction of a central air-conditioning water pump energy consumption model, the method comprising:

[0006] S1. Obtain the rated power and frequency ratio of the water pump and use them to construct a theoretical energy consumption model of the water pump;

[0007] S2. Determine the main operating factors that affect the model calculation error, wherein the main operating factors include at least one of the number of operating water pumps and the operating frequency of the water pumps;

[0008] S3. within the operating range covered by the main operating factors, error analysis is performed based on the difference between the model calculation results and the actual energy consumption in all samples;

[0009] S4. Constructing a model error correction coefficient based on the error analysis result, and correcting the model calculation result according to the model error correction coefficient to obtain a corrected water pump energy consumption value.

[0010] Furthermore, in step S1, the calculation formula of the water pump theoretical energy consumption model includes:

[0011] P=P rate ω 3 ;

[0012] Among them, P represents the actual power of the pump, P rate Indicates the rated power of the pump, ω=f / f rate represents the frequency ratio of the water pump, f represents the actual operating frequency of the water pump, and f rate Indicates the rated frequency of the pump.

[0013] Furthermore, in step S2, determining the main operating factors affecting the model calculation error includes:

[0014] S21, obtaining sample data covering various operating conditions, wherein the sample data includes actual measured energy consumption values ​​and corresponding operating conditions;

[0015] S22. For each sample, calculate the error between the model calculation result and the actual measured energy consumption value;

[0016] S23, performing statistical analysis based on the obtained errors to obtain corresponding error analysis results;

[0017] S24. Based on the error analysis results, determine the main operating factors that affect the model calculation error.

[0018] Furthermore, in step S3, within the operating range covered by the main operating factors, error analysis is performed based on the difference between the model calculation results and the actual energy consumption in all samples, including:

[0019] S31. For each sample, respectively calculate the difference between the corresponding model calculation result and the actual energy consumption, and obtain the corresponding relative error based on the ratio of this difference to the actual energy consumption;

[0020] S32, calculating the mean of the relative errors corresponding to all samples respectively, and obtaining the average relative error of the corresponding error analysis results.

[0021] Furthermore, the calculation formula of the average relative error includes:

[0022]

[0023] Among them, MRE represents the mean relative error, n represents the number of samples, and δ i represents the relative error corresponding to the i-th sample, represents the model calculation result corresponding to the i-th sample, y i Represents the actual energy consumption corresponding to the i-th sample.

[0024] Furthermore, in step S4, the model error correction coefficient is constructed based on the error analysis result, and the model calculation result is corrected according to the model error correction coefficient to obtain a corrected water pump energy consumption value, including:

[0025] S41. When determining that the main operating factors include the number of running water pumps, let the model error correction coefficient be Where m represents the number of running pumps. It represents the relative error corresponding to the i-th sample among the m water pump operating condition samples, It represents the average relative error obtained based on the relative errors obtained;

[0026] S42, based on the model error correction coefficient x m Constructing an adjustment ratio, and setting a linear relationship between the adjustment ratio and the model calculation result;

[0027] S43. Correcting the model calculation result based on the adjustment ratio to obtain a corrected water pump energy consumption value.

[0028] Furthermore, in step S4, the model error correction coefficient is constructed based on the error analysis result, and the model calculation result is corrected according to the model error correction coefficient to obtain a corrected water pump energy consumption value, including:

[0029] S41. When determining that the main operating factors include the number of running water pumps and the running frequency of the water pumps, let the model error correction coefficient be Where m represents the number of running pumps, F represents the range of the running frequency of the pumps, It represents the relative error corresponding to the i-th sample among the m water pump operating condition samples, It represents the average relative error obtained based on the relative errors obtained. Represents the relative error of the ith sample in the sample of m pumps operating in the frequency range F, Indicates the floating deviation of the average relative error caused within the F frequency range;

[0030] S42, based on the model error correction coefficient x m,FConstructing an adjustment ratio, and setting a linear relationship between the adjustment ratio and the model calculation result;

[0031] S43. Correcting the model calculation result based on the adjustment ratio to obtain a corrected water pump energy consumption value.

[0032] Furthermore, the model calculation results are corrected by the following formula to obtain the corrected water pump energy consumption value:

[0033]

[0034] in, represents the model calculation results, represents the corrected energy consumption value of the water pump, and x represents the model error correction coefficient.

[0035] In the second aspect, the present application discloses a central air-conditioning water pump energy consumption model error analysis and model correction system, the system comprising a theoretical model construction module, an operating condition factor determination module, an error analysis module, and a model correction module, wherein:

[0036] The theoretical model building module is used to obtain the rated power and frequency ratio of the water pump and use them to build a theoretical energy consumption model of the water pump;

[0037] The operating condition factor determination module is used to determine the main operating condition factors that affect the model calculation error, and the main operating condition factors include at least one of the number of running water pumps and the running frequency of the water pumps;

[0038] The error analysis module is used to perform error analysis based on the difference between the model calculation results and the actual energy consumption in all samples within the operating condition range covered by the main operating condition factors;

[0039] The model correction module is used to construct a model error correction coefficient based on the error analysis result, and correct the model calculation result according to the model error correction coefficient to obtain a corrected water pump energy consumption value.

[0040] The present invention has the following beneficial effects:

[0041] 1. This application analyzes energy consumption errors from two dimensions: the number of running units and the operating frequency. By deeply understanding the internal mechanism of water pump energy consumption changes, it helps to more accurately predict and control water pump energy consumption in practical applications;

[0042] 2. Within the operating conditions covered by the two dimensions of number of running units and operating frequency, error analysis is performed based on the difference between the model calculation results and the actual energy consumption. By quantifying the accuracy of the model prediction and identifying the operating conditions under which the model is prone to deviation, this provides a basis for further improving the model;

[0043] 3. Constructing the model error correction coefficient based on the error analysis results and correcting the model calculation results according to the coefficient can significantly improve the prediction accuracy of the model. This makes the model more valuable for reference in practical applications and helps to achieve more refined energy consumption management. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A method flow chart of a central air-conditioning water pump energy consumption model error analysis and model correction method provided by an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of the relative error distribution between the energy consumption model calculation value and the measured energy consumption after correction based on the number of running pumps;

[0047] Figure 3 It is a schematic diagram of the relative error distribution between the energy consumption model calculation value and the measured energy consumption after correction based on the number of running water pumps and the running frequency of water pumps;

[0048] Figure 4 A system structure diagram of a central air-conditioning water pump energy consumption model error analysis and model correction system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the error analysis and model correction method and system of the energy consumption model of a central air-conditioning water pump proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0050] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0051] The specific scheme of a central air-conditioning water pump energy consumption model error analysis and model correction method and system provided by the present invention is described in detail below in conjunction with the accompanying drawings.

[0052] See also Figure 1 , which shows a method flow chart of a central air-conditioning water pump energy consumption model error analysis and model correction method provided by an embodiment of the present invention, the method comprising:

[0053] Step S1, obtaining the rated power and frequency ratio of the water pump, and using them to construct a theoretical energy consumption model of the water pump.

[0054] Step S2, determining the main operating factors that affect the model calculation error, wherein the main operating factors include at least one of the number of operating water pumps and the operating frequency of the water pumps.

[0055] Step S3, within the operating condition range covered by the main operating condition factors, error analysis is performed based on the difference between the model calculation results and the actual energy consumption in all samples.

[0056] Step S4, constructing a model error correction coefficient based on the error analysis result, and correcting the model calculation result according to the model error correction coefficient to obtain a corrected water pump energy consumption value.

[0057] As can be seen from the above, the central air-conditioning water pump energy consumption model error analysis and model correction method disclosed in this application respectively performs energy consumption error analysis from two dimensions: the number of running units and the operating frequency. By deeply understanding the internal mechanism of water pump energy consumption changes, it is helpful to more accurately predict and regulate water pump energy consumption in practical applications; within the range of operating conditions covered by the two dimensions of the number of running units and the operating frequency, error analysis is performed based on the difference between the model calculation results and the actual energy consumption, and the accuracy of the model prediction is quantified, and the conditions under which the model is prone to deviation are identified. This provides a basis for further improving the model; constructing a model error correction coefficient based on the error analysis results, and correcting the model calculation results according to the coefficient can significantly improve the prediction accuracy of the model. This makes the model more valuable for reference in practical applications and helps to achieve more refined energy consumption management.

[0058] In one embodiment, in step S1, the calculation formula of the water pump theoretical energy consumption model includes:

[0059] P=P rate ω 3 ;

[0060] Among them, P represents the actual power of the pump, P rate Indicates the rated power of the pump, ω=f / f rate represents the frequency ratio of the water pump, f represents the actual operating frequency of the water pump, and f rate Indicates the rated frequency of the pump.

[0061] It should be noted that the rated power of a water pump indicates the power consumed by the water pump under standard operating conditions (usually rated voltage and rated frequency). The frequency ratio of a water pump indicates the ratio between the actual operating frequency of the water pump and the rated frequency of the water pump. Since the motor of a water pump is usually an AC motor, its speed is proportional to the power supply frequency (under constant voltage power supply), so the frequency ratio can reflect the impact of changes in the speed of the water pump on energy consumption. Since the flow rate of a water pump is usually proportional to the speed, assuming that the efficiency remains unchanged, the energy consumption is proportional to the cube of the speed.

[0062] In one embodiment, in step S2, determining the main operating factors affecting the model calculation error includes:

[0063] Step S21, obtaining sample data covering various operating conditions, wherein the sample data includes actually observed energy consumption values ​​and corresponding operating conditions.

[0064] Specifically, this application will collect a large amount of sample data covering various operating conditions, where the operating conditions include the number of running pumps, the operating frequency of the pumps, medium characteristics, and pipeline resistance, etc.

[0065] Step S22, for each sample, calculate the error between the model calculation result and the actual observation value.

[0066] Specifically, the difference between the model calculation result and the actual observation value can be calculated using at least one indicator among absolute error, relative error and mean square error.

[0067] Step S23: Perform statistical analysis based on the obtained errors to obtain corresponding error analysis results.

[0068] Specifically, after collecting a large amount of sample data and calculating the errors, the present application will perform statistical analysis on these errors to analyze the correlation between the errors and the working conditions. The analysis method here includes analyzing the distribution characteristics of the errors (such as mean, variance, deviation, kurtosis, etc.).

[0069] Step S24, based on the error analysis result, determine the main operating factors that affect the model calculation error.

[0070] Specifically, this application will identify the main operating factors that have a significant impact on the error based on these error analysis results. The main operating factors analyzed here include at least one of the number of running water pumps and the operating frequency of the water pumps. Among them, the increase or decrease in the number of running water pumps will directly affect the overall energy consumption level of the system, because as the number of running water pumps increases, the total energy consumption of the system will increase accordingly; and the change in the operating frequency of the water pump will affect the working efficiency of the water pump, and then affect the energy consumption. Usually, the water pump is at its highest when it runs close to its design frequency. Too high or too low a frequency will lead to an increase in energy consumption.

[0071] In one embodiment, in step S3, within the operating range covered by the main operating factors, error analysis is performed based on the difference between the model calculation results and the actual energy consumption in all samples, including:

[0072] Step S31, for each sample, respectively calculate the difference between the corresponding model calculation result and the actual energy consumption, and obtain the corresponding relative error based on the ratio of this difference to the actual energy consumption.

[0073] Step S32, performing mean calculation based on the relative errors corresponding to all samples, to obtain the average relative error of the corresponding error analysis result.

[0074] Based on step S31 to step S32, it should be noted that these two steps together constitute the complete process of calculating the average relative error, which ensures the accuracy and comprehensiveness of the evaluation. Through this method, we can obtain a quantitative indicator that can evaluate the prediction performance of the model under different working conditions and optimize and improve the model accordingly.

[0075] In one embodiment, the calculation formula of the average relative error includes:

[0076]

[0077] Among them, MRE represents the mean relative error, n represents the number of samples, and δ i represents the relative error corresponding to the i-th sample, represents the model calculation result corresponding to the i-th sample, y i Represents the actual energy consumption corresponding to the i-th sample.

[0078] In one embodiment, in step S4, the model error correction coefficient is constructed based on the error analysis result, and the model calculation result is corrected according to the model error correction coefficient to obtain the corrected water pump energy consumption value, including:

[0079] Step S41, when determining that the main operating condition factors include the number of running water pumps, let the model error correction coefficient be Where m represents the number of running pumps. represents the relative error corresponding to the i-th sample of the m-th water pump, It represents the average relative error obtained based on the relative errors obtained.

[0080] Specifically, when only the number of operating water pumps is considered, this application will calculate the correction coefficients for single pump operation, dual pumps in parallel operation, and triple pumps in parallel operation. The prediction result analysis of the correction model based on the number of operating water pumps can be referred to the subsequent content and will not be described in detail here.

[0081] In one embodiment, the present application uses the model error correction coefficient to correct the water pump energy consumption model according to the error analysis results of the water pump energy consumption model when the number of water pumps is different. Among them, when only considering the number of water pumps in operation, the formula can be used The model error correction coefficient was calculated. Finally, based on the 206 sample points of single-pump independent operation, 205 sample points of dual-pump parallel operation, and 165 sample points of triple-pump parallel operation (i.e., 576 model error sample points were obtained from 576 sets of data samples), the correction coefficients of single-pump operation, dual-pump parallel operation, and triple-pump parallel operation were calculated to be 5%, 10%, and 15%, respectively.

[0082] Step S42, based on the model error correction coefficient x m An adjustment ratio is constructed, and a linear relationship is set between the adjustment ratio and the model calculation result.

[0083] Specifically, this application will construct an adjustment ratio based on the model error correction coefficient. This adjustment ratio is a factor used to correct the model calculation results, which reflects the difference between the model prediction results and the actual energy consumption. In specific implementation, this application sets a linear relationship between the adjustment ratio and the model calculation results, which also means that the adjustment ratio can directly affect the model calculation results through proportional adjustment without the need for more complex nonlinear transformations.

[0084] Step S43, correcting the model calculation result based on the adjustment ratio to obtain a corrected water pump energy consumption value.

[0085] Specifically, the present application multiplies the model calculation result by (or divides, depending on the specific form of the adjustment ratio) the adjustment ratio to obtain a corrected water pump energy consumption value. This corrected value is closer to the actual water pump energy consumption because it takes into account possible errors in the model prediction.

[0086] In one embodiment, in step S4, the model error correction coefficient is constructed based on the error analysis result, and the model calculation result is corrected according to the model error correction coefficient to obtain the corrected water pump energy consumption value, including:

[0087] Step S41, when determining that the main operating factors include the number of running water pumps and the running frequency of the water pumps, let the model error correction coefficient be Where m represents the number of running pumps, F represents the range of the running frequency of the pumps, It represents the relative error corresponding to the i-th sample among the m water pump operating condition samples, It represents the average relative error obtained based on the relative errors obtained. Represents the relative error of the ith sample in the sample of m pumps operating in the frequency range F, It represents the floating deviation of the average relative error caused in the F frequency range.

[0088] Specifically, since the operating frequency of the water pump will also affect the calculation results of the energy consumption model, the impact of the water pump operating frequency is relatively small compared to the number of water pumps in operation. This article divides the water pump operating frequency into three ranges, namely 35Hz-40Hz, 40Hz-45Hz and 45Hz-50Hz. When considering the two factors of the number of water pumps in operation and the water pump operating frequency at the same time, the correction coefficients for single pump operation, dual pumps in parallel operation, and triple pumps in parallel operation in the above frequency ranges will be calculated. Among them, the prediction result analysis based on the correction model of the number of water pumps in operation and the water pump operating frequency can be referred to the subsequent content, and no detailed explanation is given here.

[0089] In one embodiment, the present application uses the corresponding model error correction coefficient to correct the water pump energy consumption model according to the error analysis results of the water pump energy consumption model when the water pump operates in different frequency ranges. Among them, when considering the number of water pumps in operation and the water pump operating frequency at the same time, the formula can be used: Finally, based on the 206 sample points of single pump independent operation, 205 sample points of dual pump parallel operation, and 165 sample points of triple pump parallel operation (i.e., 576 model error sample points were obtained from 576 sets of data samples), the correction coefficients x for single pump operation, dual pump parallel operation, and triple pump parallel operation in the three low, medium, and high pump operating frequency ranges of 35Hz-40Hz, 40Hz-45Hz, and 45Hz-50Hz were calculated. m,F See Table 1.

[0090] Table 1 Correction coefficients for the number of running pumps and the running frequency of the pumps

[0091]

[0092] Step S42, based on the model error correction coefficient x m,F An adjustment ratio is constructed, and a linear relationship is set between the adjustment ratio and the model calculation result.

[0093] Step S43, correcting the model calculation result based on the adjustment ratio to obtain a corrected water pump energy consumption value.

[0094] In one embodiment, the model calculation result is corrected by the following formula to obtain the corrected water pump energy consumption value:

[0095]

[0096] in, represents the model calculation results, represents the corrected energy consumption value of the water pump, and x represents the model error correction coefficient.

[0097] Analysis and description of the revised model prediction results:

[0098] (1) Consider only the number of operating pumps

[0099] When only the number of running water pumps is considered, the relative error distribution between the energy consumption calculated by the model and the actual measured energy consumption is shown in Figure 2. Figure 2 .from Figure 2 It can be seen that the average relative errors under single pump operation, dual pump parallel operation, and triple pump parallel operation are greatly reduced, and the confidence intervals of the error samples are also significantly reduced. Among them, when a single pump is operated independently, the average relative errors of 97% of the sample points are concentrated within ±5%; when dual pumps are operated in parallel, the average relative errors of 86% of the sample points are concentrated within ±5%; when triple pumps are operated in parallel, the average relative errors of 78% of the sample points are concentrated within ±5%; comprehensive analysis of all working conditions shows that within the full range of working conditions, the average relative errors of 88% of the sample points are concentrated within ±5%.

[0100] The MRE value and SD (standard deviation) value of the energy consumption correction model are shown in Table 2. The results in Table 2 show that when only the number of running pumps is considered, the MRE value of the water pump energy consumption correction model is close to 0, and the SD value is smaller than before correction, and the error distribution is more concentrated.

[0101] Table 2 MRE and SD values ​​of the energy consumption model before and after correction based on the number of units

[0102]

[0103] (2) Consider the number of pumps in operation and the frequency of pump operation

[0104] When considering the number of running pumps and the running frequency of the pumps at the same time, the energy consumption is calculated according to the pump energy consumption correction model based on the number of running pumps and the running frequency of the pumps. The relative error distribution between the energy consumption calculated by the model and the actual measured energy consumption in different frequency bands is shown in Figure 2. Figure 3 . From the error distribution results, it can be seen that when the number of water pumps in operation is different, the average relative error of each frequency band is greatly reduced, and the difference caused by different frequencies is also small. Among them, when a single pump is running independently, the average relative error of 98% of the sample points is concentrated within ±5%; when two pumps are running in parallel, the average relative error of 93% of the sample points is concentrated within ±5%; when three pumps are running in parallel, the average relative error of 87% of the sample points is concentrated within ±5%. Comprehensively considering all working conditions, it can be seen that within the full range of working conditions, the average relative error of 93% of the sample points is concentrated within ±5%, which is better than the prediction result of the modified model based on the number of units.

[0105] The MRE and SD values ​​of each frequency segment of the energy consumption correction model are shown in Table 3. The results in Table 3 show that the MRE values ​​of the energy consumption correction model of the pumps based on the number and frequency in each frequency segment are close to 0, and the SD values ​​are reduced compared with those before correction, and the error distribution in each frequency segment is more concentrated.

[0106] Table 3 MRE and SD values ​​of the model before and after correction based on the number of operating pumps and the operating frequency of the pumps

[0107]

[0108] In summary, on the one hand, the correction coefficient calculated by this application is applicable to the energy consumption correction of the corresponding working conditions, and does not require additional adjustment, and is universal. On the other hand, under the action of the water pump energy consumption correction model that applies the correction coefficient, the measurement errors of the two water pump energy consumption correction models that consider different working conditions are significantly reduced, and both can meet the requirements of engineering practice. The comparison results of the MRE values ​​and SD values ​​of the two water pump energy consumption correction models in the full frequency range are shown in Table 4. The results show that the MRE values ​​of the two water pump energy consumption correction models are close for single pump operation, dual pump parallel operation, and triple pump parallel operation. The SD value of the water pump energy consumption correction model based on the number of running pumps and the running frequency of the water pumps is smaller, the error is more concentrated, and the accuracy of the correction result is higher.

[0109] Table 4 Comparison of MRE and SD values ​​of two pump energy consumption correction models in the full frequency range

[0110]

[0111] Second, please refer to Figure 4The present application discloses a central air-conditioning water pump energy consumption model error analysis and model correction system, the system includes a theoretical model construction module, an operating condition factor determination module, an error analysis module, and a model correction module, wherein:

[0112] The theoretical model building module is used to obtain the rated power and frequency ratio of the water pump and use them to build a theoretical energy consumption model of the water pump;

[0113] The operating condition factor determination module is used to determine the main operating condition factors that affect the model calculation error, and the main operating condition factors include at least one of the number of running water pumps and the running frequency of the water pumps;

[0114] The error analysis module is used to perform error analysis based on the difference between the model calculation results and the actual energy consumption in all samples within the operating condition range covered by the main operating condition factors;

[0115] The model correction module is used to construct a model error correction coefficient based on the error analysis result, and correct the model calculation result according to the model error correction coefficient to obtain a corrected water pump energy consumption value.

[0116] In one embodiment, the calculation formula of the water pump theoretical energy consumption model includes:

[0117] P=P rate ω 3 ;

[0118] Among them, P represents the actual power of the pump, P rate Indicates the rated power of the pump, ω=f / f rate represents the frequency ratio of the water pump, f represents the actual operating frequency of the water pump, and f rate Indicates the rated frequency of the pump.

[0119] In one embodiment, the operating factor determination module is also used to obtain sample data covering various operating conditions, and the sample data includes the actually observed energy consumption value and the corresponding operating conditions; for each sample, the error between the model calculation result and the actual observed value is calculated; based on the obtained errors, statistical analysis is performed to obtain corresponding error analysis results; based on the error analysis results, the main operating factors that affect the model calculation error are determined.

[0120] In one embodiment, the error analysis module is also used to calculate the difference between the corresponding model calculation result and the actual energy consumption for each sample, and obtain the corresponding relative error based on the ratio of this difference to the actual energy consumption; based on the relative errors corresponding to all samples, the average relative error of the corresponding error analysis result is obtained.

[0121] In one embodiment, the calculation formula of the average relative error includes:

[0122]

[0123] Among them, MRE represents the mean relative error, n represents the number of samples, and δ i represents the relative error corresponding to the i-th sample, represents the model calculation result corresponding to the i-th sample, y i Represents the actual energy consumption corresponding to the i-th sample.

[0124] In one embodiment, the model correction module is further used to determine that the main operating condition factors include the number of running water pumps, and set the model error correction coefficient to Where m represents the number of running pumps. It represents the relative error corresponding to the i-th sample among the m water pump operating condition samples, Represents the average relative error obtained based on the relative errors obtained; based on the model error correction coefficient x m An adjustment ratio is constructed, and a linear relationship is set between the adjustment ratio and the model calculation result; the model calculation result is corrected based on the adjustment ratio to obtain a corrected water pump energy consumption value.

[0125] In one embodiment, the model correction module is further used to determine that the main operating factors include the number of running water pumps and the running frequency of the water pumps, and set the model error correction coefficient to Where m represents the number of running pumps, F represents the range of the running frequency of the pumps, It represents the relative error corresponding to the i-th sample among the m water pump operating condition samples, It represents the average relative error obtained based on the relative errors obtained. Represents the relative error of the ith sample in the sample of m pumps operating in the frequency range F, Represents the floating deviation of the average relative error caused in the F frequency range; based on the model error correction factor x m,F An adjustment ratio is constructed, and a linear relationship is set between the adjustment ratio and the model calculation result; the model calculation result is corrected based on the adjustment ratio to obtain a corrected water pump energy consumption value.

[0126] In one embodiment, the model correction module is further used to correct the model calculation result by the following formula to obtain a corrected water pump energy consumption value:

[0127]

[0128] in, represents the model calculation results, represents the corrected energy consumption value of the water pump, and x represents the model error correction coefficient.

[0129] As can be seen from the above, the central air-conditioning water pump energy consumption model error analysis and model correction system disclosed in the present application performs energy consumption error analysis from two dimensions: the number of running units and the operating frequency. By deeply understanding the internal mechanism of water pump energy consumption changes, it helps to more accurately predict and regulate water pump energy consumption in practical applications; within the range of operating conditions covered by the two dimensions of the number of running units and the operating frequency, error analysis is performed based on the difference between the model calculation results and the actual energy consumption, and the accuracy of the model prediction is quantified, and the conditions under which the model is prone to deviation are identified. This provides a basis for further improving the model; constructing a model error correction coefficient based on the error analysis results, and correcting the model calculation results according to the coefficient can significantly improve the prediction accuracy of the model. This makes the model more valuable for reference in practical applications and helps to achieve more refined energy consumption management.

[0130] It should be noted that the order of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0131] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A central air-conditioning water pump energy consumption model error analysis and model correction method, characterized in that: The method comprises: S1. Obtain the rated power and frequency ratio of the water pump and use them to construct a theoretical energy consumption model of the water pump; S2. Determine the main operating factors that affect the model calculation error, wherein the main operating factors include at least one of the number of operating water pumps and the operating frequency of the water pumps; S3. within the operating range covered by the main operating factors, error analysis is performed based on the difference between the model calculation results and the actual energy consumption in all samples; S4. Constructing a model error correction coefficient based on the error analysis result, and correcting the model calculation result according to the model error correction coefficient to obtain a corrected water pump energy consumption value.

2. The method according to claim 1, characterized in that: In step S1, the calculation formula of the water pump theoretical energy consumption model includes: P=P rate oh 3 ; Among them, P represents the actual power of the pump, P rate Indicates the rated power of the pump, ω=f / f rate represents the frequency ratio of the water pump, f represents the actual operating frequency of the water pump, and f rate Indicates the rated frequency of the pump.

3. The method according to claim 1, characterized in that In step S2, determining the main operating factors that affect the model calculation error includes: S21, obtaining sample data covering various operating conditions, wherein the sample data includes actual measured energy consumption values ​​and corresponding operating conditions; S22. For each sample, calculate the error between the model calculation result and the actual measured energy consumption value; S23, performing statistical analysis based on the obtained errors to obtain corresponding error analysis results; S24. Based on the error analysis results, determine the main operating factors that affect the model calculation error.

4. The method according to claim 1, characterized in that In step S3, within the operating range covered by the main operating factors, error analysis is performed based on the difference between the model calculation results and the actual energy consumption in all samples, including: S31. For each sample, respectively calculate the difference between the corresponding model calculation result and the actual energy consumption, and obtain the corresponding relative error based on the ratio of this difference to the actual energy consumption; S32, calculating the mean of the relative errors corresponding to all samples respectively, and obtaining the average relative error of the corresponding error analysis results.

5. The method according to claim 4, characterized in that The calculation formula of the average relative error includes: Among them, MRE represents the mean relative error, n represents the number of samples, and δ i represents the relative error corresponding to the i-th sample, represents the model calculation result corresponding to the i-th sample, y i Represents the actual energy consumption corresponding to the i-th sample.

6. The method according to claim 1, characterized in that In step S4, the model error correction coefficient is constructed based on the error analysis result, and the model calculation result is corrected according to the model error correction coefficient to obtain the corrected water pump energy consumption value, including: S41. When determining that the main operating factors include the number of running water pumps, let the model error correction coefficient be Among them, m represents the number of running pumps. It represents the relative error corresponding to the i-th sample among the m water pump operating condition samples, It represents the average relative error obtained based on the relative errors obtained; S42, based on the model error correction coefficient x m Constructing an adjustment ratio, and setting a linear relationship between the adjustment ratio and the model calculation result; S43. Correcting the model calculation result based on the adjustment ratio to obtain a corrected water pump energy consumption value.

7. The method according to claim 1, characterized in that In step S4, the model error correction coefficient is constructed based on the error analysis result, and the model calculation result is corrected according to the model error correction coefficient to obtain the corrected water pump energy consumption value, including: S41. When determining that the main operating factors include the number of running water pumps and the running frequency of the water pumps, let the model error correction coefficient be Where m represents the number of running pumps, F represents the range of the running frequency of the pumps, It represents the relative error corresponding to the i-th sample among the m water pump operating condition samples, It represents the average relative error obtained based on the relative errors obtained. Represents the relative error of the ith sample in the sample of m pumps operating in the frequency range F, Indicates the floating deviation of the average relative error caused within the F frequency range; S42, based on the model error correction coefficient x m,F Constructing an adjustment ratio, and setting a linear relationship between the adjustment ratio and the model calculation result; S43. Correcting the model calculation result based on the adjustment ratio to obtain a corrected water pump energy consumption value.

8. The method according to claim 6 or 7, characterized in that: The model calculation results are corrected by the following formula to obtain the corrected water pump energy consumption value: in, Represents the model calculation results, represents the corrected energy consumption value of the water pump, and x represents the model error correction coefficient.

9. A central air-conditioning water pump energy consumption model error analysis and model correction system, characterized in that: The system includes a theoretical model building module, an operating condition factor determination module, an error analysis module, and a model correction module, wherein: The theoretical model building module is used to obtain the rated power and frequency ratio of the water pump and use them to build a theoretical energy consumption model of the water pump; The operating condition factor determination module is used to determine the main operating condition factors that affect the model calculation error, and the main operating condition factors include at least one of the number of running water pumps and the running frequency of the water pumps; The error analysis module is used to perform error analysis based on the difference between the model calculation results and the actual energy consumption in all samples within the operating condition range covered by the main operating condition factors; The model correction module is used to construct a model error correction coefficient based on the error analysis result, and correct the model calculation result according to the model error correction coefficient to obtain a corrected water pump energy consumption value.

Images