A refrigeration system optimization method and device based on error correction

Abstract

The present application belongs to the field of refrigeration control technology, and discloses a refrigeration system optimization method and device based on error correction, the method comprising: obtaining the target demand cooling capacity and current environmental parameters, and inputting them into an optimization model to obtain optimal control parameters and predicted power; constructing a performance curve; the performance curve comprises a temperature cooling curve, a temperature correction curve, and a load correction curve; inputting the optimal control parameters into the performance curve to obtain the actual power; subtracting the actual power from the predicted power to obtain a power error value; judging whether the absolute value of the power error value is less than a preset error threshold; if so, allowing the refrigeration system to operate according to the optimal control parameters; if not, adjusting the cooling water inlet temperature in the optimal control parameters according to the power error value. The present application can correct the errors of the optimal control parameters output by the optimization model, ensuring that the refrigeration system can operate at the optimal power consumption while meeting the target demand cooling capacity.

Description

Technical Field

[0001] The present application relates to the field of refrigeration control technology, and in particular to a refrigeration system optimization method and device based on error correction. Background Art

[0002] Existing research shows that there are many factors that affect the total power of the refrigeration system. In addition to the cooling capacity and outdoor environment, factors such as the cooling water inlet temperature, flow rate, and water pump frequency will also have a certain impact. By establishing a control model for various variables of the refrigeration system and then optimizing the control model, the optimal control strategy of the refrigeration system can be obtained.

[0003] However, due to inherent algorithmic limitations (such as being trapped in local optima), inherent data flaws (such as measurement failures), and overly idealized models, there is inevitably a certain degree of discrepancy between model predictions and actual results. This leads to significant uncertainty in the model's practical application. Data noise, idealized model assumptions, and locally optimal model parameters all contribute to the existence of device model residuals. Given the wide range of residual sources, it is difficult to construct a precise physical model to accurately describe the processes that generate these residuals, resulting in the model's output of an optimal control strategy failing to achieve optimal operational results. Summary of the Invention

[0004] The present application provides a refrigeration system optimization method and device based on error correction, which can correct the errors of the optimal control parameters output by the optimization model, ensuring that the refrigeration system can operate at the optimal power consumption while meeting the target cooling demand.

[0005] In a first aspect, an embodiment of the present application provides a refrigeration system optimization method based on error correction, comprising:

[0006] Obtain the target cooling capacity and current environmental parameters, and input them into the optimization model to obtain the optimal control parameters and predicted power;

[0007] Construct performance curves; performance curves include temperature cooling curves, temperature correction curves, and load correction curves;

[0008] Input the optimal control parameters into the performance curve to obtain the actual power;

[0009] Subtract the actual power from the predicted power to get the power error value;

[0010] Determine whether the absolute value of the power error value is less than a preset error threshold;

[0011] If so, the refrigeration system is operated according to the optimal control parameters;

[0012] If not, the cooling water inlet temperature in the optimal control parameter is adjusted according to the power error value.

[0013] Furthermore, the method further comprises:

[0014] Input the adjusted optimal control parameters into the optimization model to obtain the adjusted predicted power;

[0015] Input the adjusted optimal control parameters into the performance curve to obtain the adjusted actual power;

[0016] The cooling water inlet temperature in the optimal control parameter is adjusted according to the power error value between the predicted power and the actual power until the absolute value of the power error value is less than the preset error threshold.

[0017] Furthermore, the optimal control parameters include the chilled water outlet temperature, chilled water inlet temperature, cooling water outlet temperature, cooling water inlet temperature, cooling tower frequency, chilled water pump flow rate and chilled water pump flow rate of the refrigeration system.

[0018] Furthermore, the method further comprises:

[0019] Obtain historical operating data of the refrigeration system under various working conditions;

[0020] Build water pump energy consumption model, chiller energy consumption model and cooling tower energy consumption model based on historical operation data;

[0021] Construct the power objective function based on the water pump energy consumption model, the chiller energy consumption model and the cooling tower energy consumption model;

[0022] An optimization model is constructed based on the power objective function and preset cooling constraints.

[0023] Furthermore, the historical operation data includes the cooling capacity of the refrigeration system, environmental data, chilled water outlet temperature, chilled water inlet temperature, cooling water outlet temperature, cooling water inlet temperature, cooling tower frequency, chilled water pump flow rate, and chilled water pump flow rate.

[0024] Furthermore, the method further comprises:

[0025] After obtaining the historical operation data, remove the abnormal values ​​in the historical operation data;

[0026] The K-Means algorithm is used to cluster the historical operation data to obtain clustered historical operation data;

[0027] The Min-Max normalization method is used to standardize the clustered historical operation data.

[0028] Furthermore, the above-mentioned removal of outliers in historical operating data includes:

[0029] Statistically analyze the mean and standard deviation of the same variable in historical operating data;

[0030] Determine the limited fluctuation range of the corresponding variable based on the mean value and standard deviation;

[0031] Data outside the specified fluctuation range in the variable are removed as outliers.

[0032] Furthermore, the method further comprises:

[0033] After the refrigeration system is operated according to the optimal control parameters, actual operating parameters of the refrigeration system are obtained;

[0034] Determine whether the actual operating parameters are equal to the optimal control parameters;

[0035] If not, the performance curve is updated based on the actual operating parameters.

[0036] Furthermore, the above-mentioned adjusting the cooling water inlet temperature in the optimal control parameter according to the power error value includes:

[0037] Determine the perturbation temperature step of the cooling water inlet temperature;

[0038] If the power error value is less than 0, add the perturbation temperature step to the cooling water inlet temperature;

[0039] If the power error value is greater than 0, the cooling water inlet temperature is subtracted from the disturbance temperature step.

[0040] In a second aspect, an embodiment of the present application provides a refrigeration system optimization device based on error correction, comprising:

[0041] The parameter optimization module is used to obtain the target cooling capacity and current environmental parameters, and input them into the optimization model to obtain the optimal control parameters and predicted power;

[0042] A curve building module is used to build a performance curve; wherein the performance curve includes a temperature cooling curve, a temperature correction curve and a load correction curve;

[0043] Power calculation module, used to input the optimal control parameters into the performance curve to obtain the actual power;

[0044] An error calculation module is used to subtract the actual power from the predicted power to obtain a power error value;

[0045] A judging module, configured to judge whether the absolute value of the power error value is less than a preset error threshold;

[0046] An operation module, configured to operate the refrigeration system according to the optimal control parameters when the result of the judgment module is yes;

[0047] The error correction module is used to adjust the cooling water inlet temperature in the optimal control parameter according to the power error value when the result of the judgment module is no.

[0048] Furthermore, the error correction module is also used to input the adjusted optimal control parameters into the optimization model, obtain the adjusted predicted power, and return it to the power calculation module; adjust the cooling water inlet temperature in the optimal control parameters according to the power error value between the adjusted predicted power and the adjusted actual power until the absolute value of the power error value is less than the preset error threshold.

[0049] Furthermore, the device also includes:

[0050] A historical data acquisition module is used to obtain historical operating data of the refrigeration system under various working conditions;

[0051] Target architecture module, used to build water pump energy consumption model, chiller energy consumption model and cooling tower energy consumption model based on historical operation data;

[0052] Function construction module, used to construct power objective function based on water pump energy consumption model, chiller energy consumption model and cooling tower energy consumption model;

[0053] The model building module is used to build an optimization model based on the power objective function and preset cooling constraints.

[0054] Furthermore, the device also includes:

[0055] An operation acquisition module is used to obtain actual operation parameters of the refrigeration system after the refrigeration system is operated according to the optimal control parameters;

[0056] The power judgment module is used to judge whether the actual operating parameters are equal to the optimal control parameters;

[0057] The curve updating module is used to update the performance curve based on the actual operating parameters when the result of the power judgment module is negative.

[0058] In a third aspect, an embodiment of the present application provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the processor executes the steps of a refrigeration system optimization method based on error correction as in any of the above embodiments.

[0059] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of a refrigeration system optimization method based on error correction as in any of the above embodiments.

[0060] In summary, compared with the prior art, the technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0061] An embodiment of the present application provides a refrigeration system optimization method based on error correction. After the optimization model outputs the optimal control parameters and the corresponding predicted power based on the target demand cooling capacity and the current environmental parameters, three performance curves, namely, a temperature cooling curve, a temperature correction curve, and a load correction curve, are constructed. The actual power is calculated using the performance curves and the optimal control parameters output by the model. If the power error value between the predicted power output by the model and the actual power exceeds a preset error threshold, the cooling water inlet temperature in the optimal control parameters is corrected according to the power error value, thereby achieving error correction of the optimal control parameters output by the optimization model and ensuring that the refrigeration system can operate at the optimal power consumption while meeting the target demand cooling capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A flowchart of a refrigeration system optimization method based on error correction is provided as an exemplary embodiment of the present application.

[0063] Figure 2 A flowchart of the steps for constructing an optimization model provided for an exemplary embodiment of the present application.

[0064] Figure 3 A flowchart of the steps of pre-processing historical operation data provided by an exemplary embodiment of the present application.

[0065] Figure 4 A schematic diagram of the distribution of historical operating data after filtering outliers is provided for an exemplary embodiment of the present application.

[0066] Figure 5 A schematic diagram of the distribution of historical operating data after clustering provided by an exemplary embodiment of the present application.

[0067] Figure 6 A structural diagram of a refrigeration system optimization device based on error correction is provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0069] Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of this application.

[0070] See Figure 1 , an embodiment of the present application provides a refrigeration system optimization method based on error correction, comprising:

[0071] Step S11: Obtain the target cooling capacity and current environmental parameters, input them into an optimization model, and obtain the optimal control parameters and predicted power. The optimization model aims to solve the problem based on the current target cooling capacity and current outdoor environmental parameters, and obtain the optimal control parameters that can achieve the target cooling capacity and minimize the total power required under the current outdoor environment.

[0072] The process of calculating the optimal control parameters by the optimization model includes data processing and fitting of a multivariate function regression model. However, using a multivariate function model to fit the complex relationship between the various variables of the refrigeration system and the output power will inevitably produce certain model deviations. Therefore, this application corrects the errors of the optimal control parameters through the following steps.

[0073] Step S12, constructing a performance curve; the performance curve includes a temperature cooling curve, a temperature correction curve and a load correction curve.

[0074] The temperature-cooling curve represents the relationship between the system's temperature and cooling capacity, the temperature correction curve represents the relationship between temperature and EIR, and the load correction curve represents the relationship between the partial load factor and EIR. EIR is the inverse of COP, or the ratio of the system's input power to its output cooling capacity. These three performance curves are derived from historical operating data used in fitting the optimization model. These performance curves accurately reflect the operating characteristics of the refrigeration system under actual operating conditions.

[0075] Specifically, the temperature-cooling capacity relationship curve is used to calculate the cooling capacity correction factor CapFunT of the chiller, which determines the functional relationship between the maximum available cooling capacity of the chiller and the chilled water outlet temperature and the cooling water inlet temperature: CapFunT = g 11 +g 12 *T conde,out +g 13 *T conde,out 2 +g 14 *T cw,in +g 15 *T cw,in 2 +g 16 *T conde,out *T cw,in .

[0076] Among them, T conde,out The chilled water outlet temperature can be collected by a sensor installed at the chilled water outlet, and the unit is ℃.

[0077] T cw,in The cooling water inlet temperature can be collected by a sensor installed at the cooling water inlet, and the unit is also ℃.

[0078] g 11 、g12 、g 13 、g 14 、g 15 and g 16 are fitting coefficients.

[0079] Based on the above functional relationship, the maximum available cooling capacity of the chiller can be calculated as shown in the following formula:

[0080] CAP ava =CAP rated * CapFunT

[0081] Among them, CAP ava The maximum available cooling capacity of the chiller in kW; CAP rated is the rated cooling capacity of the chiller, also in kW; CapFunT is the cooling capacity correction factor calculated from the above temperature-cooling capacity relationship curve.

[0082] The temperature-EIR relationship curve is used to calculate the first correction coefficient EIRFunT of the chiller EIR, which determines the functional relationship between the chiller EIR and the chilled water outlet temperature and the cooling water inlet temperature: EIRFunT = g 21 +g 22 *T conde,out +g 23 *T conde,out 2 +g 24 *T cw,in +g 25 *T cw,in 2 +g 26 *T conde,out *T cw,in

[0083] Among them, T conde,out T is the chilled water outlet temperature, in °C; cw,in It is the cooling water inlet temperature, and the unit is also ℃.

[0084] g 21 、g 22 、g 23 、g 24 、g 25 and g 26 is the fitting coefficient.

[0085] The part load rate-EIR relationship curve is used to calculate the second correction factor EIRFunPLR of the chiller EIR. It determines the functional relationship between the chiller EIR and the part load rate, as shown in the following formula:

[0086] EIRFunPLR=g31 +g 32 *PLR+g 33 *PLR 2

[0087] Where PLR ​​is the partial load rate, which is the ratio of the actual cooling capacity of the chiller to the maximum available cooling capacity, where the maximum available cooling capacity is the factory rated value; g 31 、g 32 and g 33 is the fitting coefficient.

[0088] Step S13: input the optimal control parameters into the performance curve to obtain the actual power.

[0089] Finally, the parameter CAP obtained by combining the above three performance curves is ava , EIRFunT and EIRFunPLR calculate the actual power:

[0090]

[0091] Among them, P2 is the actual power of the refrigeration system (chiller), COP rated is the rated COP of the chiller.

[0092] Specifically, the optimal control parameters include the chilled water outlet temperature, chilled water inlet temperature, cooling water outlet temperature, cooling water inlet temperature, cooling tower frequency, chilled water pump flow rate and chilled water pump flow rate of the refrigeration system.

[0093] Step S14: Subtract the actual power from the predicted power to obtain a power error value.

[0094] Step S15: determine whether the absolute value of the power error is less than a preset error threshold.

[0095] Step S16: If yes, the refrigeration system is operated according to the optimal control parameters.

[0096] Step S17: If not, adjust the cooling water inlet temperature in the optimal control parameter according to the power error value.

[0097] Specifically, if the absolute value of the power error value is less than the preset error threshold, it means that there is no error in the output of the optimization model, and the optimal control parameters are directly sent to the refrigeration system for execution. If the absolute value of the power error value is greater than or equal to the preset error threshold, it means that there is an error in the optimization model, and the error is locally optimized.

[0098] Since the power of the refrigeration system is related to the cooling water inlet temperature, to minimize the power of the refrigeration system, the cooling water inlet temperature should be adjusted to an appropriate value to minimize the sum of the power of the freezing side subsystem and the cooling side subsystem.

[0099] Therefore, this application adopts a fixed-step active perturbation algorithm to adjust the cooling water inlet temperature so that the optimal control parameters of the optimization model meet the current operating conditions and the refrigeration system operates in an efficient and energy-saving state.

[0100] First, determine the perturbation temperature step ΔT of the cooling water inlet temperature. This perturbation temperature step ΔT can be set based on historical data and empirical values ​​to ensure that the perturbation is within a safe and effective range. Here, it can be initially set to 1 degree Celsius.

[0101] If the power error value is less than 0, add the cooling water inlet temperature to the disturbance temperature step, that is, set Adjust the cooling water inlet temperature in the direction of increasing the temperature; if the power error value is greater than 0, subtract the disturbance temperature step from the cooling water inlet temperature, that is, set Adjust the cooling water inlet temperature in the direction of lowering the temperature.

[0102] Furthermore, since the perturbation temperature step size for adjusting the cooling water inlet temperature is set based on historical experience, it may happen that the power error value cannot be completely corrected by adjusting it only once.

[0103] Therefore, after adjusting the cooling water inlet temperature of the optimal control parameter, the present application inputs the adjusted optimal control parameter into the optimization model to obtain the adjusted predicted power; inputs the adjusted optimal control parameter into the performance curve to obtain the adjusted actual power; adjusts the cooling water inlet temperature in the optimal control parameter according to the power error value between the predicted power and the actual power, repeats the above steps until the absolute value of the power error value is less than the preset error threshold, and then issues the optimal control parameter.

[0104] The above embodiment provides a refrigeration system optimization method based on error correction. After the optimization model outputs the optimal control parameters and the corresponding predicted power based on the target demand cooling capacity and the current environmental parameters, three performance curves, namely the temperature cooling curve, the temperature correction curve and the load correction curve, are constructed. The actual power is calculated using the performance curves and the optimal control parameters output by the model. If the power error value between the predicted power output by the model and the actual power exceeds the preset error threshold, the cooling water inlet temperature in the optimal control parameters is corrected according to the power error value, thereby realizing the error correction of the optimal control parameters output by the optimization model, and ensuring that the refrigeration system can operate at the optimal power energy consumption while meeting the target demand cooling capacity.

[0105] See Figure 2 In some embodiments, the method further comprises:

[0106] Step S21: Acquire historical operating data of the refrigeration system under various operating conditions.

[0107] Among them, the historical operation data includes the cooling capacity of the refrigeration system, environmental data, chilled water outlet temperature, chilled water inlet temperature, cooling water outlet temperature, cooling water inlet temperature, cooling tower frequency, chilled water pump flow and chilled water pump flow.

[0108] Step S22: constructing a water pump energy consumption model, a chiller energy consumption model, and a cooling tower energy consumption model based on historical operation data.

[0109] Step S23: constructing a power objective function based on the water pump energy consumption model, the chiller energy consumption model, and the cooling tower energy consumption model.

[0110] It is worth noting that when constructing the optimization model, this application adopts a hybrid modeling strategy that integrates mechanism characteristics and data-driven methods. The core advantage of this strategy is that it not only relies on the mechanism model constructed based on physical laws and prior knowledge of equipment, but also integrates actual operation data, aiming to achieve higher prediction accuracy and model generalization capabilities, making it easier to adapt to different operating environments and conditions, and improving the applicability of the model under diverse working conditions.

[0111] First, the water pump power consumption model is: P = P0n 3 ; Where n is the pump speed ratio and P0 is the pump rated power.

[0112]

[0113] V is the water pump flow, including the cooling water pump flow v cool and chilled water pump flow v frozen ; a, b, c are fitting coefficients.

[0114] H is the pump head: H = S a V 2 , S a =S c +S d +S e ; Among them, S a is the pipe network impedance, S c 、S d 、S e They are the cold source equipment impedance, cold source pipeline impedance and terminal pipeline impedance brought by the chiller and water pump respectively.

[0115] The chiller energy consumption model is the relationship between the chiller power and the variables that affect the chiller power:

[0116]

[0117] Among them, a1~a 11 is the fitting coefficient; P chiller is the chiller power, T conde,outis the chilled water outlet temperature, ΔT conde is the chilled water temperature difference, T cw,out is the cooling water outlet temperature, ΔT cw is the cooling water temperature difference, Q chiller is the target cooling capacity required.

[0118] The cooling tower energy consumption model is the relationship between the cooling water outlet temperature and the variables that affect the cooling water outlet temperature:

[0119]

[0120] Among them, g1~g 12 and h1~h3 are fitting coefficients; T cw,out is the cooling water outlet temperature, v cool is the cooling water pump flow rate, f cw is the cooling tower fan frequency, N is the number of cooling towers open, T out Outdoor temperature, H out is the outdoor humidity, (T cw,in -T cw,out ) is the cooling water temperature difference, P cw is the cooling tower power.

[0121] The power objective function of the refrigeration system constructed based on the above three models is:

[0122] minP1=(P chiller +P frozen,pump )+(P cool,pump +P cw )

[0123] Among them, P frozen,pump and P cool,pump They are the chilled water pump power and the cooling water pump power respectively.

[0124] Specifically, the model parameters updated during each training are the fitting coefficients in the above formula.

[0125] Step S24: constructing an optimization model based on the power objective function and the preset cooling constraints.

[0126] The following is the formula expression of the preset cooling constraint:

[0127]

[0128] Among them, the first 7 inequalities are the upper and lower limits of the parameter variables, as well as the two basic principles of the chilled water outlet temperature being lower than the chilled water inlet temperature and the cooling tower outlet water temperature being lower than the cooling tower inlet water temperature. chiller The two formulas are the demand cooling capacity constraint on the freezing side and the heat balance cooling capacity constraint on the cooling side, c wateris the specific heat capacity of water, and finally there are the influence constraints between variables.

[0129] The above three models, power objective function and preset cooling constraints constitute the optimization model.

[0130] The model building process of the above embodiment eliminates those complex factors that contribute little to the model prediction. The simplified model reduces the consumption of computing resources while maintaining sufficient accuracy, so that the model can respond to real-time data more quickly and improve the timeliness of decision-making. At the same time, according to the above model building process, it can be seen that the trained optimization model may fall into local optimality, and as the system equipment runs for a long time, the algorithm model cannot synchronize the attenuation of the hardware equipment, resulting in errors in the prediction results.

[0131] See Figure 3 In some embodiments, the method further comprises:

[0132] Step S31: After obtaining the historical operation data, remove abnormal values ​​in the historical operation data.

[0133] Specifically, we first statistically analyze the mean and standard deviation of the same variable in the historical operating data. We then determine the corresponding variable's limited fluctuation range based on the mean and standard deviation. For example, we add or subtract three times the standard deviation from the mean to arrive at a reasonable limited fluctuation range. Data outside this range is then removed as an outlier. For example, if the variable is cooling water outlet temperature, we calculate the standard deviation and mean of the cooling water outlet temperature in the historical operating data to determine the limited fluctuation range. We then remove temperatures outside this limited fluctuation range. The same process is repeated for other variables in the historical operating data.

[0134] Step S32: clustering the historical operation data using the K-Means algorithm to obtain clustered historical operation data.

[0135] Specifically, see Figure 4 and Figure 5 After filtering out outliers, the historical operating data is discrete and fragmentary. Therefore, it is necessary to use the K-Means clustering algorithm to perform cluster analysis on the historical operating data, and divide the parameters in the historical operating data into K clusters according to the operating conditions; finally, according to the number of numerical values ​​of the parameters corresponding to each operating condition, data selection is performed to obtain steady-state operating condition (typical operating condition) data, so that each operating condition is a data point for model fitting and learning.

[0136] Step S33: Standardize the clustered historical operation data using the Min-Max standardization method.

[0137] Specifically, the dimensions and magnitudes of different variables in the clustered historical operating data vary greatly. In order to avoid weakening the factors with lower values ​​and ensure the reliability of model training, this application further selects the Min-Max normalization method to perform normalization processing, namely:

[0138]

[0139] Among them, x ij represents the original value of the i-th variable in the historical operating data corresponding to the j-th operating condition; y ij Represents the original value x ij The corresponding value after normalization.

[0140] The above embodiment ensures the training efficiency and calculation accuracy of the optimization model by performing operations such as outlier removal, cluster analysis, and standardization processing on the historical operating data used to train the optimization model.

[0141] In some embodiments, the method further comprises:

[0142] Step S41 : After the refrigeration system is operated according to the optimal control parameters, actual operating parameters of the refrigeration system are obtained.

[0143] Step S42: determine whether the actual operating parameters are equal to the optimal control parameters.

[0144] Step S43: If not equal, update the performance curve based on the actual operating parameters.

[0145] Specifically, since the performance of various devices in the refrigeration system may degrade after long-term operation, the actual power calculated by the performance curve cannot be guaranteed to be accurate for a long time.

[0146] Therefore, after delegating the optimal control parameters, the above embodiment obtains the actual operating parameters of the refrigeration system and compares them with the optimal control parameters. If any parameters are not equal, the fitting coefficients in the performance curve are adjusted until the actual power output by the performance curve according to the actual operating parameters remains unchanged.

[0147] See Figure 6 Another embodiment of the present application provides a refrigeration system optimization device based on error correction, comprising:

[0148] The parameter optimization module 101 is used to obtain the target required cooling capacity and current environmental parameters, and input them into the optimization model to obtain the optimal control parameters and predicted power.

[0149] The curve construction module 102 is used to construct a performance curve.

[0150] The performance curve includes a temperature cooling curve, a temperature correction curve, and a load correction curve.

[0151] The power calculation module 103 is used to input the optimal control parameters into the performance curve to obtain the actual power.

[0152] The error calculation module 104 is configured to subtract the actual power from the predicted power to obtain a power error value.

[0153] The judging module 105 is configured to judge whether the absolute value of the power error value is less than a preset error threshold.

[0154] The operation module 106 is configured to enable the refrigeration system to operate according to the optimal control parameters when the result of the judgment module is yes.

[0155] The error correction module 107 is used to adjust the cooling water inlet temperature in the optimal control parameter according to the power error value when the result of the judgment module is no.

[0156] In some embodiments, the error correction module is also used to input the adjusted optimal control parameters into the optimization model, obtain the adjusted predicted power, and return it to the power calculation module; adjust the cooling water inlet temperature in the optimal control parameters according to the power error value between the adjusted predicted power and the adjusted actual power until the absolute value of the power error value is less than the preset error threshold.

[0157] In some embodiments, the apparatus further comprises:

[0158] The historical data acquisition module is used to obtain historical operating data of the refrigeration system under various working conditions.

[0159] The target architecture module is used to construct water pump energy consumption models, chiller energy consumption models and cooling tower energy consumption models based on historical operation data.

[0160] The function construction module is used to construct the power objective function according to the water pump energy consumption model, the chiller energy consumption model and the cooling tower energy consumption model.

[0161] The model building module is used to build an optimization model based on the power objective function and preset cooling constraints.

[0162] In some embodiments, the apparatus further comprises:

[0163] An operation acquisition module is used to obtain actual operation parameters of the refrigeration system after the refrigeration system is operated according to the optimal control parameters;

[0164] The power judgment module is used to judge whether the actual operating parameters are equal to the optimal control parameters;

[0165] The curve updating module is used to update the performance curve based on the actual operating parameters when the result of the power judgment module is negative.

[0166] In some embodiments, the device also includes a data processing module for eliminating outliers in the historical operation data after obtaining the historical operation data; clustering the historical operation data using the K-Means algorithm to obtain clustered historical operation data; and standardizing the clustered historical operation data using the Min-Max standardization method.

[0167] The specific limitations of the error-correction-based refrigeration system optimization device provided in this embodiment can be found in the above embodiment of the error-correction-based refrigeration system optimization method, and will not be repeated here. The various modules in the above-mentioned error-correction-based refrigeration system optimization device can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0168] An embodiment of the present application provides a computer device, which may include a processor, a memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the processor executes the steps of a refrigeration system optimization method based on error correction as described in any of the above embodiments.

[0169] The working process, working details and technical effects of the computer equipment provided in this embodiment can be found in the above embodiment of a refrigeration system optimization method based on error correction, and will not be described in detail here.

[0170] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of a refrigeration system optimization method based on error correction as described in any of the above embodiments are implemented. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive and / or a memory stick, and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The working process, working details, and technical effects of the computer-readable storage medium provided in this embodiment can be found in the above embodiment of a refrigeration system optimization method based on error correction, and will not be repeated here.

[0171] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0172] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0173] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A refrigeration system optimization method based on error correction, characterized in that: include: Obtain the target cooling capacity and current environmental parameters, and input them into the optimization model to obtain the optimal control parameters and predicted power; Construct performance curves; The performance curve includes a temperature cooling curve, a temperature correction curve and a load correction curve; Inputting the optimal control parameter into the performance curve to obtain actual power; Subtracting the actual power from the predicted power to obtain a power error value; Determining whether the absolute value of the power error value is less than a preset error threshold; If so, the refrigeration system is operated according to the optimal control parameters; If not, the cooling water inlet temperature in the optimal control parameter is adjusted according to the power error value; specifically, the disturbance temperature step of the cooling water inlet temperature is determined; if the power error value is less than 0, the disturbance temperature step is added to the cooling water inlet temperature; if the power error value is greater than 0, the disturbance temperature step is subtracted from the cooling water inlet temperature.

2. The refrigeration system optimization method based on error correction according to claim 1, characterized in that: Also includes: Inputting the adjusted optimal control parameters into the optimization model to obtain the adjusted predicted power; Inputting the adjusted optimal control parameters into the performance curve to obtain the adjusted actual power; The cooling water inlet temperature in the optimal control parameter is adjusted according to the power error value between the predicted power and the actual power until the absolute value of the power error value is less than the preset error threshold.

3. The refrigeration system optimization method based on error correction according to claim 1, characterized in that: The optimal control parameters include the chilled water outlet temperature, chilled water inlet temperature, cooling water outlet temperature, cooling water inlet temperature, cooling tower frequency, chilled water pump flow rate and chilled water pump flow rate of the refrigeration system.

4. The refrigeration system optimization method based on error correction according to claim 1, characterized in that: Also includes: Acquiring historical operating data of the refrigeration system under various operating conditions; Constructing a water pump energy consumption model, a chiller energy consumption model, and a cooling tower energy consumption model based on the historical operation data; Construct the power objective function based on the water pump energy consumption model, the chiller energy consumption model and the cooling tower energy consumption model; An optimization model is constructed based on the power objective function and preset cooling constraints.

5. The refrigeration system optimization method based on error correction according to claim 4, characterized in that: The historical operation data includes the cooling capacity of the refrigeration system, environmental data, chilled water outlet temperature, chilled water inlet temperature, cooling water outlet temperature, cooling water inlet temperature, cooling tower frequency, chilled water pump flow rate and chilled water pump flow rate.

6. The refrigeration system optimization method based on error correction according to claim 5, characterized in that: Also includes: After obtaining the historical operation data, eliminating abnormal values ​​in the historical operation data; Using the K-Means algorithm to cluster the historical operation data to obtain clustered historical operation data; The clustered historical operation data is standardized using the Min-Max standardization method.

7. The refrigeration system optimization method based on error correction according to claim 6, characterized in that: The removing of abnormal values ​​from the historical operation data includes: Statistically analyzing the mean value and standard deviation of the same variable in the historical operating data; Determine a limited fluctuation range of the corresponding variable based on the mean value and standard deviation; The data outside the specified fluctuation range of the variables are removed as outliers.

8. The refrigeration system optimization method based on error correction according to claim 1, characterized in that: Also includes: After the refrigeration system is operated according to the optimal control parameters, actual operating parameters of the refrigeration system are obtained; Determining whether the actual operating parameter is equal to the optimal control parameter; If not, the performance curve is updated based on the actual operating parameters.

9. A refrigeration system optimization device based on error correction, characterized in that: include: The parameter optimization module is used to obtain the target cooling capacity and current environmental parameters, and input them into the optimization model to obtain the optimal control parameters and predicted power; A curve construction module is used to construct a performance curve; wherein the performance curve includes a temperature cooling curve, a temperature correction curve and a load correction curve; A power calculation module, configured to input the optimal control parameters into the performance curve to obtain actual power; an error calculation module, configured to subtract the actual power from the predicted power to obtain a power error value; A judging module, configured to judge whether the absolute value of the power error value is less than a preset error threshold; an operating module, configured to, when the result of the judging module is yes, cause the refrigeration system to operate according to the optimal control parameters; an error correction module, configured to adjust the cooling water inlet temperature in the optimal control parameter according to the power error value when the result of the judgment module is negative; specifically, determine a disturbance temperature step of the cooling water inlet temperature; if the power error value is less than 0, add the disturbance temperature step to the cooling water inlet temperature; if the power error value is greater than 0, subtract the disturbance temperature step from the cooling water inlet temperature.

10. The refrigeration system optimization device based on error correction according to claim 9, characterized in that: The error correction module is also used to input the adjusted optimal control parameters into the optimization model, obtain the adjusted predicted power, and return it to the power calculation module; adjust the cooling water inlet temperature in the optimal control parameters according to the power error value between the adjusted predicted power and the adjusted actual power until the absolute value of the power error value is less than the preset error threshold.

11. The refrigeration system optimization device based on error correction according to claim 9, characterized in that: Also includes: A historical data acquisition module, used to acquire historical operating data of the refrigeration system under various working conditions; A target architecture module, configured to construct a water pump energy consumption model, a chiller energy consumption model, and a cooling tower energy consumption model based on the historical operation data; Function construction module, used to construct power objective function based on water pump energy consumption model, chiller energy consumption model and cooling tower energy consumption model; The model building module is used to build an optimization model based on the power objective function and preset cooling constraints.

12. The refrigeration system optimization device based on error correction according to claim 9, characterized in that: Also includes: An operation acquisition module is used to obtain actual operation parameters of the refrigeration system after the refrigeration system is operated according to the optimal control parameters; A power judgment module, configured to judge whether the actual operating parameter is equal to the optimal control parameter; The curve updating module is used to update the performance curve based on actual operating parameters when the result of the power judgment module is negative.

13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the refrigeration system optimization method based on error correction according to any one of claims 1 to 8 are implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the refrigeration system optimization method based on error correction according to any one of claims 1 to 8 are implemented.

Images