Method and system for dynamically adjusting the optimal number and frequency of cooling towers in a cold station

Abstract

The present invention discloses a method and system for dynamically adjusting the optimal number and frequency of cooling towers in a cold station. The method includes: collecting data and performing data preprocessing; screening target values ​​and related characteristic values; statistically analyzing adjustment time points under historical effective operating conditions, and screening and collecting historical data before and after the effective operating conditions according to the target values ​​and characteristic values; establishing a linear regression model for the target values ​​and characteristic values, obtaining the coefficients of the characteristic values, and then obtaining an expression for solving the dynamic adjustment value of the cooling tower frequency; setting restrictive parameters; monitoring the water supply temperature of the main chiller pipe to generate a cooling tower number and frequency adjustment strategy; executing the cooling tower number and frequency adjustment strategy, continuously monitoring, and updating the expression for the dynamic adjustment value of the cooling tower frequency after a certain period. In the natural cooling mode, the present invention enables the cooling tower to maintain the optimal operating state under different conditions, reducing resource waste and achieving energy saving goals.

Description

Technical Field

[0001] The present invention relates to the technical field of energy conservation in large-scale central air-conditioning cooling stations, and in particular to a method and system for dynamically adjusting the optimal number and frequency of cooling towers in a cooling station. Background Art

[0002] Chilling stations are important energy providers in modern buildings and industrial facilities, and their operating efficiency directly impacts overall energy efficiency and operating costs. During chiller operation, cooling towers, as key equipment, are responsible for dissipating heat discharged from cooling water into the atmosphere, thereby maintaining the proper functioning of the refrigeration system and playing a vital role in the energy efficiency of the chiller system. Existing cooling tower control methods for chillers primarily employ PID regulation targeting a fixed cooling water supply temperature. Specifically, a fixed cooling water supply temperature is set as the control target, and a PID (proportional-integral-differential) controller is used to dynamically adjust the number of cooling towers started and stopped, as well as the fan operating frequency, based on the deviation between the current supply temperature and the target temperature. This method is effective in achieving automated control and maintaining stable cooling water temperature, and has been widely used in engineering practice. While this control method offers good temperature control accuracy under steady-state conditions, it suffers from the following drawbacks in actual operation:

[0003] Slow response and low regulation accuracy: Fixed cooling water supply temperature targets are difficult to account for transient changes in the cooling station's environment in real-world operating conditions. The PID control algorithm struggles to accurately and promptly adjust the cooling tower's operating state in response to weather changes, load fluctuations, and chilled water temperature fluctuations, resulting in delayed response and unstable energy consumption across the cooling station system.

[0004] The decoupling issue between cooling tower capacity adjustment and frequency control. Existing solutions typically treat cooling tower capacity switching and fan frequency regulation as independent control steps, lacking a coordinated optimization mechanism. When the cooling station system is at critical load, a "ping-pong effect" occurs, with fans operating at full frequency and adding more towers. This leads to increased equipment wear and additional energy loss. Field data shows that this unnecessary switching can increase equipment maintenance costs by over 25% annually.

[0005] Static parameter settings are mismatched with dynamic operating conditions. Fixed temperature setpoints cannot adapt to the time-varying characteristics of meteorological conditions (such as outdoor wet-bulb and dry-bulb temperatures). The thermodynamic characteristics of high-temperature and high-humidity summer climates differ significantly from those of the transitional spring and autumn climates. Existing technologies use a fixed hysteresis threshold for switching between units, leading to frequent cooling tower starts and stops and oscillating regulation. Statistics show that the resulting inefficient switching can account for 12%-18% of the cooling station's total energy consumption. Summary of the Invention

[0006] In order to solve the above problems, the present invention proposes a method and system for dynamically adjusting the optimal number and frequency of cooling towers in a cold station, which can integrate historical data, real-time operating conditions and future ambient temperature, and can more accurately predict and adjust the optimal number and frequency of cooling towers, effectively improving the dynamic response capability and overall energy efficiency of the adjustment.

[0007] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0008] The method for dynamically adjusting the optimal number and frequency of cooling towers in a cold station of the present invention comprises the following operations:

[0009] Step 1: Collect the forecasted wet-bulb temperature of the area, collect the operating data of each device in the cooling station, and perform data preprocessing to form historical data;

[0010] Step 2: Screen the target value and related feature values ​​and process the data;

[0011] Step 3: Count the adjustment time points under the historical effective working condition adjustment, and screen and collect the historical data before and after the historical effective working condition adjustment according to the target value and characteristic value;

[0012] Step 4: Establish a linear regression model for the target value and the eigenvalue, obtain the coefficient of the eigenvalue, and determine the expression for solving the target value;

[0013] Step 5: Set restrictive parameters;

[0014] Step 6: Monitor the water supply temperature of the chiller main and generate a frequency adjustment strategy for the number of cooling towers based on the limiting parameters;

[0015] Step 7: Execute the frequency adjustment strategy for the number of cooling towers and continuously monitor the water supply temperature of the main chiller. Repeat the cycle from step 6 and execute step 4 after reaching the set period to update the expression for solving the target value.

[0016] The present invention is further improved in that the operating data of each device in the cooling station includes: cooling tower fan switch status feedback value: TOF1, TOF2...TOF n , Cooling tower fan frequency: F1, F2...F n , Chilled main water supply temperature: T s , where n is the device number.

[0017] A further improvement of the present invention is that: the target value screened in step 2 is a dynamic adjustment value of the cooling tower frequency, and the characteristic values ​​include: the difference in the weather forecast wet-bulb temperature between the time of the working condition adjustment and 2 hours after the working condition adjustment, the difference in the water supply temperature of the refrigeration main between the time of the working condition adjustment and 1 hour before the working condition adjustment, and the number of cooling towers in operation before the working condition adjustment;

[0018] After data processing:

[0019] The calculation method of the dynamic adjustment value of the cooling tower frequency is: [(TOF1*F1+TOF2*F2…+TOF n *F n )-(TOF1*F1+TOF2*F2…+TOF 10 minutes before the working condition adjustment n *F n )] / (TOF1+TOF2+…+TOF 10 minutes ago when the working condition is adjusted n );

[0020] The calculation method for the number of cooling tower working units before the working condition adjustment is: the sum of the switch status feedback values ​​of all cooling tower fans 10 minutes before the working condition adjustment.

[0021] A further improvement of the present invention is that the judgment criteria for adjusting the historical effective working conditions in step 3 are:

[0022] Set judgment value: TOF1*F1+TOF2*F2…+TOF n *F n ;

[0023] The time point at which the judgment value changes is recorded as the adjustment time point Tc. The adjustment time point Tc meets the following conditions:

[0024] Adjust the time point Tc, that is, the judgment value calculated at the current minute is not equal to the judgment value calculated by the cooling tower fan switch state feedback value and the cooling tower fan frequency 10 minutes before the current minute;

[0025] The absolute value of the difference between the chiller main water supply temperature 1 hour before the adjustment time point Tc and the chiller main water supply temperature 1 hour after the adjustment time point Tc is less than the set acceptance threshold Td;

[0026] The adjustment time point Tc that meets the conditions is recorded as the adjustment time point Tr of the historical effective working condition adjustment.

[0027] A further improvement of the present invention is that: the specific operation of step 4 includes: assuming that the difference in wet-bulb temperature in the weather forecast during the operating condition adjustment and 2 hours after the operating condition adjustment is X1, the coefficient is b, assuming that the difference in water supply temperature of the freezing main during the operating condition adjustment and 1 hour before the operating condition adjustment is X2, the coefficient is c, assuming that the number of cooling tower working units before the operating condition adjustment is X3, the coefficient is d, assuming that the dynamic adjustment value of the cooling tower frequency is Y, the intercept is a, then solving the target value, that is, the expression of the dynamic adjustment value of the cooling tower frequency is: Y=a+b*X1+c*X2+d*X3, and rounding the obtained result to retain the integer.

[0028] A further improvement of the present invention is that the limiting parameters include the normal range of the freezing main water supply temperature [T lo, T hi ], the minimum chilled main water supply temperature difference T that triggers the generation strategy ch , the minimum wet-bulb temperature difference T that triggers the generation strategy wbt , the minimum time interval of the strategy T i , cooling tower fan full load operation frequency F h , cooling tower fan minimum operating frequency , cooling tower fan number range [T owl , T owh ], the number of cooling tower fans is adjusted in steps of T owc .

[0029] A further improvement of the present invention is that the specific operations of step 6 include:

[0030] Step 6.1: When the time interval from the previous strategy is greater than the minimum time interval T of the strategy i If the current chilled main water supply temperature is greater than the minimum normal value T lo , and is less than the minimum normal value of the freezing main water supply temperature T lo The maximum normal value of the freezing main water supply temperature T hi The average value lasts for 10 minutes and satisfies the following conditions: the difference between the chilled main water supply temperature 1 hour ago and the current chilled main water supply temperature is greater than the minimum chilled main water supply temperature difference T that triggers the generation strategy. ch Or the difference between the current forecast wet-bulb temperature and the forecast wet-bulb temperature 2 hours later is greater than the minimum wet-bulb temperature difference T that triggers the generation strategy. wbt , then start calculating the cooling tower frequency dynamic adjustment value; or the current main chiller water supply temperature is greater than the minimum normal value T lo The maximum normal value of the freezing main water supply temperature T hi The average value of the water supply temperature of the main chiller is less than the maximum normal value T hi , lasts for 10 minutes, and satisfies: the difference between the current chilled main water supply temperature and the chilled main water supply temperature 1 hour ago is greater than the minimum chilled main water supply temperature difference T that triggers the generation strategy ch Or the difference between the forecast wet-bulb temperature in 2 hours and the current forecast wet-bulb temperature is greater than the minimum wet-bulb temperature difference T that triggers the generation strategy. wbt , then start calculating the dynamic adjustment value of the cooling tower frequency;

[0031] Step 6.2: Generate a frequency adjustment strategy for the number of cooling towers based on the calculated dynamic adjustment value of the cooling tower frequency:

[0032] If the cooling tower frequency dynamic adjustment value meets the following conditions: F h ≥[Current(TOF1*F1+TOF2*F2…+TOF n *Fn ) / Current(TOF1+TOF2+…+TOF n )]+Cooling tower frequency dynamic adjustment value ≥ , then the frequency adjustment strategy for the number of cooling towers is: the number of cooling tower fans involved in the adjustment is the current (TOF1+TOF2+…+TOF n ), the frequency is [current (TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )] + cooling tower frequency dynamic adjustment value, the obtained frequency result is rounded to retain the integer;

[0033] If the cooling tower frequency dynamic adjustment value satisfies: [current (TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )]+Cooling tower frequency dynamic adjustment value< Or [Current (TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )]+Cooling tower frequency dynamic adjustment value>F h , then the frequency adjustment strategy for the number of cooling towers is:

[0034] When the cooling tower frequency dynamic adjustment value is less than 0:

[0035] The number of cooling tower fans involved in the regulation is: Current (TOF1+TOF2+…+TOF n )-T owc ;

[0036] Frequency is: [Current (TOF1*F1+TOF2*F2…+TOF n *F n )+Current(TOF1+TOF2+…+TOF n )*Cooling tower frequency dynamic adjustment value] / [Current (TOF1+TOF2+…+TOF n )-T owc ], round the obtained frequency result to an integer;

[0037] When the cooling tower frequency dynamic adjustment value is greater than 0:

[0038] The number of cooling tower fans involved in the regulation is: Current (TOF1+TOF2+…+TOF n )+T owc ;

[0039] Frequency is: [Current (TOF1*F1+TOF2*F2…+TOF n *F n )+Current(TOF1+TOF2+…+TOF n )*Cooling tower frequency dynamic adjustment value] / [Current (TOF1+TOF2+…+TOF n )+T owc ], round the obtained frequency result to an integer;

[0040] If any of the number of cooling tower fans or the frequency involved in the above cooling tower frequency adjustment strategy is greater than the corresponding maximum value, that is, the maximum number of cooling tower fans T owh Or the cooling tower fan full load operation frequency F h , then the frequency adjustment strategy for the number of cooling towers is: the number of cooling tower fans involved in the adjustment is T owh , frequency F h ;

[0041] If any of the number of cooling tower fans or the frequency involved in the cooling tower frequency adjustment strategy is less than the corresponding minimum value, that is, the minimum number of cooling tower fans T owl Or the minimum operating frequency of the cooling tower fan , then the frequency adjustment strategy for the number of cooling towers is: the number of cooling tower fans involved in the adjustment is T owl , the frequency is .

[0042] The optimal number and frequency dynamic adjustment system for cooling towers in a cold station of the present invention comprises:

[0043] The data acquisition module is used to collect the wet-bulb temperature of the weather forecast in the area, collect the operating data of each device in the cooling station, and perform data preprocessing to form historical data;

[0044] Data screening module, used to screen target values ​​and related feature values ​​for data processing;

[0045] The data statistics module is used to count the adjustment time points under the historical effective working condition adjustment, and to filter and collect the historical data before and after the historical effective working condition adjustment according to the target value and characteristic value;

[0046] The model building module is used to build a linear regression model for the target value and the eigenvalue, obtain the coefficient of the eigenvalue, and determine the expression for solving the target value;

[0047] Parameter setting module, used to set restrictive parameters;

[0048] The strategy generation module is used to monitor the water supply temperature of the chilled main pipe, generate a cooling tower frequency adjustment strategy based on the restrictive parameters, execute the cooling tower frequency adjustment strategy, continuously monitor the water supply temperature of the chilled main pipe, and update the expression for solving the target value after reaching the set period.

[0049] The beneficial effects of the present invention are as follows: the present invention combines historical data and a linear regression model to provide a new solution for the dynamic adjustment of cooling towers in cold stations, which can achieve the following effects:

[0050] Dynamic optimization: It fully considers the dynamic changes of the environment and the cooling station system and can adjust the operating status of the cooling tower in real time.

[0051] Energy saving and high efficiency: By accurately adjusting the number and frequency of cooling tower operations, the energy consumption of the cooling station system can be significantly reduced.

[0052] Fast response: Utilize historical data and linear regression models to improve the response speed and accuracy of adjustments.

[0053] Reduce operating costs: Extend equipment life and reduce maintenance costs caused by frequent starts and stops. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention;

[0055] Figure 2 Comparison chart of actual values ​​and fitted values ​​in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only intended to illustrate the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0057] like Figure 1 As shown, this embodiment is a method for dynamically adjusting the optimal number and frequency of cooling towers in a cold station under natural cooling mode, including the following operations:

[0058] Step 1: Collect the operating data of each device in the cooling station from the BA (Building Automation System) group control system and perform data preprocessing. Collect the hourly weather forecast wet bulb temperature of the area and perform data preprocessing to form historical data. Data preprocessing includes deleting abnormal data and interpolating missing data. The collected operating data of each device in the cooling station includes: cooling tower fan switch status feedback value: TOF1, TOF2...TOF n, Cooling tower fan frequency: F1, F2...F n , Chilled main water supply temperature: T s , where n is the device number.

[0059] Step 2: Filter the target value and related characteristic values ​​and perform data processing, including data standardization or normalization. The target value is the cooling tower frequency dynamic adjustment value. The characteristic values ​​include: the difference in weather forecast wet-bulb temperature between the operating condition adjustment and 2 hours after the operating condition adjustment, the difference in chiller main water supply temperature between the operating condition adjustment and 1 hour before the operating condition adjustment, and the number of cooling towers operating before the operating condition adjustment.

[0060] The target value and eigenvalue are calculated as follows after standardization:

[0061] Cooling tower frequency dynamic adjustment value: [(TOF1*F1+TOF2*F2…+TOF n *F n )-(TOF1*F1+TOF2*F2…+TOF 10 minutes before the working condition adjustment n *F n )] / (TOF1+TOF2+…+TOF 10 minutes ago when the working condition is adjusted n ), the cooling tower frequency dynamic adjustment value calculated in this way is the historical actual value of the target value;

[0062] The difference between the forecast wet-bulb temperature at the time of working condition adjustment and 2 hours after working condition adjustment: the difference between the forecast wet-bulb temperature 2 hours after working condition adjustment minus the forecast wet-bulb temperature at the time of working condition adjustment;

[0063] The difference between the chilled main water supply temperature during the working condition adjustment and 1 hour before the working condition adjustment is: the chilled main water supply temperature during the working condition adjustment minus the chilled main water supply temperature 1 hour before the working condition adjustment;

[0064] Number of cooling towers working before working condition adjustment: the sum of all cooling tower fan switch status feedback values ​​10 minutes before working condition adjustment, that is, TOF1+TOF2+…+TOF n .

[0065] Step 3: Count the adjustment time points under historical effective working condition adjustment, and screen and collect historical data before and after the effective working condition according to the target value and characteristic value.

[0066] The screening criteria for historical effective operating condition adjustments are:

[0067] Set judgment value: TOF1*F1+TOF2*F2…+TOF n *F n ;

[0068] The time point at which the judgment value changes is recorded as the adjustment time point Tc. The adjustment time point Tc meets the following conditions:

[0069] Adjust the time point Tc, that is, the judgment value calculated at the current minute (current time point) is not equal to the judgment value calculated by the cooling tower fan switch state feedback value and the cooling tower fan frequency 10 minutes before the current minute;

[0070] The absolute value of the difference between the main refrigeration pipe water supply temperature 1 hour before the adjustment time point Tc and the main refrigeration pipe water supply temperature 1 hour after the adjustment time point Tc is less than the set acceptable threshold Td. In this embodiment, the acceptable threshold Td is set to 0.3.

[0071] The adjustment time point Tc that meets the conditions is recorded as the adjustment time point Tr of the historical effective working condition adjustment.

[0072] Step 4: Establish a linear regression model for the target value and the characteristic value to obtain the coefficient of the characteristic value, and then obtain the expression for solving the target value, that is, the dynamic adjustment value of the cooling tower frequency.

[0073] Perform a linear regression fit, with feature X1 being the "Weather forecast wet-bulb temperature difference between the operating condition adjustment and 2 hours after the adjustment" column data, feature X2 being the "Chiller main supply water temperature difference between the operating condition adjustment and 1 hour before the adjustment" column data, feature X3 being the "Number of cooling towers before the adjustment" column data, and target value Y being the "Dynamic adjustment value of cooling tower frequency." Let a be the intercept, b be the coefficient of X1, c be the coefficient of X2, and d be the coefficient of X3. The expression for the dynamic adjustment value of cooling tower frequency is: Y = a + b * X1 + c * X2 + d * X3. Round the result to the nearest integer.

[0074] Step 5: Set the limiting parameters, including the normal range of the chilled main water supply temperature [T lo , T hi ], the minimum chilled main water supply temperature difference T that triggers the generation strategy ch , the minimum wet-bulb temperature difference T that triggers the generation strategy wbt , the minimum time interval of the strategy T i , cooling tower fan full load operation frequency F h , cooling tower fan minimum operating frequency , cooling tower fan number range [T owl , T owh ], the number of cooling tower fans is adjusted in steps of T owc .

[0075] Step 6: Monitor the water temperature of the main chiller. If the water temperature of the main chiller is within the range (T lo , T hi), a frequency adjustment strategy for the number of cooling towers is generated.

[0076] The process of generating a cooling tower frequency adjustment strategy includes:

[0077] The time interval between the previous strategy is greater than the minimum time interval T of the strategy i Under the conditions:

[0078] 1. If the current main chiller water supply temperature is greater than the minimum normal value of the main chiller water supply temperature T lo , and is less than the minimum normal value of the freezing main water supply temperature T lo The maximum normal value of the freezing main water supply temperature T hi The average value of T lo <Current main chiller water supply temperature <(T lo +T hi ) / 2, lasts for 10 minutes, and satisfies:

[0079] ① The difference between the chilled main water supply temperature 1 hour ago and the current chilled main water supply temperature is greater than the minimum chilled main water supply temperature difference T that triggers the generation strategy. ch , that is, the main chiller water supply temperature 1 hour ago - the current main chiller water supply temperature > T ch ; or ② the difference between the current forecast wet-bulb temperature and the forecast wet-bulb temperature 2 hours later is greater than the minimum wet-bulb temperature difference T that triggers the generation strategy wbt , that is, the current weather forecast wet bulb temperature - the weather forecast wet bulb temperature 2 hours later > T wbt , then calculate the dynamic adjustment value of the cooling tower frequency according to the calculation method in step 4.

[0080] 2. If the current main chiller water supply temperature is greater than the minimum normal value T lo The maximum normal value of the freezing main water supply temperature T hi The average value of the water supply temperature of the main chiller is less than the maximum normal value T hi , that is (T lo +T hi ) / 2<Current main chiller water supply temperature<T hi , lasting 10 minutes, and meeting:

[0081] ① The difference between the current chilled main water supply temperature and the chilled main water supply temperature 1 hour ago is greater than the minimum chilled main water supply temperature difference T that triggers the generation strategy. ch , that is, the current main chiller water supply temperature - the main chiller water supply temperature 1 hour ago > T ch ; or ② The difference between the forecast wet-bulb temperature 2 hours later and the current forecast wet-bulb temperature is greater than the minimum wet-bulb temperature difference T that triggers the generation strategy wbt , that is, the forecast wet-bulb temperature 2 hours later - the current forecast wet-bulb temperature > Twbt , then calculate the cooling tower frequency dynamic adjustment value according to the calculation method of step 4;

[0082] Based on the calculated value of the dynamic adjustment value of the cooling tower frequency, the frequency adjustment strategy for the number of cooling towers is generated:

[0083] 1) If the cooling tower frequency dynamic adjustment value meets: F h ≥[Current(TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )]+Cooling tower frequency dynamic adjustment value ≥ , then the frequency adjustment strategy for the number of cooling towers is: the number of cooling tower fans involved in the adjustment is the current (TOF1+TOF2+…+TOF n ), the frequency is [current (TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )] + cooling tower frequency dynamic adjustment value, the obtained frequency result is rounded to retain the integer;

[0084] 2) If the cooling tower frequency dynamic adjustment value satisfies: [Current (TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )]+Cooling tower frequency dynamic adjustment value< Or [Current (TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )]+Cooling tower frequency dynamic adjustment value>F h , then the frequency adjustment strategy for the number of cooling towers is:

[0085] When the cooling tower frequency dynamic adjustment value is less than 0:

[0086] The number of cooling tower fans involved in the regulation is: Current (TOF1+TOF2+…+TOF n )-T owc ;

[0087] Frequency is: [Current (TOF1*F1+TOF2*F2…+TOF n *F n )+Current(TOF1+TOF2+…+TOF n)*Cooling tower frequency dynamic adjustment value] / [Current (TOF1+TOF2+…+TOF n )-T owc ], and round the obtained frequency result to an integer.

[0088] When the cooling tower frequency dynamic adjustment value is greater than 0:

[0089] The number of cooling tower fans involved in the regulation is: Current (TOF1+TOF2+…+TOF n )+T owc ;

[0090] Frequency is: [Current (TOF1*F1+TOF2*F2…+TOF n *F n )+Current(TOF1+TOF2+…+TOF n )*Cooling tower frequency dynamic adjustment value] / [Current (TOF1+TOF2+…+TOF n )+T owc ], and round the obtained frequency result to an integer.

[0091] If any of the number of cooling tower fans or the frequency involved in the above cooling tower frequency adjustment strategy is greater than the corresponding maximum value, that is, the maximum number of cooling tower fans T owh Or the cooling tower fan full load operation frequency F h , then the frequency adjustment strategy for the number of cooling towers is: the number of cooling tower fans involved in the adjustment is T owh , frequency F h ;

[0092] If any of the number of cooling tower fans or the frequency involved in the cooling tower frequency adjustment strategy is less than the corresponding minimum value, that is, the minimum number of cooling tower fans T owl Or the minimum operating frequency of the cooling tower fan , then the frequency adjustment strategy for the number of cooling towers is: the number of cooling tower fans involved in the adjustment is T owl , the frequency is .

[0093] Step 7: Execute the cooling tower frequency adjustment strategy and continuously monitor the chiller main water supply temperature. The cycle repeats from step 6. After the set period is reached, execute step 4 to update the target value, i.e., the expression for the dynamic adjustment value of the cooling tower frequency. In this embodiment, the monitoring frequency is set to every minute. The repetition period of step 4 is set to one week.

[0094] The above method is implemented by the optimal number and frequency dynamic adjustment system of cooling towers in a cold station of this embodiment, which includes:

[0095] The data acquisition module is used to collect the wet-bulb temperature of the weather forecast in the area, collect the operating data of each device in the cooling station, and perform data preprocessing to form historical data;

[0096] Data screening module, used to screen target values ​​and related feature values ​​for data processing;

[0097] The data statistics module is used to count the adjustment time points under the historical effective working condition adjustment, and to filter and collect the historical data before and after the historical effective working condition adjustment according to the target value and characteristic value;

[0098] The model building module is used to build a linear regression model for the target value and the eigenvalue, obtain the coefficient of the eigenvalue, and then obtain the expression for solving the target value;

[0099] Parameter setting module, used to set the limiting parameters, including the normal range of the main chilled water supply temperature [T lo , T hi ], the minimum chilled main water supply temperature difference T that triggers the generation strategy ch , the minimum wet-bulb temperature difference T that triggers the generation strategy wbt , the minimum time interval of the strategy T i , cooling tower fan full load operation frequency F h , cooling tower fan minimum operating frequency , cooling tower fan number range [T owl , T owh ], the number of cooling tower fans is adjusted in steps of T owc ;

[0100] Strategy generation module, used to monitor the main chiller water supply temperature, if the current main chiller water supply temperature is within the value range (T lo , T hi ), a frequency adjustment strategy for the number of cooling towers is generated, and the control points of the BA (building automation system) group control system execute the frequency adjustment strategy for the number of cooling towers, continuously monitor the water supply temperature of the chilled main, and update the expression for solving the target value after reaching the set period.

[0101] In order to further illustrate the specific operation of the method of the present invention, a specific cold station is taken as an example below:

[0102] In step 1, the current minute operation data collected include: cooling tower fan switch status feedback value: (1, 1, 1, 1, 1, 1); cooling tower fan frequency: (39.7, 39.5, 39.8, 39.5, 39.6, 39.8); main chiller water supply temperature: 12.70.

[0103] In step 2, when the frequency of cooling tower unit operation adjustment occurs in the historical data, the following data are collected during the operation adjustment: cooling tower fan switch status feedback value: (1, 1, 1, 1, 1, 1); cooling tower fan frequency: (32.7, 32.5, 32.8, 32.5, 32.6, 32.8); chiller main water supply temperature feedback value: 12.57. The data collected 10 minutes before the operation adjustment is: cooling tower fan switch status feedback value: (0, 1, 1, 1, 1, 1); cooling tower fan frequency: (2.1, 32.6, 32.7, 32.7, 32.5, 32.8); chiller main water supply temperature feedback value: 12.19. The current weather forecast wet-bulb temperature is 3; the weather forecast wet-bulb temperature 2 hours later is 6.2. The target value and the calculation results after feature normalization are as follows:

[0104] Cooling tower frequency dynamic adjustment value: [(TOF1*F1+TOF2*F2…+TOF n *F n )-(TOF1*F1+TOF2*F2…+TOF 10 minutes before the working condition adjustment n *F n )] / (TOF1+TOF2+…+TOF 10 minutes ago when the working condition is adjusted n )=[(1*32.7+1*32.5+1*32.8+1*32.5+1*32.8+1*32.8)-(0*2.1+1*32.6+1*32.7+1*32.7+1*32.5+1*32.8)] / (0+1+1+1+1+1)=6.6;

[0105] The difference between the weather forecast wet-bulb temperature at the time of working condition adjustment and 2 hours after working condition adjustment is 3.2;

[0106] The difference in water supply temperature of the chilled main during the working condition adjustment and 1 hour before the working condition adjustment is 0.38;

[0107] Number of cooling towers working before working condition adjustment: (TOF1+TOF2+…+TOF n )=(0+1+1+1+1+1)=5.

[0108] In step 3, some of the results of data screening and collection of historical data before and after the effective working condition according to the target value and characteristic value are shown in the following table:

[0109] Table 1: Data screening results

[0110]

[0111] In step 4, the linear regression fitting results are shown in Table 2. The intercept is 7.37, the coefficient of X1 is 0.57, the coefficient of X2 is 9.47, the coefficient of X3 is -1.45, and the dynamic adjustment value of the cooling tower frequency = 7.37 + 0.57 * X1 + 9.47 * X2 - 1.45 * X3.

[0112] Table 2: Linear regression fitting results

[0113]

[0114] The target value is obtained by solving the expression of the dynamic adjustment value of the cooling tower frequency. Compared with the historical actual value of the target value, it has a relatively high degree of fit, such as Figure 2 shown.

[0115] In step 5, set the limiting parameters: normal range of chilled main water supply temperature [T lo , T hi ] is [12.5, 13.5], the minimum chilled main water supply temperature difference T that triggers the generation strategy ch The minimum wet-bulb temperature difference T that triggers the generation strategy is 0.5. wbt is 0.7, the minimum time interval of the strategy is T i For 60 minutes, the cooling tower fan is fully loaded and the frequency F h The minimum operating frequency of the cooling tower fan is 48Hz. The frequency is 30Hz, and the number of cooling tower fans is adjusted in steps of T. owc For 1 unit.

[0116] In step 6, the previous policy was issued 150 minutes ago, and the interval since the previous policy is greater than 60 minutes. Monitoring shows that the chilled water temperature over the past 10 minutes was (12.81, 12.82, 12.80, 12.79, 12.77, 12.76, 12.75, 12.75, 12.74, 12.70). The chilled main supply water temperature was 12.93°C one hour ago. The current forecast wet-bulb temperature is 5.3°C, and the forecast wet-bulb temperature in two hours is 3.7°C. The current cooling tower fan on / off status feedback values ​​are (1, 1, 1, 1, 1, 1); the current cooling tower fan frequency is (39.7, 39.5, 39.8, 39.5, 39.6, 39.8). The current number of cooling towers is 6, 12.5 < current chiller main water supply temperature < (12.5 + 13.5) / 2 for 10 minutes, and the current weather forecast wet-bulb temperature - the weather forecast wet-bulb temperature 2 hours later = 5.3 - 3.7 = 1.6 > 0.7, then the cooling tower frequency dynamic adjustment value is calculated as = 7.37 + 0.57 * (5.5 - 3.7) + 9.47 * (12.70 - 12.93) - 1.45 * 6 = -3.6, which is rounded to an integer and is -4. [Current (TOF1 * F1 + TOF2 * F2 ... + TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )] + Cooling tower frequency dynamic adjustment value = (1*39.7+1*39.5+1*39.8+1*39.5+1*39.6+1*39.8) / 6-4 = 35.65, where 30 < 35.65 < 48. Therefore, the cooling tower frequency adjustment strategy is: the number of cooling tower fans participating in the adjustment remains unchanged at the current 6 units, with a frequency of 36 Hz.

[0117] In summary, through real-time monitoring and adjustment, in natural cooling mode, the cooling tower can maintain optimal operating status under different conditions, reduce resource waste and achieve energy-saving goals.

[0118] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and, unless defined similarly as herein, will not be interpreted in an idealized or overly formal sense.

[0119] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for dynamically adjusting the optimal number and frequency of cooling towers in a cold station, characterized by: The following operations are included: Step 1: Collect the forecasted wet-bulb temperature of the area, collect the operating data of each device in the cooling station, and perform data preprocessing to form historical data; Step 2: Screen the target value and related feature values ​​and process the data; Step 3: Count the adjustment time points under the historical effective working condition adjustment, and screen and collect the historical data before and after the historical effective working condition adjustment according to the target value and characteristic value; Step 4: Establish a linear regression model for the target value and the eigenvalue, obtain the coefficient of the eigenvalue, and determine the expression for solving the target value; Step 5: Set restrictive parameters; Step 6: Monitor the water supply temperature of the chiller main and generate a frequency adjustment strategy for the number of cooling towers based on the limiting parameters; Step 7: Execute the cooling tower frequency adjustment strategy and continuously monitor the chiller main water supply temperature. Repeat the cycle from step 6 and execute step 4 after reaching the set period to update the expression for solving the target value. The operating data of each equipment in the cooling station include: cooling tower fan switch status feedback value: TOF1, TOF2...TOF n , Cooling tower fan frequency: F1, F2...F n , Chilled main water supply temperature: T s , where n is the device number; The target value screened in step 2 is the dynamic adjustment value of the cooling tower frequency, and the characteristic values ​​include: the difference in the weather forecast wet-bulb temperature between the working condition adjustment and the working condition adjustment 2 hours later, the difference in the refrigeration main water supply temperature between the working condition adjustment and the working condition adjustment 1 hour before the working condition adjustment, and the number of cooling towers in operation before the working condition adjustment; After data processing: The calculation method of the dynamic adjustment value of the cooling tower frequency is: [(TOF1*F1+TOF2*F2…+TOF n *F n )-(TOF1*F1+TOF2*F2…+TOF 10 minutes before the working condition adjustment n *F n )] / (TOF1+TOF2+…+TOF 10 minutes ago when the working condition is adjusted n ); The calculation method for the number of cooling tower working units before the working condition adjustment is: the sum of the on-off status feedback values ​​of all cooling tower fans 10 minutes before the working condition adjustment; The judgment criteria for adjusting the historical effective working conditions in step 3 are: Set judgment value: TOF1*F1+TOF2*F2…+TOF n *F n ; The time point at which the judgment value changes is recorded as the adjustment time point Tc. The adjustment time point Tc meets the following conditions: Adjust the time point Tc, that is, the judgment value calculated at the current minute is not equal to the judgment value calculated by the cooling tower fan switch state feedback value and the cooling tower fan frequency 10 minutes before the current minute; The absolute value of the difference between the chiller main water supply temperature 1 hour before the adjustment time point Tc and the chiller main water supply temperature 1 hour after the adjustment time point Tc is less than the set acceptance threshold Td; The adjustment time point Tc that meets the conditions is recorded as the adjustment time point Tr of the historical effective working condition adjustment; The specific operation of step 4 includes: assuming that the difference in the wet-bulb temperature of the weather forecast during the working condition adjustment and 2 hours after the working condition adjustment is X1, the coefficient is b, assuming that the difference in the water supply temperature of the refrigeration main during the working condition adjustment and 1 hour before the working condition adjustment is X2, the coefficient is c, assuming that the number of cooling tower working units before the working condition adjustment is X3, the coefficient is d, assuming that the dynamic adjustment value of the cooling tower frequency is Y, the intercept is a, then solving the target value, that is, the expression of the dynamic adjustment value of the cooling tower frequency is: Y=a+b*X1+c*X2+d*X3, and rounding the obtained result to retain the integer; Limiting parameters include the normal range of chilled main water supply temperature [T lo , T hi ], the minimum chilled main water supply temperature difference T that triggers the generation strategy ch , the minimum wet-bulb temperature difference T that triggers the generation strategy wbt , the minimum time interval of the strategy T i , cooling tower fan full load operation frequency F h , cooling tower fan minimum operating frequency , cooling tower fan number range [T owl , T owh ], the number of cooling tower fans is adjusted in steps of T owc .

2. The method for dynamically adjusting the optimal number and frequency of cooling towers in a cold station according to claim 1, characterized in that: The specific operations of step 6 include: Step 6.1: When the time interval from the previous strategy is greater than the minimum time interval T of the strategy i If the current chilled main water supply temperature is greater than the minimum normal value T lo , and is less than the minimum normal value of the freezing main water supply temperature T lo The maximum normal value of the freezing main water supply temperature T hi The average value lasts for 10 minutes and satisfies the following conditions: the difference between the chilled main water supply temperature 1 hour ago and the current chilled main water supply temperature is greater than the minimum chilled main water supply temperature difference T that triggers the generation strategy. ch Or the difference between the current forecast wet-bulb temperature and the forecast wet-bulb temperature 2 hours later is greater than the minimum wet-bulb temperature difference T that triggers the generation strategy. wbt , then start calculating the cooling tower frequency dynamic adjustment value; or the current main chiller water supply temperature is greater than the minimum normal value T lo The maximum normal value of the freezing main water supply temperature T hi The average value of the water supply temperature of the main chiller is less than the maximum normal value T hi , lasts for 10 minutes, and satisfies: the difference between the current chilled main water supply temperature and the chilled main water supply temperature 1 hour ago is greater than the minimum chilled main water supply temperature difference T that triggers the generation strategy ch Or the difference between the forecast wet-bulb temperature in 2 hours and the current forecast wet-bulb temperature is greater than the minimum wet-bulb temperature difference T that triggers the generation strategy. wbt , then start calculating the dynamic adjustment value of the cooling tower frequency; Step 6.2: Generate a frequency adjustment strategy for the number of cooling towers based on the calculated dynamic adjustment value of the cooling tower frequency: If the cooling tower frequency dynamic adjustment value meets the following conditions: F h ≥[Current(TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )]+Cooling tower frequency dynamic adjustment value ≥ , then the frequency adjustment strategy for the number of cooling towers is: the number of cooling tower fans involved in the adjustment is the current (TOF1+TOF2+…+TOF n ), the frequency is [current (TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )] + cooling tower frequency dynamic adjustment value, the obtained frequency result is rounded to retain the integer; If the cooling tower frequency dynamic adjustment value satisfies: [current (TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )]+Cooling tower frequency dynamic adjustment value< Or [Current (TOF1*F1+TOF2*F2…+TOF n *F n ) / Current(TOF1+TOF2+…+TOF n )]+Cooling tower frequency dynamic adjustment value>F h , then the frequency adjustment strategy for the number of cooling towers is: When the cooling tower frequency dynamic adjustment value is less than 0: The number of cooling tower fans involved in the regulation is: Current (TOF1+TOF2+…+TOF n )-T owc ; Frequency is: [Current (TOF1*F1+TOF2*F2…+TOF n *F n )+Current(TOF1+TOF2+…+TOF n )*Cooling tower frequency dynamic adjustment value] / [Current (TOF1+TOF2+…+TOF n )-T owc ], round the obtained frequency result to an integer; When the cooling tower frequency dynamic adjustment value is greater than 0: The number of cooling tower fans involved in the regulation is: Current (TOF1+TOF2+…+TOF n )+T owc ; Frequency is: [Current (TOF1*F1+TOF2*F2…+TOF n *F n )+Current(TOF1+TOF2+…+TOF n )*Cooling tower frequency dynamic adjustment value] / [Current (TOF1+TOF2+…+TOF n )+T owc ], round the obtained frequency result to an integer; If any of the number of cooling tower fans or the frequency involved in the above cooling tower frequency adjustment strategy is greater than the corresponding maximum value, that is, the maximum number of cooling tower fans T owh Or the cooling tower fan full load operation frequency F h , then the frequency adjustment strategy for the number of cooling towers is: the number of cooling tower fans involved in the adjustment is T owh , frequency F h ; If any of the number of cooling tower fans or the frequency involved in the cooling tower frequency adjustment strategy is less than the corresponding minimum value, that is, the minimum number of cooling tower fans T owl Or the minimum operating frequency of the cooling tower fan , then the frequency adjustment strategy for the number of cooling towers is: the number of cooling tower fans involved in the adjustment is T owl , the frequency is .

3. A system based on the method for dynamically adjusting the optimal number and frequency of cooling towers in a cold station according to any one of claims 1 to 2, characterized in that: include: The data acquisition module is used to collect the wet-bulb temperature of the weather forecast in the area, collect the operating data of each device in the cooling station, and perform data preprocessing to form historical data; Data screening module, used to screen target values ​​and related feature values ​​for data processing; The data statistics module is used to count the adjustment time points under the historical effective working condition adjustment, and to filter and collect the historical data before and after the historical effective working condition adjustment according to the target value and characteristic value; The model building module is used to build a linear regression model for the target value and the eigenvalue, obtain the coefficient of the eigenvalue, and determine the expression for solving the target value; Parameter setting module, used to set restrictive parameters; The strategy generation module is used to monitor the water supply temperature of the chilled main pipe, generate a cooling tower frequency adjustment strategy based on the restrictive parameters, execute the cooling tower frequency adjustment strategy, continuously monitor the water supply temperature of the chilled main pipe, and update the expression for solving the target value after reaching the set period.

Images