Cooling tower fan current prediction method, fault detection method and related device

Abstract

The invention provides a cooling tower fan current prediction method, a fault detection method and related devices. A method for detecting a fault of a cooling tower includes: acquiring a power value, a frequency value, and a current value associated with each other measured for a fan of the cooling tower; predicting a current value of a fan of the cooling tower according to the measured power value and the measured frequency value by using a prediction model, wherein the prediction model is a function of current with respect to power and frequency; and under the condition that the difference value between the predicted current value and the measured current value is larger than a difference value threshold value, an alarm is given to indicate that the fault of the cooling tower is detected.

Description

Technical Field

[0001] The present disclosure relates to the technical field of cooling towers, and more particularly, to a method for predicting the current of a fan of a cooling tower, a method and device for detecting a fault of a cooling tower, a computing device, a non-transitory storage medium, and a computer program product. Background Art

[0002] A cooling tower is an important part of a refrigeration system and often plays a role in dissipating heat for a chiller or a plate heat exchanger in the HVAC architecture of a data center. Its core principle is usually to transfer the heat in the cooling water to the air by means of direct or indirect contact between the cooling water and the air, using evaporation heat dissipation, convective heat transfer, and conductive heat transfer, etc., so as to reduce the water temperature.

[0003] A cooling tower usually consists of a tower body, packing, a fan, etc. The packing is used to increase the contact area between the cooling water and the air and improve the heat transfer efficiency. The fan accelerates the air flow through forced ventilation to enhance the cooling effect. The fan usually includes a fan and a motor for driving the fan. Due to the large volume of the fan of the cooling tower, the currently put into production cooling tower fans usually use asynchronous motors, which are indirectly driven by a speed reducer and a transmission belt. Summary of the Invention

[0004] A brief overview of the present disclosure is given below to provide a basic understanding of some aspects of the present disclosure. However, it should be understood that this overview is not an exhaustive overview of the present disclosure. It is not intended to identify the key or important parts of the present disclosure, nor is it intended to limit the scope of the present disclosure. Its purpose is only to present some concepts of the present disclosure in a simplified form as a prelude to the more detailed description given later.

[0005] According to a first aspect of the present disclosure, there is provided a method for predicting the current of a fan of a cooling tower, including: obtaining a plurality of data points measured for the fan of the cooling tower in a state where the cooling tower is operating normally, each data point including a measured power value, a measured frequency value, and a measured current value that are associated with each other; using a first subset of the plurality of data points to fit a prediction model to obtain fitting parameters of the prediction model, the prediction model being a function of current with respect to power and frequency; and using the prediction model with the fitting parameters to predict a current value of the fan of the cooling tower according to the power value and the frequency value that are associated with each other and measured for the fan of the cooling tower.

[0006] In some embodiments, the prediction model determines the current based on the product of a power term of the power and a power term of the frequency.

[0007] In some embodiments, the prediction model is expressed as: I = CPm f n where I represents the current, C represents a constant parameter, P represents the power, m represents the power exponent parameter of the power, f represents the frequency, and n represents the power exponent parameter of the frequency.

[0008] In some embodiments, the method includes: validating the prediction model with the fitting parameters using a second subset of the plurality of data points that is different from the first subset, where the validation includes: for each data point in the second subset, using the prediction model to determine a predicted current value of the data point based on the measured power value and measured frequency value of the data point, and determining an error value between the predicted current value and the measured current value of the data point; the validation passes when the ratio between the number of data points in the second subset with error values exceeding a first error threshold and the total number of data points in the second subset does not exceed a first ratio threshold; and using the validated prediction model to predict the current value of the fan of the cooling tower based on the power value and frequency value associated with each other measured for the fan of the cooling tower.

[0009] In some embodiments, the validation includes: the validation passes when the ratio between the number of data points in the second subset with error values exceeding the first error threshold and the total number of data points in the second subset does not exceed the first ratio threshold, and the ratio between the number of data points in the second subset with error values exceeding a second error threshold and the total number of data points in the second subset does not exceed a second ratio threshold, where the second error threshold is less than the first error threshold and the second ratio threshold is greater than the first ratio threshold.

[0010] In some embodiments, the validation includes: the validation passes when the ratio between the number of data points in the second subset with error values exceeding the first error threshold and the total number of data points in the second subset does not exceed the first ratio threshold and the data points with error values exceeding the first error threshold in the second subset are continuously distributed.

[0011] In some embodiments, the validation includes: the validation passes when the ratio between the number of data points in the second subset with error values exceeding the first error threshold and the total number of data points in the second subset does not exceed the first ratio threshold and the data points in the first subset are continuously distributed.

[0012] In some embodiments, the measured power value, the measured frequency value, and the measured current value in each data point correspond to the same moment in time. In some embodiments, the measured power value, the measured frequency value, and the measured current value in each data point correspond to a first moment in time, a second moment in time, and a third moment in time, respectively, and the third moment in time has an offset relative to the first moment in time and / or the second moment in time.

[0013] According to a second aspect of the present disclosure, there is provided a method for detecting a fault in a cooling tower, including: obtaining power values, frequency values, and current values that are associated with each other and measured for a fan of the cooling tower; using a prediction model to predict a current value of the fan of the cooling tower based on the measured power value and the measured frequency value, where the prediction model is a function of current with respect to power and frequency; and in a case where a difference between the predicted current value and the measured current value is greater than a difference threshold, giving an alarm to indicate that a fault in the cooling tower has been detected.

[0014] In some embodiments, in a case where the difference between the predicted current value and the measured current value is greater than the difference threshold for a duration threshold, giving an alarm to indicate that a fault in the cooling tower has been detected.

[0015] In some embodiments, the prediction model determines the current based on a product of a power term of the power and a power term of the frequency.

[0016] In some embodiments, the prediction model is expressed as: I = CP m f n ^m f^n, where I represents the current, C represents a constant parameter, P represents the power, m represents a power parameter of the power, f represents the frequency, and n represents a power parameter of the frequency.

[0017] In some embodiments, using the prediction model to predict the current value of the fan of the cooling tower based on the measured power value and the measured frequency value is performed by the method according to any one of the embodiments of the first aspect of the present disclosure.

[0018] In some embodiments, the method further includes: in a case where the difference between the predicted current value and the measured current value is greater than the difference threshold for the duration threshold, determining a cause of the fault based on one or more of a magnitude relationship between the predicted current value and the measured current value, a relationship of a current value measured for the fan of the cooling tower changing with time in a past time period, and an ambient temperature.

[0019] In some embodiments, determining the cause of the fault includes: when the predicted current value is greater than the measured current value and the variation relationship shows a stepwise decline, determining the cause of the fault as the belt of the fan for driving the fan of the cooling tower being broken or fallen off.

[0020] In some embodiments, determining the cause of the fault includes: when the predicted current value is greater than the measured current value, the variation relationship shows a gradual decline, and the ambient temperature is not higher than the freezing point of the packing of the cooling tower, determining the cause of the fault as the packing of the cooling tower being frozen; or when the predicted current value is greater than the measured current value, the variation relationship shows a gradual decline, and the ambient temperature is higher than the freezing point of the packing of the cooling tower, determining the cause of the fault as the packing of the cooling tower being dirty blocked.

[0021] In some embodiments, the severity of the packing of the cooling tower being frozen or dirty blocked is determined based on the slope of the gradual decline.

[0022] In some embodiments, determining the cause of the fault includes: when the predicted current value is less than the measured current value, determining the cause of the fault as the blade angle of the fan of the fan of the cooling tower being changed.

[0023] In some embodiments, the difference threshold is set based on one or more of grid voltage fluctuation, outdoor wind speed, and the operating condition of the cooling tower.

[0024] In some embodiments, the measured power value, the measured frequency value, and the measured current value respectively correspond to a first moment, a second moment, and a third moment, and wherein the difference threshold is set based on the offset of the third moment relative to the first moment and / or the second moment.

[0025] In some embodiments, the duration threshold is set based on the time interval for obtaining the power value, the frequency value, and the current value measured for the fan of the cooling tower that are associated with each other.

[0026] According to a third aspect of the present disclosure, there is provided a device for detecting a fault of a cooling tower, including: a data acquirer configured to acquire power values, frequency values, and current values that are associated with each other and measured for the fan of the cooling tower; a controller coupled to the data acquirer and configured to detect the fault of the cooling tower by using the method according to any one of the embodiments of the second aspect of the present disclosure; and a user interface, and the controller gives an alarm via the user interface to indicate that the fault of the cooling tower is detected.

[0027] In some embodiments, the apparatus includes at least one of the following: a data memory, coupled to the data acquirer and the controller and configured to store data acquired by the data acquirer and the operation results of the controller; a building automation BA system, where the BA system includes one or more of the user interface and the controller.

[0028] In some embodiments, the cooling tower includes a fan and an inverter for performing variable frequency control on the fan, the data acquirer is configured to acquire data measured for the fan of the cooling tower from the inverter, and wherein the prediction model is constructed based on the inverter.

[0029] According to a fourth aspect of the present disclosure, there is provided a computing device, including: one or more processors; and a memory storing computer-executable instructions, which when executed by the one or more processors cause the one or more processors to execute the method according to any one of the embodiments of the first aspect or the second aspect of the present disclosure.

[0030] According to a fifth aspect of the present disclosure, there is provided a non-transitory storage medium storing computer-executable instructions, which when executed by a computer cause the computer to execute the method according to any one of the embodiments of the first aspect or the second aspect of the present disclosure.

[0031] According to a sixth aspect of the present disclosure, there is provided a computer program product, the computer program product including instructions, which when executed by a processor implement the method according to any one of the embodiments of the first aspect or the second aspect of the present disclosure. Description of the Drawings

[0032] From the following description of the embodiments of the present disclosure shown in conjunction with the drawings, the foregoing and other features and advantages of the present disclosure will become apparent. The drawings are incorporated herein and form a part of the specification, further for explaining the principles of the present disclosure and enabling those skilled in the art to make and use the present disclosure. Among them:

[0033] Figure 1 is a flowchart showing a method for detecting a fault of a cooling tower according to some embodiments of the present disclosure;

[0034] Figure 2 is a flowchart showing a method for predicting the current of a fan of a cooling tower according to some embodiments of the present disclosure;

[0035] Figure 3 is a schematic three-dimensional diagram exemplarily showing data points for fitting a first subset of a prediction model and the prediction model fitted using the first subset;

[0036] Figure 4 is a flowchart showing a method for predicting the current of a fan of a cooling tower according to some embodiments of the present disclosure;

[0037] Figure 5 is a schematic three-dimensional diagram exemplarily showing data points for validating a second subset of a prediction model and the prediction model validated using the second subset;

[0038] Figure 6 is a flowchart showing a method for detecting a fault of a cooling tower according to some embodiments of the present disclosure;

[0039] Figure 7 is a flowchart exemplarily showing a process for determining a fault cause, in which a method for detecting a fault of a cooling tower according to some embodiments of the present disclosure is applied;

[0040] Figure 8 is a graph showing the variation of predicted current values and measured current values obtained using a prediction model over time in an example application scenario;

[0041] Figure 9 is a schematic block diagram showing a fault detection device according to some embodiments of the present disclosure;

[0042] Figure 10 is a schematic block diagram showing a fault detection device and a cooling tower according to some embodiments of the present disclosure;

[0043] Figure 11 is a schematic block diagram showing a fault detection device and a cooling tower according to some embodiments of the present disclosure;

[0044] Figure 12 is a schematic block diagram showing a computing device according to some embodiments of the present disclosure;

[0045] Figure 13 is a schematic block diagram showing a computer system on which embodiments of the present disclosure can be implemented.

[0046] Note that in the embodiments described below, sometimes the same reference numerals are used commonly between different drawings to denote the same parts or parts having the same functions, and their repeated descriptions are omitted. In this specification, similar reference numerals and letters are used to denote similar items. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0047] For ease of understanding, the positions, dimensions, ranges, etc. of the various structures shown in the drawings and the like sometimes do not represent the actual positions, dimensions, ranges, etc. Therefore, the disclosed invention is not limited to the positions, dimensions, ranges, etc. disclosed in the drawings and the like. In addition, the drawings do not have to be drawn to scale, and some features may be enlarged to show details of specific components. Detailed Description of the Invention

[0048] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the drawings. It should be noted that unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure.

[0049] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way limits the present disclosure, its application, or its use. Those skilled in the art will understand that they merely illustrate exemplary ways in which the present disclosure can be implemented, rather than exhaustive ways.

[0050] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and devices should be considered as part of the specification.

[0051] In all the examples shown and discussed herein, any specific values should be construed as merely exemplary, not as limitations. Thus, other examples of the exemplary embodiments may have different values.

[0052] In addition, in this document, when referring to the concept of "value", it generally refers to the absolute value, unless otherwise specified.

[0053] Generally, a cooling tower includes multiple (e.g., 5 - 6) belts for driving the operation of the fan. During long-term operation, these belts may become loose and worn, and in severe cases, may even break or fall off. This will affect the operating efficiency of the cooling tower, resulting in high-temperature water output from the cooling tower, causing the cooling tower to alarm and shut down, and further affecting the operation of the data center refrigeration system and the end equipment. Since the data center has high requirements for the safe and stable operation of the HVAC system, the belts of the cooling tower need to be maintained or repaired in a timely manner when they become loose, worn, broken, or fall off.

[0054] Currently, the belts of the cooling tower are maintained through daily manual inspections, which results in the lack of immediacy in discovering the falling or breaking of the belts. There may be no response for a long time after the belts fall or break, leading to a high-temperature alarm in the data center refrigeration system.

[0055] In addition to belt breakage or falling off, the faults of the cooling tower also include the change of the blade angle of the fan of the blower, the icing of the packing or the fouling and blockage of the packing, etc. During operation, the fastening nuts of the fan may become loose, resulting in an increase in the inclination angle of the blades, which will increase the resistance suffered by the blades during the operation of the fan, leading to a decrease in the operating efficiency of the cooling tower. If the change in the blade angle cannot be detected in time, in severe cases, the blades may hit the tower body of the cooling tower, ultimately resulting in damage or even scrapping of the blades. In addition, when the outdoor temperature is relatively low, such as in winter, icing may occur inside the packing. Or, the packing accumulates dirt, impurities or microorganisms due to long-term use, resulting in the blockage of its pores. The icing or fouling and blockage of the packing will lead to an increase in the air resistance flowing through the packing and a decrease in the air volume, which will lead to a decrease in the operating efficiency of the cooling tower and is not conducive to the energy-saving operation of the system.

[0056] In order to detect the faults of the cooling tower in time, an improved method for detecting the faults of the cooling tower is desired. Through a large amount of research, the inventor found that the faults of the cooling tower can be monitored by the current value of the cooling tower blower, and even the cause of the faults can be judged. For example, in the case of belt breakage or falling off, the motor cannot transfer part or all of the power to the fan, resulting in a decrease in the motor load in a short time, thus causing a sudden drop in the current of the blower. Another example is that in the case of the change of the blade angle, the resistance suffered by the operation of the fan will increase, and the torque of the fan will also increase, resulting in an increase in the current of the blower. For another example, in the case of icing or fouling and blockage of the packing, the air inlet of the cooling tower is gradually blocked, resulting in an increase in the air inlet resistance and a decrease in the air inlet volume. This causes the air volume received by the fan to gradually decrease, so the resistance received by the fan gradually decreases, resulting in a gradual decrease in the current of the blower.

[0057] Based on the above, the present disclosure provides a method for detecting the faults of a cooling tower, which can identify whether a fault occurs in the cooling tower through the deviation between the actual current value and the theoretical current value of the cooling tower blower.

[0058] The following will describe in detail a method for detecting the faults of a cooling tower according to various embodiments of the present disclosure with reference to the accompanying drawings. It can be understood that the actual method may further include other steps, and in order to avoid obscuring the key points of the present disclosure, these other steps are not shown in the drawings and will not be discussed herein.

[0059] Figure 1 The flowchart of a method 10 for detecting the faults of a cooling tower according to some embodiments of the present disclosure is shown. As Figure 1 shown, the method 10 includes steps S12 to S16.

[0060] In step S12, power values, frequency values and current values measured for the blower of the cooling tower and associated with each other are obtained.

[0061] Specifically, the power value and the current value respectively refer to the power value and the current value consumed by the fan of the cooling tower, and the frequency value refers to the rotation frequency of the fan of the cooling tower.

[0062] In some embodiments, the fan of the cooling tower is controlled by an inverter. For example, the power value, the frequency value, and the current value measured for the fan can be obtained via the inverter. In some embodiments, additional sensors or measuring devices can also be provided to collect the power value, the frequency value, and the current value of the fan. The present disclosure does not particularly limit the specific measurement method of the power value, the frequency value, and the current value of the fan and the method for obtaining the measurement results.

[0063] In step S14, a prediction model is used to predict the current value of the fan of the cooling tower based on the measured power value and the measured frequency value, and the prediction model is a function of current with respect to power and frequency.

[0064] The prediction model and the method for predicting the current value of the fan of the cooling tower using the prediction model will be explained in more detail below.

[0065] In step S16, in the case where the difference between the predicted current value and the measured current value is greater than the difference threshold, an alarm is given to indicate that a fault of the cooling tower is detected.

[0066] The predicted current value indicates the theoretical current value when the cooling tower is in a normal operating state. When the deviation between the measured current value and the predicted current value is too large, the cooling tower may be in an abnormal operating state, which indicates that there is a fault in the cooling tower.

[0067] In this article, the normal operating state of the cooling tower can include that the heat exchange efficiency of the cooling tower meets the standard, the water flow rate and the air volume are matched, the equipment operates smoothly, the packing state is good, and / or the energy consumption is within a reasonable range, etc. More specifically, for example, the cooling tower being in a normal operating state can include that the belt of the fan is not broken or fallen off, the blade angle of the fan is normal, and / or the packing is not frozen or blocked.

[0068] Compared with manual inspection or monitoring the temperature of the cooling water of the cooling tower, the fault detection method based on monitoring current can detect sudden faults more timely, immediately give an alarm to indicate the staff to solve the problem, avoid causing more serious consequences (for example, it can avoid the water pressure fluctuation of the cooling water system caused by the high-temperature alarm shutdown of the cooling tower), and ensure the safe and stable operation of the data center system. In addition, manual inspection relies on experience judgment, and water temperature monitoring is often a post-event response, and these methods are difficult to detect early latent faults. The fault detection method based on monitoring current of the present disclosure can effectively improve the timeliness, objectivity, and accuracy of fault discovery. In addition, the fault detection method of the present disclosure does not require shutdown inspection, reducing production interruption. At the same time, it also avoids the risks of manual high-altitude operation or confined space operation.

[0069] Further, the present disclosure uses a prediction model to predict the current of the fan of the cooling tower. The prediction model can predict the current of the cooling tower fan based on other operating parameters of the cooling tower fan measured under corresponding operating conditions. Specifically, the prediction model of the present disclosure is a function of current with respect to power and frequency. Therefore, the present disclosure can use the prediction model to predict the current value of the fan of the cooling tower according to the measured power value and the measured frequency value.

[0070] For example, the prediction model can be a mathematical model constructed based on the principle of the frequency converter. In some embodiments, the prediction model may include the product of the power term and the frequency term. Such a model can take into account the instability of the mathematical relationship between the current of the cooling tower fan and power and frequency caused by voltage fluctuations, power factor fluctuations, and magnetic flux fluctuations during the operation of the motor, making the prediction of the model more accurate.

[0071] In some embodiments, the prediction model can be expressed as: I = CP m f n , where I represents current, C represents a constant parameter, P represents power, m represents the power exponent parameter of power, f represents frequency, and n represents the power exponent parameter of frequency. Such a prediction model has fewer parameters and lower fitting difficulty while ensuring the prediction effect.

[0072] The parameters C, m, and n can be specifically set according to the actual situation. For example, they can be determined by the fitting method described later, or can be determined according to test experience. In some examples, m is constrained to be a positive number and n is constrained to be a negative number, that is In some examples, the values of m and n are further set to 1, that is

[0073] It can be understood that the parameters m and n are related to fluctuations, so their positive and negative properties can also be unconstrained during the fitting process. During the fitting process, it is possible that m is positive and n is negative, or m is negative and n is positive, or both m and n are positive, or both m and n are negative, which is specifically determined by whether the fitting result meets the accuracy and reliability requirements.

[0074] In some embodiments, the prediction model can be expressed as: I = CP m f n + A, where A represents a constant parameter. Compared with the previous example, such a prediction model has an adjustable baseline level and can flexibly adapt to different operating conditions of the cooling tower.

[0075] In some embodiments, the prediction model can be in the form of a polynomial. In some examples, the prediction model can be expressed as: where a iCoefficient parameter representing power, b j Coefficient parameter representing frequency. Such a prediction model has a high degree of parameterization and strong scalability, and is suitable for the cooling tower working conditions that generate complex data points. In some examples, the prediction model can be expressed as: Such a prediction model can make a trade-off between scalability and fitting difficulty.

[0076] The following will be combined with Figures 2 to 5 Elaborate in detail the method for determining the parameters of the prediction model and the method for predicting the current of the fan of the cooling tower.

[0077] Figure 2 The flowchart of method 20 for predicting the current of the fan of the cooling tower according to some embodiments of the present disclosure is shown. As Figure 2 shown, method 20 includes steps S22 to S26.

[0078] In step S22, obtain a plurality of data points measured for the fan of the cooling tower in the normal operating state of the cooling tower. Each data point includes a measured power value, a measured frequency value, and a measured current value that are associated with each other.

[0079] In step S24, use a first subset of the plurality of data points to fit the prediction model to obtain the fitting parameters of the prediction model. The prediction model is a function of current with respect to power and frequency.

[0080] In step S26, use the prediction model with the fitting parameters to predict the current value of the fan of the cooling tower according to the power value and frequency value that are associated with each other measured for the fan of the cooling tower.

[0081] For example, the least squares method can be used to fit the prediction model. Of course, other model fitting methods such as maximum likelihood estimation, Bayesian estimation, and random sample consensus are also feasible, and the present disclosure does not make special restrictions on the specific fitting method. The fitting method can be implemented by a computer program, such as a program written in a programming language such as python.

[0082] During the model fitting process, it can be considered that the fitting is completed when the coefficient of determination R 2 of the model reaches or exceeds the coefficient of determination threshold. The coefficient of determination threshold can also be considered as the accuracy requirement for the prediction model, and it can be set according to the cooling tower operating conditions and on-site requirements. In some embodiments, the coefficient of determination threshold can be set between 0.90 and 0.99, or between 0.95 and 0.99. For example, it can be 0.98.

[0083] For the purpose of non-limiting example illustration, Figure 3Schematically shown are the data points for fitting the first subset of the prediction model and the prediction model I = CP fitted using the first subset m f n . Figure 3 The three-dimensional graph shown includes three coordinate axes: the P-axis represents power as the independent variable, the f-axis represents frequency as the independent variable, and I represents current as the dependent variable. Each point represents a data point in the first subset. The surface is a fitted surface obtained by using the first subset and fitting based on the least squares method, which graphically represents the prediction model with fitting parameters. The prediction model is fitted based on the operation data (the first subset) of the cooling tower in a certain data center over half a year. The specific fitting parameters are C = 55.1797, m = 0.5985, and n = -0.5312. The coefficient of determination R 2 of this prediction model is 0.9880, and it can be intuitively seen that the data points are basically continuously distributed near the fitted surface, indicating that the model has a good fitting degree for the data. Using such a prediction model can obtain more accurate predicted current values, and further, the false alarm rate of fault detection can be reduced.

[0084] In addition, the fitted prediction model can also be verified to evaluate its prediction accuracy. As Figure 4 shown, compared with method 20, method 20' is different in that step S25 is added and step S26 is replaced by step S26'.

[0085] In step S25, the prediction model with fitting parameters is verified using a second subset of the multiple data points that is different from the first subset.

[0086] In step S26', using the verified prediction model, according to the power value and frequency value measured for the fan of the cooling tower that are associated with each other, the current value of the fan of the cooling tower is predicted.

[0087] The second subset can include some or all of the other data points among the multiple data points except the first subset. In some cases, the second subset can also include some or all of the data points in the first subset.

[0088] For example, the verification can include, for each data point in the second subset, using the prediction model to determine the predicted current value of the data point according to the measured power value and measured frequency value of the data point, and determining the error between the predicted current value and the measured current value of the data point.

[0089] The conditions for passing the verification can be different. In some embodiments, the verification passes when the ratio between the number of data points in the second subset whose error values exceed the first error threshold and the total number of data points in the second subset does not exceed the first ratio threshold. The combination of the first error threshold and the first ratio threshold can reflect the acceptable minimum prediction accuracy, which can be set according to specific circumstances. In some embodiments, the first error threshold can be between 2.5 amperes (A) and 4 A, for example, it can be 3 A. In some embodiments, the first ratio threshold can be between 0.1% and 1%, or between 0.2% and 0.5%, for example, it is 0.25%.

[0090] In some embodiments, the verification passes when the ratio between the number of data points in the second subset whose error values exceed the first error threshold and the total number of data points in the second subset does not exceed the first ratio threshold, and the ratio between the number of data points in the second subset whose error values exceed the second error threshold and the total number of data points in the second subset does not exceed the second ratio threshold. The second error threshold is less than the first error threshold, and the second ratio threshold is greater than the first ratio threshold. The combination of the first error threshold and the first ratio threshold can reflect the acceptable minimum prediction accuracy, and the combination of the second error threshold and the second ratio threshold can reflect how high the prediction accuracy can reach, which can be set according to specific circumstances. Such gradient evaluation can provide a more fine-grained basis for evaluating the prediction effect of the model. In some embodiments, the second error threshold can be between 0.5 A and 2.5 A, for example, it can be 2 A. In some embodiments, the second ratio threshold can be between 0.5% and 2%, or between 0.5% and 1%, for example, it is 0.75%.

[0091] Taking Figure 3 the prediction model shown as an example, the model is verified. Substituting the data points of the first subset into the prediction model I = 55.1797P 0.5985 f -0.5312 , it is obtained that the proportion of the data volume with a current error value above 2 A (the second error threshold of 2 A) is 0.60% (not exceeding the second ratio threshold of 0.75%), and the proportion of the data volume with a current error value above 3 A (the first error threshold of 3 A) is 0.09% (not exceeding the first ratio threshold of 0.25%). Taking the operation data of this data center in the other half year as the second subset to verify the prediction model, it is obtained that the proportion of the data volume with a current error value above 2 A is 0.64%, and the proportion of the data volume with a current error value above 3 A is 0.16%. This proves that the prediction model has a good fitting effect.

[0092] It can be understood that the above embodiments of setting the two combinations of the error threshold and the ratio threshold are merely exemplary rather than restrictive, and more combinations of the error threshold and the ratio threshold can be set according to actual needs.

[0093] Additionally or alternatively, in addition to evaluating with a combination of an error threshold and a ratio threshold, the distribution of data points may also be considered to evaluate whether the data points used for fitting are appropriate and / or whether the data points used for verification are appropriate.

[0094] In some embodiments, when the ratio between the number of data points in the second subset whose error values exceed the first error threshold and the total number of data points in the second subset does not exceed the first ratio threshold, and the data points in the second subset whose error values exceed the first error threshold are continuously distributed, the verification passes. Here, continuous distribution means that in a three-dimensional graph with power, frequency, and current as axes, the data points are continuously rather than discretely distributed. That is, the distance between adjacent data points with error values greater than the first error threshold in the three-dimensional space defined by power, frequency, and current is small. The inventors have noticed that due to various reasons such as grid voltage fluctuations, outdoor wind speed effects, and cooling tower operation publicity, various situations may occur, such as a sudden drop in the measured power value resulting in a low predicted current value, a sudden drop in the measured frequency value resulting in a high predicted current value, and a sudden increase in the measured current value. Data points with error values greater than the first error threshold caused by these reasons usually do not show a significant continuous distribution, and using such data points to verify the prediction model may be inaccurate. Therefore, in such a case, the verification may not pass, and the verification may be re-performed by replacing a batch of data points.

[0095] In some embodiments, when the ratio between the number of data points in the second subset whose error values exceed the first error threshold and the total number of data points in the second subset does not exceed the first ratio threshold, and the data points in the first subset are continuously distributed, the verification passes. Here, continuous distribution means that in a three-dimensional graph with power, frequency, and current as axes, the data points are continuously rather than discretely distributed. That is, the distance between adjacent data points in the first subset in the three-dimensional space defined by power, frequency, and current is small. The continuous distribution of the data points in the first subset, especially continuously distributed along the fitting surface near the fitting surface, means a higher fitting effectiveness, and the alarms generated by the prediction model verified in this way will be more valuable. From another perspective, this can also be reflected in the high or low value of the determination coefficient R 2 of the fitting result. As described above, the inventors have noticed that due to various reasons such as grid voltage fluctuations, outdoor wind speed effects, and cooling tower operation publicity, various situations may occur, such as a sudden drop in the measured power value resulting in a low predicted current value, a sudden drop in the measured frequency value resulting in a high predicted current value, and a sudden increase in the measured current value. These reasons may cause the mathematical relationship between the current value and the power value and frequency value of the data points to be unstable, and using such data points to fit the prediction model may be inaccurate. Therefore, in such a case, the verification may not pass, and the fitting may be re-performed by replacing a batch of data points.

[0096] For purposes of illustrative and non - limiting example, Figure 5 Data points of a second subset for verifying a prediction model and the prediction model verified using the second subset are schematically shown, where the second subset includes data points of the first subset. It can be found that these data points are discretely distributed, and many do not fall on the fitting surface characterizing the prediction model. Additionally, the coefficient of determination R 2 is only 0.8408. Therefore, as Figure 5 shown, the prediction model cannot pass the verification.

[0097] In the case where the verification fails, there are also various ways to adjust the prediction model. In some embodiments, the fitting and verification processes can be repeatedly executed, and the fitting parameters are continuously updated until the conditions for passing the verification are met. In some embodiments, the data used for model fitting can be adjusted, and data more corresponding to the normal operating conditions of the cooling tower can be selected. In some embodiments, the model function can be adjusted, such as increasing / decreasing the fitting parameters, etc. In some embodiments, the fitting method can be adjusted to obtain a fitting result that better conforms to the distribution of the data points.

[0098] Next, with reference to Figure 6 we continue to discuss a method for detecting faults in a cooling tower according to some embodiments of the present disclosure. As Figure 6 shown, compared with method 10, method 10' is different in that step S16 is replaced by step S16', and optionally step S18 is added.

[0099] In step S16', when the difference between the predicted current value and the measured current value is greater than the difference threshold for a duration threshold, an alarm is given to indicate that a fault in the cooling tower is detected. In other words, compared with step S16 of method 10, the alarm condition of step S16' of method 10' requires not only that the difference is greater than the difference threshold but also that the duration of this phenomenon is greater than the duration threshold. This can advantageously reduce false alarms.

[0100] In step S18, the cause of the fault is determined. It can be understood that step S18 can also be included in method 10 as Figure 1 shown.

[0101] In some embodiments, the cause of the fault can be determined based on one or more of the magnitude relationship between the predicted current value and the measured current value, the variation relationship of the current value measured for the fan of the cooling tower over time in a past time period, and the ambient temperature.

[0102] For example, the past time period may include a period of time forward from the moment when the difference between the predicted current value and the measured current value starts to be greater than the difference threshold, and in some cases may also include a period of time backward from the moment when the difference between the predicted current value and the measured current value starts to be greater than the difference threshold. In some embodiments, the past time period may be from 5 minutes to 25 minutes, or from 10 minutes to 20 minutes, for example 15 minutes. The present disclosure does not particularly limit the length of the past time period, as long as the past time period includes the time period during which the current undergoes a change that triggers an alarm and a part in the vicinity thereof.

[0103] Specifically, in some examples, when the predicted current value is greater than the measured current value, and the relationship between the current value measured for the fan of the cooling tower over time shows a stepwise decrease during the past time period, the cause of the failure is determined to be that the belt of the fan driving the fan of the cooling tower is broken or has fallen off.

[0104] In some examples, when the predicted current value is greater than the measured current value, and the relationship between the current value measured for the fan of the cooling tower over time shows a gradual decrease, the cause of the failure is determined to be that the packing of the cooling tower is frozen or clogged. Further, when the ambient temperature is not higher than the freezing point of the packing of the cooling tower, the cause of the failure is determined to be that the packing of the cooling tower is frozen, and when the ambient temperature is higher than the freezing point of the packing of the cooling tower, the cause of the failure is determined to be that the packing of the cooling tower is clogged. For example, the severity of the freezing or clogging of the packing of the cooling tower can be determined based on the slope of the gradual decrease. The greater the slope (the faster the gradual decrease), the more severe the freezing or clogging of the packing is indicated. In this way, an objective index can be provided for arranging the priority of maintenance, enabling the cooling tower with more severe freezing or clogging of the packing to obtain maintenance earlier and improving the reliability of the operation of the cooling tower. In some examples, when the predicted current value is less than the measured current value, the cause of the failure is determined to be that the blade angle of the fan of the cooling tower has changed.

[0105] For purposes of non-limiting illustration, Figure 7 exemplarily shows a flowchart of a process for determining the cause of a failure. As Figure 7 shown, step S18 includes steps S182 to S1814.

[0106] After step S16 or step S16' is executed, step S182 is executed. In step S182, it is judged whether the predicted current value is greater than the measured current value. Alternatively, the positivity or negativity of the difference obtained by subtracting the measured current value from the predicted current value can be judged. If the judgment is yes (the difference is positive), step S184 is executed. If the judgment is no (the difference is negative), step S1814 is entered, that is, the cause of the failure is determined to be that the blade angle of the fan of the cooling tower has changed.

[0107] In step S184, the relationship between the current value measured for the fan of the cooling tower and the change in time in the past time period is determined. If the determination result of step S184 is a step-down, the process proceeds to step S186, that is, the cause of the fault is determined to be the breakage or fall of the belt of the fan used to drive the fan of the cooling tower. If the determination result of step S184 is a gradual decline, step S188 is executed. In the present disclosure, a step-down may refer to a sudden drop in current in a short period of time, which may appear in a step shape on the current-time curve; a gradual decline may refer to a ramp drop in current over time, which may appear in a ramp shape on the current-time curve. For example, a step-down and a gradual decline may be distinguished by setting a slope threshold.

[0108] It should be noted that when the cause of the fault is the belt falling or breaking, the typical rule is that when the number of belts falling or breaking does not exceed a certain proportion (for example, half), the cooling tower fan current does not change significantly, and when the number of belts falling or breaking exceeds this proportion, the cooling tower fan current changes significantly. Therefore, when entering step S186, the cooling tower fan belt has fallen or broken more than the above proportion. The specific number of belts falling or breaking that causes a significant change in current is related to the cooling tower model and the use of the cooling tower fan.

[0109] by Figure 3Taking the prediction model shown as an example, this prediction model is applied to a fault detection method to detect a certain cooling tower with 5 belts. Among them, the difference threshold is set to 2A, and the duration threshold is set to 15 minutes. When 1 belt drops, the measured current value has no significant change, and the system does not alarm. When 2 belts drop, the measured current value of the cooling tower fan changes from 39.9A to 30.4A, and the difference between the measured current values before and after is 9.5A. The difference from the predicted current value is higher than 2A. After 15 minutes, an alarm is issued to indicate that a fault has been detected. Moreover, based on the fact that the predicted current value is higher than the measured current value and the measured current value drops step by step, the cause of the fault is determined to be belt dropping or breaking. Continuing to observe the change of the measured current value, the measured current value of the cooling tower fan remains at about 30A for 3 hours and 15 minutes. Then the 3rd belt drops, the measured current value changes from 28.4A to 23.2A, and the change in the measured current value before and after is 5.2A. The difference from the predicted current value is higher than 2A. After 15 minutes, an alarm is issued and the cause of the fault is determined to be belt dropping or breaking. Continuing to observe the change of the measured current value, the situation where the measured current value continues to change from 0A to about 20A occurs within 1 hour, and the alarm continues. After 1 hour, the measured current value completely reaches 0A. When there are only 2 belts left in the cooling tower, since the belts can no longer drive the fan to rotate, the measured current value shows a drastic fluctuation. According to the above embodiments, when 2 or more belts of the cooling tower drop or break, the measured current value of the cooling tower fan changes significantly. After meeting the alarm logic, an alarm is normally issued and the correct cause of the fault is judged, which proves the reliability of the fault detection method of the present disclosure.

[0110] In step S188, it is judged whether the ambient temperature is higher than the freezing point of the packing of the cooling tower. The freezing point of the packing can be, for example, 0 degrees Celsius. Alternatively or additionally, it can be judged whether the current time is a non-winter time period. The winter time period can be, for example, from November to February of the following year, and the specific value can be based on the local climate where the cooling tower is located. If the judgment is no, then step S1810 is entered, that is, the cause of the fault is determined to be the icing of the packing of the cooling tower. If the judgment is yes, then step S1812 is entered, that is, the cause of the fault is determined to be the fouling of the packing of the cooling tower.

[0111] It can be understood that although mainly taking belt dropping or breaking, packing icing or fouling, and fan blade angle change as examples in the embodiments herein, the present disclosure is not limited thereto. As long as the faults that can be identified through the change law of the fan current can be incorporated into the Figure 7 process shown.

[0112] In some embodiments, after determining the cause of the failure, any operation that puts the faulty cooling tower in a repairable state, such as shutting down the cooling tower and switching off the machine, can be performed to facilitate timely maintenance by the staff and ensure the safe and stable operation of the data center.

[0113] The difference threshold in steps S16 and S16' can be determined by considering multiple factors. For example, these factors include, but are not limited to, the possible jitter of the measured power value, frequency value, and current value, and the delay between the recording times of power, frequency, and current.

[0114] For purposes of non-limiting illustration, Figure 8 shows the predicted current value and the measured current value obtained using the prediction model changing over time in an example application scenario. Figure 8 In the figure, the light solid line represents the measured current value, and the dark dashed line represents the predicted current value. It can be seen that in most regions, the curve of the predicted current value coincides highly with the curve of the measured current value, indicating that the prediction model proposed in the present disclosure has high accuracy in predicting the fan current. In some regions, such as the region circled by the ellipse, the measured current value shows jitter. The reasons for these jitters may include grid voltage fluctuations, outdoor wind speed effects, and adjustment of the operating conditions of the cooling tower. For such jitters in the current value, it is desirable not to generate an alarm. However, as analyzed earlier, the prediction model does not perform well in predicting or fitting such data, resulting in an undesired alarm. Therefore, the difference threshold can be set based on one or more of grid voltage fluctuations, outdoor wind speed, and the operating conditions of the cooling tower. Specifically, the current jitter can be considered to set the difference threshold. For example, assuming the maximum jitter amplitude is I max , then the difference threshold can be set to a value greater than I max to reduce the false alarm rate.

[0115] In an ideal situation, the power value, frequency value, and current value described in the methods 10, 10' for fault detection and the methods 20, 20' for current prediction in the present disclosure being associated with each other can mean that the measurement of the above parameters for each data point occurs at the same moment. The current prediction model obtained using such data points has better accuracy. The false alarm rate of the fault detection method using such data points as input will also be lower.

[0116] However, in actual situations, there is a time delay in the numerical recording of equipment (e.g., frequency converters). Therefore, the power value, frequency value, and current value that are associated with each other may not necessarily be acquired at the same moment. For example, the power value, frequency value, and current value that are measured substantially simultaneously may be acquired at the first moment, the second moment, and the third moment respectively. There is often an offset between the first moment, the second moment, and the third moment, which will have a certain impact on data accuracy: for example, the current value at the same power value may differ by about 1 - 2A. For this reason, on the one hand, if the offset is known, the data can be pre - processed, and the data acquired at each moment can be re - organized through time offset to generate corresponding data points, so that the frequency value, power value, and current value accurately correspond to each other. On the other hand, the difference threshold can be set according to the offset or the current deviation caused by the offset. For example, the difference threshold is set to 2A. The specific value of the difference threshold can be further determined according to the on - site data during actual application, thereby reducing the possibility of false alarms.

[0117] Therefore, for methods 10, 10', in some embodiments, the measured power value, the measured frequency value, and the measured current value correspond to the first moment, the second moment, and the third moment respectively, where the difference threshold can be set based on the offset of the third moment relative to the first moment and / or the second moment. Similarly, for methods 20, 20', in some embodiments, the measured power value, the measured frequency value, and the measured current value in each data point correspond to the same moment; or, the measured power value, the measured frequency value, and the measured current value in each data point correspond to the first moment, the second moment, and the third moment respectively, and the third moment may have an offset relative to the first moment and / or the second moment. The moment here can refer to the data acquisition moment.

[0118] In some embodiments, with reference to Figure 6 , the duration threshold in step S16' is set based on the time interval for acquiring the mutually associated power value, frequency value, and current value measured for the fan of the cooling tower. This time interval can also be referred to as the data acquisition step size. In the case where the data acquisition step size is short (e.g., several seconds), the duration threshold can be set to be relatively long compared to the data acquisition step size (e.g., several minutes or several times the data acquisition step size). In this way, false alarms of error data can be prevented. Additionally, considering that the belt break occurs instantaneously and the time interval for the belt to fall is not too long, the duration threshold should not be set too long. In the case where the data acquisition step size is long (e.g., greater than 10 minutes), the duration threshold can be set shorter, or even zero, that is, directly alarm without waiting when the difference threshold is exceeded. In this way, the immediacy of the alarm can be improved.

[0119] On the other hand, the present disclosure also provides a fault detection device for a cooling tower.Figure 9 FIG. 301 shows a schematic block diagram of a fault detection device 300 according to some embodiments of the present disclosure. As Figure 9 shown, the fault detection device 300 includes a data acquirer 320, a controller 340, and a user interface 360. The data acquirer 320 is configured to acquire power values, frequency values, and current values that are associated with each other and measured for a fan of a cooling tower. The controller 340 is coupled to the data acquirer 320 and is configured to detect a fault of the cooling tower using any one of the embodiments of methods 10, 10'. The controller 340 gives an alarm via the user interface 360 to indicate that a fault of the cooling tower has been detected. For example, a pop-up alarm is given on an interactive page of the user interface 360. As another example, an alarm sound is emitted via the user interface 360. In some embodiments, the user interface 360 may display or broadcast the cause of the fault.

[0120] In some embodiments, the fault detection device 300 includes at least one of the following: a data memory, coupled to the data acquirer 320 and the controller 340 and configured to store the data acquired by the data acquirer 320 and the operation result of the controller 340; a Building Automation (BA) system, including one or more of the user interface 360 and the controller 340.

[0121] Figure 10 FIG. 308 shows a non-limiting implementation 300' of the fault detection device 300 and a cooling tower 400. As Figure 10 shown, the fault detection device 300' may further include a data memory 380 and a BA system 350. The data memory 380 is coupled to the data acquirer 320 and the controller 340, and is configured to store the data acquired by the data acquirer 320 and the operation result of the controller 340. The BA system 350 includes the user interface 360 and the controller 340. In some embodiments, when the BA system 350 determines that the measured current value is abnormal, it statistically records the duration of the abnormality. When the accumulated duration reaches a duration threshold, the BA system 350 gives an alarm and stores the alarm record in the data memory 380. In some embodiments, after being manually operated or automatically logically recognized, the BA system 350 may cause the controller 340 to send a control signal to implement fault maintenance.

[0122] The cooling tower 400 includes a frequency converter 420 and a fan 450. The fan 450 may include a motor 452 and a fan 454. The motor 452 drives the fan 454 in a belt drive manner. The frequency converter 420 can perform variable frequency control on the fan 450. The data acquirer 320 can acquire the data measured for the fan 450 via the frequency converter 420. The prediction model can be constructed based on the principle of the frequency converter 420. The controller 340 can send a parameter control command to the frequency converter 420, so that the frequency converter 420 controls the operating state of the fan 450 (such as the fan rotation frequency) according to the received parameter control command. The cooling tower 400 may further include a start-stop module (not shown in the figure). The controller 340 can send a shutdown operation command, a fault shutdown command, etc. to the start-stop module, so that the cooling tower stops working and is in a repairable state.

[0123] Figure 11 Another non-limiting implementation 300” of the fault detection device 300 and the cooling tower 400 is shown. As Figure 11 shown, in the fault detection device 300”, the BA system 350 only provides a user interface 360 and does not provide a controller 340. That is, the controller 340 is a control component separate from the BA system 350. The settings of the remaining components are the same as those of the fault detection device 300’ and the cooling tower 400 shown Figure 10 as, and will not be described again here.

[0124] The present disclosure also provides a computing device, which may include one or more processors and a memory storing computer-executable instructions. When the computer-executable instructions are executed by the one or more processors, the one or more processors execute the method according to any one of the foregoing embodiments of the present disclosure. As Figure 12As shown, the computing device 500 may include one or more processors 520 and a memory 540 that stores computer-executable instructions. When the computer-executable instructions are executed by the one or more processors 520, the one or more processors 520 are caused to execute the method according to any one of the foregoing embodiments of the present disclosure. The one or more processors 520 may be, for example, the central processing unit (CPU) of the computing device 500. The one or more processors 520 may be any type of general-purpose processor or may be a processor specifically designed for cooling tower fault detection and / or fan current prediction, such as an application-specific integrated circuit (“ASIC”). The memory 540 may be coupled to the one or more processors 520 and may include various computer-readable media accessible by the one or more processors 520. In various embodiments, the memory 540 described herein may include volatile and non-volatile media, removable and non-removable media. For example, the memory 540 may include any combination of the following: random access memory (“RAM”), dynamic RAM (“DRAM”), static RAM (“SRAM”), read-only memory (“ROM”), flash memory, cache memory, and / or any other type of non-transitory computer-readable media. The memory 540 may store instructions that, when executed by the processor 520, cause the processor 520 to execute the method according to any one of the foregoing embodiments of the present disclosure.

[0125] The present disclosure also provides a non-transitory storage medium having computer-executable instructions stored thereon. When the computer-executable instructions are executed by a computer, the computer is caused to execute the method according to any one of the foregoing embodiments of the present disclosure.

[0126] The present disclosure also provides a computer program product that may include instructions that, when executed by a processor, may implement the method according to any one of the foregoing embodiments of the present disclosure. The instructions may be any set of instructions that are directly executable by one or more processors, such as machine code, or any set of instructions that are indirectly executable, such as a script. The instructions may be stored in a target code format for direct processing by one or more processors or may be stored in any other computer language, including a script or collection of independent source code modules that are interpreted on demand or pre-compiled.

[0127] Figure 13FIG. 0 is a schematic block diagram of a computer system 600 on which embodiments of the present disclosure may be implemented. The computer system 600 includes a bus 602 or other communication mechanism for transferring information, and a processing device 604 coupled to the bus 602 for processing information. The computer system 600 also includes a memory 606 coupled to the bus 602 for storing instructions to be executed by the processing device 604. The memory 606 may be a random access memory (RAM) or other dynamic storage device. The memory 606 may also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by the processing device 604. The computer system 600 also includes a read-only memory (ROM) 608 or other static storage device coupled to the bus 602 for storing static information and instructions for the processing device 604. A storage device 610, such as a magnetic disk or optical disk, is provided and coupled to the bus 602 for storing information and instructions. The computer system 600 may be coupled via the bus 602 to an output device 612 for providing output to a user, such as, but not limited to, a display (such as a cathode ray tube (CRT) or liquid crystal display (LCD)), a speaker, etc. Input devices 614, such as a keyboard, a mouse, a microphone, etc., are coupled to the bus 602 for transmitting information and command selections to the processing device 604. The computer system 600 may execute embodiments of the present disclosure. Consistent with certain implementations of the present disclosure, results are provided by the computer system 600 in response to execution of one or more sequences of one or more instructions contained in the memory 606 by the processing device 604. Such instructions may be read into the memory 606 from another computer-readable medium, such as the storage device 610. Execution of the sequences of instructions contained in the memory 606 causes the processing device 604 to perform the methods described herein. Alternatively, the present teachings may be implemented using hardwired circuitry in place of or in combination with software instructions. Accordingly, implementations of the present disclosure are not limited to any specific combination of hardware circuitry and software. In various embodiments, the computer system 600 may be connected across a network to one or more other computer systems, such as the computer system 600, via a network interface 616 to form a networked system. The network may include a private network or a public network such as the Internet. In the networked system, one or more computer systems may store data and supply the data to other computer systems. As used herein, the term "computer-readable medium" refers to any medium that participates in providing instructions to the processing device 604 for execution. Such a medium may take many forms, including but not limited to non-volatile media, volatile media, and transmission media. Non-volatile media includes, for example, optical or magnetic disks such as the storage device 610. Volatile media includes dynamic memory such as the memory 606. Transmission media includes coaxial cables, copper wire, and fiber optics, including the wiring that includes the bus 602.Common forms of computer-readable media or computer program products include, for example, floppy disks, flexible disks, hard disks, magnetic tapes, or any other magnetic medium, CD-ROMs, digital video discs (DVDs), Blu-ray discs, any other optical medium, thumb drives, memory cards, RAM, PROM, and EPROM, flash EPROM, any other memory chip or cartridge, or any other tangible medium from which a computer can read. Various forms of computer-readable media may be involved in carrying one or more sequences of one or more instructions to the processing device 604 for execution. For example, the instructions may initially be carried on a disk of a remote computer. The remote computer may load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to the computer system 600 may receive the data over the telephone line and convert the data into an infrared signal using an infrared transmitter. An infrared detector coupled to the bus 602 may receive the data carried in the infrared signal and place the data on the bus 602. The bus 602 carries the data to the memory 606, and the processing device 604 retrieves the instructions from the memory 606 and executes the instructions. Optionally, the instructions received by the memory 606 may be stored on the storage device 610 before or after being executed by the processing device 604.

[0128] In accordance with various embodiments, instructions configured to be executed by a processing device to perform a method are stored on a computer-readable medium. The computer-readable medium may be a device that stores digital information. For example, the computer-readable medium includes a compact disc read-only memory (CD-ROM) known in the art for storing software. The computer-readable medium is accessed by a processor suitable for executing the instructions configured to be executed.

[0129] One or more exemplary embodiments of the present disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain implementations, multitasking and parallel processing are also possible or may be advantageous.

[0130] The systems, apparatuses, modules, or units illustrated in the above embodiments may be specifically implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a server system. Of course, the present disclosure does not exclude that with the development of future computer technologies, the computers implementing the functions of the above embodiments may be, for example, personal computers, laptop computers, in-vehicle human-machine interaction devices, cellular phones, camera phones, smart phones, personal digital assistants, media players, game consoles, tablet computers, wearable devices, or any combination thereof.

[0131] The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, product or apparatus that comprises a series of elements includes not only those elements but also other elements not expressly listed, or elements that are inherent to such process, method, product or apparatus. Without further limitation, there is no exclusion of additional identical or equivalent elements in the process, method, product or apparatus that comprises the said elements. For example, when words such as "first", "second" are used to denote names, they do not denote any particular order.

[0132] For the sake of convenience of description, when describing the above device, it is divided into various modules according to functions for separate description. Of course, when implementing one or more embodiments of the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware, or the modules implementing the same function can be realized by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0133] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate a device for realizing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0134] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the function specified in one or more blocks of a flowchart and / or one or more blocks of a block diagram. These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one or more blocks of a flowchart and / or one or more blocks of a block diagram.

[0135] Those skilled in the art will appreciate that one or more embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0136] One or more embodiments of the present disclosure may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the present disclosure may also be practiced in a distributed computing environment where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

[0137] For the same or similar parts among the various embodiments of the present disclosure, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the apparatus embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the corresponding descriptions in the method embodiments. In the description of the present disclosure, the description referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", "exemplary", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. In the present disclosure, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in the present disclosure and the features of different embodiments or examples.

[0138] In addition, as used in the present disclosure, the words "here", "above", "below", "hereinafter", "above-mentioned", and words with similar meanings shall refer to the whole of the present disclosure rather than any specific part of the present disclosure. Moreover, unless otherwise clearly stated or understood in the context in which it is used, the conditional language used herein, such as "may", "might", "for example", "such as", etc., generally intends to indicate that certain embodiments include, while other embodiments do not include certain features, elements, and / or states. Therefore, such conditional language generally does not intend to imply that one or more embodiments require in any way the features, elements, and / or states, or whether they include these features, elements, and / or states or perform these features, elements, and / or states in any specific embodiment.

[0139] The above description is only for the embodiments of one or more embodiments of the present disclosure and is not intended to limit one or more embodiments of the present disclosure. For those skilled in the art, various changes and modifications can be made to one or more embodiments of the present disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included within the scope of the claims.

Claims

1. A method for predicting the current of a fan of a cooling tower, comprising: Obtaining a plurality of data points measured for the fan of the cooling tower in a state where the cooling tower is operating normally, each data point including a measured power value, a measured frequency value, and a measured current value that are associated with each other; Fitting a prediction model using a first subset of the plurality of data points to obtain fitting parameters of the prediction model, the prediction model being a function of current with respect to power and frequency; And Using the prediction model with the fitting parameters, predicting the current value of the fan of the cooling tower according to the power value and the frequency value that are associated with each other and measured for the fan of the cooling tower.

2. The method according to claim 1, wherein The prediction model determines the current based on the product of a power term of the power and a power term of the frequency.

3. The method according to claim 2, wherein The prediction model is expressed as: I = CP m f n Wherein, I represents the current, C represents a constant parameter, P represents the power, m represents a power parameter of the power, f represents the frequency, and n represents a power parameter of the frequency.

4. The method according to claim 1, wherein, The method includes: Validating the prediction model with the fitting parameters using a second subset of the plurality of data points that is different from the first subset, wherein the validation includes: For each data point in the second subset, using the prediction model to determine a predicted current value of the data point according to the measured power value and the measured frequency value of the data point, and determining an error value between the predicted current value and the measured current value of the data point; When the proportion between the number of data points in the second subset whose error values exceed a first error threshold and the total number of data points in the second subset does not exceed a first proportion threshold, the validation passes; and Using the validated prediction model, predicting the current value of the fan of the cooling tower according to the power value and the frequency value that are associated with each other and measured for the fan of the cooling tower.

5. The method according to claim 4, wherein, The validation includes: When the proportion between the number of data points in the second subset whose error values exceed the first error threshold and the total number of data points in the second subset does not exceed the first proportion threshold, and the proportion between the number of data points in the second subset whose error values exceed a second error threshold and the total number of data points in the second subset does not exceed a second proportion threshold, the validation passes, Wherein, the second error threshold is less than the first error threshold, and the second proportion threshold is greater than the first proportion threshold.

6. The method according to claim 4, wherein The validation includes: When the proportion between the number of data points in the second subset whose error values exceed the first error threshold and the total number of data points in the second subset does not exceed the first proportion threshold, and the data points whose error values exceed the first error threshold in the second subset are continuously distributed, the validation passes; or When the proportion between the number of data points in the second subset whose error values exceed the first error threshold and the total number of data points in the second subset does not exceed the first proportion threshold, and the data points in the first subset are continuously distributed, the validation passes.

7. The method according to claim 1, wherein: The measured power value, measured frequency value, and measured current value in each data point correspond to the same moment in time; or The measured power value, measured frequency value, and measured current value in each data point correspond to a first moment, a second moment, and a third moment respectively, and the third moment has an offset relative to the first moment and / or the second moment.

8. A method for detecting a fault in a cooling tower, comprising: Obtaining power values, frequency values, and current values that are associated with each other and measured for a fan of the cooling tower; Using a prediction model to predict the current value of the fan of the cooling tower based on the measured power value and the measured frequency value, where the prediction model is a function of current with respect to power and frequency; and In the case where the difference between the predicted current value and the measured current value is greater than a difference threshold, generating an alarm to indicate that a fault in the cooling tower has been detected.

9. The method according to claim 8, wherein In the case where the difference between the predicted current value and the measured current value is greater than the difference threshold for a duration threshold, generating an alarm to indicate that a fault in the cooling tower has been detected.

10. The method according to claim 8, wherein, The prediction model determines the current based on the product of a power term of the power and a power term of the frequency.

11. The method according to claim 10, wherein, The prediction model is expressed as: I = CP m f n where I represents the current, C represents a constant parameter, P represents the power, m represents a power parameter of the power, f represents the frequency, and n represents a power parameter of the frequency.

12. The method according to claim 8, wherein, Predicting the current value of the fan of the cooling tower using a prediction model based on the measured power value and the measured frequency value is performed by the method according to any one of claims 1 to 7.

13. The method according to claim 9, further comprising: In the case where the difference between the predicted current value and the measured current value is greater than the difference threshold for the duration threshold, determining the cause of the fault based on one or more of the magnitude relationship between the predicted current value and the measured current value, the relationship of the current value measured for the fan of the cooling tower over time in a past time period, and the ambient temperature.

14. The method according to claim 13, wherein, Determining the cause of the fault includes: In the case where the predicted current value is greater than the measured current value and the relationship shows a stepwise decrease, determining the cause of the fault as a belt breakage or drop of a fan for driving the fan of the cooling tower.

15. The method according to claim 13, wherein, Determining the cause of the fault includes: In the case where the predicted current value is greater than the measured current value, the relationship shows a gradual decrease, and the ambient temperature is not higher than the freezing point of the packing of the cooling tower, determining the cause of the fault as icing of the packing of the cooling tower; or In the case where the predicted current value is greater than the measured current value, the relationship shows a gradual decrease, and the ambient temperature is higher than the freezing point of the packing of the cooling tower, determining the cause of the fault as fouling of the packing of the cooling tower.

16. The method according to claim 15, wherein Determining the severity of icing or fouling of the packing of the cooling tower based on the slope of the gradual decrease.

17. The method according to claim 13, wherein, Determining the cause of the fault includes: In the case that the predicted current value is less than the measured current value, determine the cause of the fault as the change in the blade angle of the fan of the blower of the cooling tower.

18. The method according to claim 8, wherein The difference threshold is set based on one or more of grid voltage fluctuations, outdoor wind speed, and the operating conditions of the cooling tower.

19. The method according to claim 8, wherein, The measured power value, the measured frequency value, and the measured current value respectively correspond to the first moment, the second moment, and the third moment, and wherein the difference threshold is set based on the offset of the third moment relative to the first moment and / or the second moment.

20. The method according to claim 9, wherein, The duration threshold is set based on the time interval for acquiring the power value, the frequency value, and the current value measured for the blower of the cooling tower that are correlated with each other.

21. A device for detecting faults in a cooling tower, comprising: A data acquirer configured to acquire power values, frequency values, and current values measured for the blower of the cooling tower that are correlated with each other; A controller coupled to the data acquirer and configured to detect faults in the cooling tower using the method according to any one of claims 8-20; And A user interface through which the controller gives an alarm to indicate that a fault in the cooling tower has been detected.

22. The device according to claim 21, comprising at least one of the following: A data memory coupled to the data acquirer and the controller and configured to store the data acquired by the data acquirer and the operation results of the controller; A building automation BA system, wherein the BA system includes one or more of the user interface and the controller.

23. The device according to claim 21, wherein, The cooling tower includes a blower and an inverter that performs variable frequency control on the blower, the data acquirer is configured to acquire data measured for the blower of the cooling tower from the inverter, and wherein the prediction model is constructed based on the inverter.

24. A computing device, comprising: One or more processors; And A memory storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to execute the method according to any one of claims 1 to 20.

25. A non-transitory storage medium storing computer-executable instructions that, when executed by a computer, cause the computer to execute the method according to any one of claims 1-20.

26. A computer program product, the computer program product comprising instructions that, when executed by a processor, implement the method according to any one of claims 1-20.

Images