Cooling tower equipment diagnosis method, device, terminal and medium based on deep learning

Abstract

The present application provides a cooling tower equipment diagnosis method, device, terminal and medium based on deep learning, which collects the current operation data of the refrigeration unit when the cooling pump of the refrigeration unit is connected in parallel; pre-processes the collected current operation data to obtain the pre-processed operation data; based on the cooling tower energy consumption model of each cooling tower and the cooling tower outlet water temperature model constructed, obtain the monitoring simulation data of each cooling tower according to the pre-processed operation data; based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, use the set maximum deviation threshold to perform equipment diagnosis on each cooling tower. Through the method of the present application, equipment diagnosis of a single cooling tower is realized, and the single cooling tower can be repaired in a timely manner.

Description

Technical Field

[0001] The present application relates to the technical field of equipment diagnosis, and in particular to a cooling tower equipment diagnosis method, device, terminal and medium based on deep learning. Background Art

[0002] Refrigeration units are usually composed of components such as chillers, cooling pumps, freezing pumps, cooling towers and sensors. They are used to control ambient temperature or cool equipment and play a vital role in industry. When performing equipment diagnosis on a cooling tower group, it is necessary to abstract and simplify it from the operating mechanism to a physical model in order to form a simulation model. Most of the existing technologies treat the cooling tower group as a whole for unified simulation modeling. However, in the process of equipment diagnosis, if the cooling tower group is treated as a whole, the failure of a single cooling tower may be masked by the whole, making it difficult to accurately judge the problem of a single device, resulting in the inability to timely discover and evaluate the failure of a single device. Summary of the invention

[0003] In view of the shortcomings of the prior art described above, the purpose of the present application is to provide a cooling tower equipment diagnosis method, device, terminal and medium based on deep learning, so as to solve the problem in the prior art that a single cooling tower cannot be diagnosed.

[0004] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides a cooling tower equipment diagnosis method based on deep learning, comprising: collecting the current operating data of the refrigeration unit when the cooling pumps of the refrigeration unit are connected in parallel; wherein the refrigeration unit comprises multiple cooling towers; preprocessing the collected current operating data to obtain the preprocessed current operating data; based on the constructed cooling tower energy consumption model of each cooling tower and the cooling tower outlet water temperature model, obtaining the monitoring simulation data of each cooling tower according to the preprocessed operating data; based on the error value between the monitoring simulation data and the actual operating data of each cooling tower, using the set maximum deviation threshold, performing equipment diagnosis on each cooling tower.

[0005] In some embodiments of the first aspect of the present application, the method of constructing a cooling tower energy consumption model for each cooling tower includes: preprocessing the acquired historical operation data of the refrigeration unit to obtain the preprocessed historical operation data; constructing a cooling tower energy consumption data set for each cooling tower based on the preprocessed historical operation data; inputting the constructed energy consumption data set for each cooling tower into the cooling tower frequency energy consumption model for training to obtain the cooling tower energy consumption model for each cooling tower.

[0006] In some embodiments of the first aspect of the present application, a method for constructing a cooling tower outlet water temperature model for each cooling tower includes: preprocessing the acquired historical operating data of the refrigeration unit to obtain the preprocessed historical operating data; constructing an outlet water temperature data set for each cooling tower based on the preprocessed historical operating data; and inputting the constructed outlet water temperature data set for each cooling tower into an echo state network for training to obtain a cooling tower outlet water temperature model for each cooling tower.

[0007] In some embodiments of the first aspect of the present application, the operating data include: chiller data, cooling tower data, environmental data and cooling main pipe data; wherein the chiller data include: chiller frequency data, cooling side inlet temperature data, cooling side outlet temperature data and cooling side flow data; the cooling tower data include: cooling tower frequency data, cooling tower energy consumption data and outlet water temperature data; the environmental data include: wet bulb temperature data and dry bulb temperature data; the cooling main pipe data include: cooling main pipe water supply temperature data.

[0008] In some embodiments of the first aspect of the present application, the preprocessing method includes: based on the switching time of the number of cooling towers, removing the data in the unstable state in the operating data to obtain preliminary preprocessing data; marking the preliminary preprocessing data for the state of the cooling machine according to the cooling machine frequency data in the preliminary preprocessing data to obtain the marked preliminary preprocessing data; calculating the total heat data of the cooling machine based on the marked preliminary preprocessing data, and removing null values ​​from the calculated total heat data of the cooling machine to obtain the final total heat data of the cooling machine; screening the cooling tower state of the preliminary preprocessing data according to the cooling tower frequency data in the preliminary preprocessing data to obtain the cooling tower Total opening quantity data; removing null values ​​from the environmental data in the preliminary preprocessing data, and filtering the environmental data after null value removal according to the set dry-bulb temperature screening threshold to obtain final environmental temperature data; removing null values ​​from the cooling main pipe data in the preliminary preprocessing data, and filtering the cooling main pipe data after null value removal according to the set temperature screening threshold to obtain final cooling main pipe data; integrating the cooling tower frequency data, cooling tower energy consumption data, final ambient temperature data, final chiller total heat data, cooling tower total opening quantity data and tower outlet water temperature data according to the time of the data to obtain preprocessed operation data.

[0009] In some embodiments of the first aspect of the present application, calculating the total heat data of the refrigerator based on the marked preliminary preprocessing data includes: calculating the heat of each refrigerator at each moment based on the cooling side inlet temperature, cooling side outlet temperature and cooling side flow at each moment in the marked preliminary preprocessing data; calculating the total heat of the refrigerator at each moment based on the calculated heat of each refrigerator at each moment and the refrigerator state of each refrigerator at each moment, thereby obtaining the total heat data of the refrigerator.

[0010] In some embodiments of the first aspect of the present application, based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, using the set maximum deviation threshold, equipment diagnosis of each cooling tower includes: calculating the energy consumption error value of the cooling tower based on the energy consumption simulation data in the monitoring simulation data of each cooling tower and the actual energy consumption data in the actual operation data; calculating the outlet water temperature error value of the cooling tower based on the outlet water temperature simulation data in the monitoring simulation data of the cooling tower and the actual outlet water temperature data in the actual operation data; obtaining the total error value of the cooling tower based on the energy consumption error value and the outlet water temperature error value of the cooling tower according to the set weight; when the total error value of the cooling tower is greater than the set maximum deviation threshold, the cooling tower is diagnosed as having low efficiency; when the total error value of the cooling tower is not greater than the set maximum deviation threshold, the cooling tower is diagnosed as having normal efficiency.

[0011] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides a cooling tower equipment diagnostic device based on deep learning, including: an acquisition module, used to collect the current operating data of the refrigeration unit when the cooling pump of the refrigeration unit is connected in parallel; wherein the refrigeration unit includes multiple cooling towers; a preprocessing module, connected to the acquisition module, used to preprocess the collected current operating data to obtain the preprocessed current operating data; a simulation module, connected to the preprocessing module, used to obtain the monitoring simulation data of each cooling tower based on the constructed cooling tower energy consumption model of each cooling tower and the cooling tower outlet water temperature model according to the preprocessed operating data; an effect diagnosis module, connected to the simulation module, used to perform equipment diagnosis on each cooling tower based on the error value between the monitoring simulation data and the actual operating data of each cooling tower, using a set maximum deviation threshold.

[0012] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides an electronic terminal, including: a processor and a memory; the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory, so that the terminal executes the cooling tower equipment diagnostic method based on deep learning.

[0013] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the deep learning-based cooling tower equipment diagnostic method is implemented.

[0014] As described above, the cooling tower equipment diagnosis method, device, terminal and medium based on deep learning of the present application have the following beneficial effects:

[0015] The current operation data of the refrigeration unit is collected when the cooling pumps of the refrigeration unit are connected in parallel; the collected current operation data is preprocessed to obtain the preprocessed operation data; based on the cooling tower energy consumption model of each cooling tower and the cooling tower outlet water temperature model constructed, the monitoring simulation data of each cooling tower is obtained according to the preprocessed operation data; based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, the equipment diagnosis of each cooling tower is performed using the set maximum deviation threshold. Through the method of the present application, the equipment diagnosis of a single cooling tower is realized, and the single cooling tower can be repaired in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Shown is a flow chart of a cooling tower equipment diagnosis method based on deep learning in one embodiment of the present application.

[0017] Figure 2 Shown is a specific schematic diagram of the cooling tower diagnosis process in one embodiment of the present application.

[0018] Figure 3 Shown is a schematic diagram of the echo state network structure in an embodiment of the present application.

[0019] Figure 4 Shown is a schematic diagram of the structure of a cooling tower equipment diagnostic device based on deep learning in one embodiment of the present application.

[0020] Figure 5 Shown is a schematic diagram of the structure of an electronic terminal in one embodiment of the present application. DETAILED DESCRIPTION

[0021] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0022] It should be noted that in the following description, with reference to the accompanying drawings, several embodiments of the present application are described in the accompanying drawings. It should be understood that other embodiments may also be used, and mechanical composition, structure, electrical and operational changes may be made without departing from the spirit and scope of the present application. The following detailed description should not be considered restrictive, and the scope of the embodiments of the present application is limited only by the claims of the published patents. The terms used here are only for describing specific embodiments and are not intended to limit the present application. Spatially related terms, such as "upper", "lower", "left", "right", "below", "below", "lower", "above", "upper", etc., may be used in the text to facilitate the description of the relationship between an element or feature shown in the figure and another element or feature.

[0023] In this application, unless otherwise clearly specified and limited, the terms "install", "connect", "connect", "fix", "hold" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0024] Furthermore, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "comprising" and "including" indicate the presence of the described features, operations, elements, components, items, kinds, and / or groups, but do not exclude the presence, occurrence or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. It should be further understood that the terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". Exceptions to this definition occur only when a combination of elements, functions, or operations are inherently mutually exclusive in some manner.

[0025] The present application provides a cooling tower equipment diagnosis method, device, terminal and medium based on deep learning, which collects the current operation data of the refrigeration unit when the cooling pump of the refrigeration unit is connected in parallel; pre-processes the collected current operation data to obtain the pre-processed operation data; based on the cooling tower energy consumption model of each cooling tower and the cooling tower outlet water temperature model constructed, obtain the monitoring simulation data of each cooling tower according to the pre-processed operation data; based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, use the set maximum deviation threshold to perform equipment diagnosis on each cooling tower. Through the method of the present application, equipment diagnosis of a single cooling tower is realized, and the single cooling tower can be repaired in a timely manner.

[0026] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the technical solution in the embodiments of the present invention is further described in detail through the following embodiments and in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the invention.

[0027] like Figure 1 As shown, a cooling tower equipment diagnosis method based on deep learning in an embodiment of the present invention is demonstrated.

[0028] The cooling tower equipment diagnosis method based on deep learning includes:

[0029] Step S101: collecting current operating data of the refrigeration unit when the cooling pumps of the refrigeration unit are connected in parallel.

[0030] It should be noted that a refrigeration unit is usually composed of components such as a chiller, a cooling pump, a freezing pump, a cooling tower, and a sensor. When the refrigeration unit is in operation, the cooling pumps included in it are usually connected in parallel.

[0031] In one embodiment, the refrigeration unit includes a plurality of cooling towers.

[0032] In one embodiment, the operating data includes: chiller data, cooling tower data, environmental data and cooling main pipe data; wherein, the chiller data includes: chiller frequency data dech_freq, cooling side inlet temperature data dech_temp_in, cooling side outlet temperature data dech_temp_out and cooling side flow data dech_flow; the cooling tower data includes: cooling tower frequency data freq, cooling tower energy consumption data power and outlet water temperature data temp_out; the environmental data includes: wet bulb temperature data deth_wb_temp and dry bulb temperature data deth_temp; the cooling main pipe data includes: cooling main pipe water supply temperature data decowp_temp_in.

[0033] In one embodiment, the refrigeration machine frequency data includes: the refrigeration machine frequency at multiple times; the cooling side inlet temperature data includes: the cooling side inlet temperature at multiple times; the cooling side outlet temperature data includes: the cooling side outlet temperature at multiple times; the cooling side flow data includes: the cooling side flow at multiple times; the cooling tower frequency data includes: the cooling tower frequency at multiple times; the cooling tower energy consumption data includes: the cooling tower energy consumption at multiple times; the outlet water temperature data includes: the outlet water temperature at multiple times; the wet bulb temperature data includes: the wet bulb temperature at multiple times; the dry bulb temperature data includes: the dry bulb temperature at multiple times; the cooling main water supply temperature data includes: the cooling main water supply temperature at multiple times.

[0034] In a specific embodiment, the start time is defined as start_time and the end time is defined as end_time. A python script is used to obtain the operation data of the refrigeration unit within the range from the start time to the end time.

[0035] In a specific embodiment, the current operation data of the refrigeration unit can be collected by setting sensors on components such as the refrigerator, cooling pump, freezing pump, cooling tower, etc.

[0036] For example, by setting a thermometer on the cooling main pipe, the current cooling main water supply temperature can be obtained; by setting a flow meter on the chiller, the current cooling side flow can be obtained.

[0037] Step S102: pre-processing the collected current operation data to obtain pre-processed current operation data.

[0038] The following is a detailed explanation of the preprocessing process:

[0039] When the number of cooling towers is switched, an unstable state will occur for 20 to 40 minutes. In this state, the outlet water temperature of the cooling tower will fluctuate up and down in order to meet the demand of the outlet water temperature setting value, and the data fluctuates greatly. Therefore, when obtaining the data of the cooling tower, chiller and ambient temperature, it is necessary to remove the data in the unstable operation state, especially the unstable state that occurs when the number of units is switched. Assuming that the switching time of the number of cooling towers is T1, all the data from T1 to T1+ΔT will be removed, that is, the data from T1 to T1+ΔT is the data in the unstable state. It should be noted that ΔT is usually 40 minutes. The data obtained after removing the data in the unstable state is the preliminary preprocessing data.

[0040] Furthermore, the first table is constructed, which is used to record the number of chiller opening data at each moment. The preliminary preprocessing data is screened and processed according to the chiller frequency data. The specific process of screening and processing is: if the chiller frequency of a chiller at a certain moment is greater than the set chiller frequency threshold, then the chiller state of the chiller at that moment is marked as 1, indicating that the chiller is in the open state at that moment; if the frequency of the chiller at that moment is not greater than the set chiller frequency threshold, then the chiller state of the chiller at that moment is marked as 0, indicating that the chiller is in the closed state. It should be noted that the chiller frequency threshold is usually set to 10Hz. After the preliminary preprocessing data is marked, the marked preliminary preprocessing data is obtained.

[0041] For example, a refrigeration unit has three refrigeration devices, coded as dech01, dech02, and dech03. Construct dech01_open column, dech02_open column, and dech03_open column to record the refrigeration status of the corresponding refrigeration devices at each moment. When the refrigeration status of dech01 at a certain moment is marked as 1, the refrigeration status is saved in the corresponding position of the dech01_open column.

[0042] Furthermore, a subtraction operation is performed on the cooling side inlet temperature and the cooling side outlet temperature at each moment in the marked preliminary preprocessing data to obtain the inlet and outlet temperature difference of the cooling side at each moment; the inlet and outlet temperature difference of the cooling side obtained at each moment is multiplied by the cooling side flow rate to obtain the heat Q of each refrigerator at each moment; the heat of each refrigerator at each moment and the corresponding refrigerator state are multiplied to obtain the multiplication result of each refrigerator at each moment; the multiplication results of each refrigerator at the same moment are added to obtain the total heat of the refrigerator at each moment, and then the total heat data of the refrigerator is obtained; wherein, the total heat data of the refrigerator includes the total heat of the refrigerator at multiple moments; the null values ​​in the obtained total heat data of the refrigerator are removed to obtain the final total heat data of the refrigerator.

[0043] For example, a refrigeration unit has three cooling devices, coded as dech01, dech02 and dech03. At time 1, the inlet temperature of the cooling side of dech01 is q1_in, and the outlet temperature of the cooling side of dech01 is q1_out. It is calculated that the inlet and outlet temperature difference of the cooling side of dech01 at time 1 is (q1_out-q1_in). The cooling side flow rate of dech01 at time 1 is F, and it is calculated that the heat of dech01 at time 1 is Q1=F×(q1_out-q1_in). The method of calculating the heat of dech02 and dech03 at time 1 is the same as that of dech01, and will not be repeated here. After calculation, it is found that at time 1, the heat of dech01 is Q1 and the cooling machine state is 1, the heat of dech02 is Q2 and the cooling machine state is 0, and the heat of dech03 is Q3 and the cooling machine state is 1. (Q1×1) is the multiplication result of dech01 at time 1, (Q2×0) is the multiplication result of dech02 at time 1, and (Q3×1) is the multiplication result of dech03 at time 1. Add the multiplication results of each chiller at time 1, and the total heat of the chiller at time 1 is Q1×1+Q2×0+Q3×1.

[0044] Furthermore, a second table is constructed, which is used to record the number of cooling towers that are open at each moment. Data is marked according to the model performance of the cooling tower. The specific process of marking is: if the frequency of a cooling tower at a certain moment is greater than the set first cooling tower frequency threshold, the cooling pump state of the cooling tower at that moment is marked as 1, indicating that the cooling tower is in the open state at that moment; if the frequency of the cooling tower at that moment is not greater than the set first cooling tower frequency threshold, the cooling pump state of the cooling tower at that moment is marked as 0, indicating that the cooling tower is in the closed state at that moment. It should be noted that the first cooling tower frequency threshold is usually set to 10Hz.

[0045] After the marking is completed, the data whose cooling tower frequency is greater than the set second cooling tower frequency threshold and less than the set third cooling tower frequency threshold, and whose energy consumption is greater than the set energy consumption threshold are screened in the marked data. It should be noted that the second cooling tower frequency threshold is usually set to 15Hz, the third cooling tower frequency threshold is usually set to 50Hz, and the energy consumption threshold is usually set to 0kwh.

[0046] After the filtering is completed, all data containing null value time points in the filtered data are removed.

[0047] According to the cooling pump status of each cooling tower, the total number of cooling towers opened at each moment is calculated according to the time, and the total number of cooling towers opened at multiple moments is output as the total number of cooling towers opened data.

[0048] For example, suppose there are three cooling towers in the refrigeration unit, namely cooling tower A, cooling tower B and cooling tower C. The cooling pump state of cooling tower A at time 1 is 1, the cooling pump state of cooling tower B at time 1 is 0, and the cooling pump state of cooling tower C at time 1 is 1. Then, the total number of cooling towers opened at time 1 is 2.

[0049] Furthermore, null values ​​are removed from the environmental data in the preliminary preprocessing data, and data with wet-bulb temperatures greater than 0°C and dry-bulb temperatures less than 40°C in the environmental data after null values ​​are removed are screened out to obtain final environmental temperature data.

[0050] Furthermore, the cooling main pipe data in the preliminary preprocessing data are null-removed, and the data with cooling main pipe water supply temperature greater than 14°C are screened out in the cooling main pipe data after null-removal to obtain the final cooling main pipe data. Furthermore, according to the time of the data, the cooling tower frequency data, cooling tower energy consumption data, final ambient temperature data, final chiller total heat data, cooling tower total opening quantity data and tower outlet water temperature data are integrated to obtain the preprocessed operation data.

[0051] Specifically, the cooling tower frequency data, cooling tower energy consumption data, final ambient temperature data, final chiller total heat data, cooling tower total opening quantity data and outlet water temperature data at the same time are integrated into an array, and the multiple arrays obtained after integration are the preprocessed operation data.

[0052] For example, the cooling tower frequency at time 1, the cooling tower energy consumption, the final ambient temperature, the final total heat of the chiller, the total number of cooling tower openings, and the outlet water temperature are integrated into the first array; the cooling tower frequency at time 2, the cooling tower energy consumption, the final ambient temperature, the final total heat of the chiller, the total number of cooling tower openings, and the outlet water temperature are integrated into the second array.

[0053] Step S103: Based on the constructed cooling tower energy consumption model and cooling tower outlet water temperature model of each cooling tower, monitoring simulation data of each cooling tower is obtained according to the pre-processed operation data.

[0054] In one embodiment, the method of constructing a cooling tower energy consumption model for each cooling tower includes: preprocessing the acquired historical operation data of the refrigeration unit to obtain the preprocessed historical operation data; constructing a cooling tower energy consumption data set for each cooling tower based on the preprocessed historical operation data; inputting the constructed energy consumption data set for each cooling tower into the cooling tower frequency energy consumption model for training to obtain the cooling tower energy consumption model for each cooling tower.

[0055] It should be noted that, assuming that the refrigeration unit has three cooling towers, a corresponding cooling tower energy consumption model is constructed for each cooling tower, and the number of cooling tower energy consumption models finally constructed is three.

[0056] In one embodiment, the operation data includes: chiller data, cooling tower data, environmental data and cooling main pipe data; wherein the chiller data includes: chiller frequency data dech_freq, cooling side inlet temperature data dech_temp_in, cooling side outlet temperature data dech_temp_out and cooling side flow data dech_flow; cooling tower data includes: cooling tower frequency data freq, cooling tower energy consumption data power and outlet water temperature data temp_out; environmental data includes: wet bulb temperature data deth_wb_temp and dry bulb temperature data deth_temp; cooling main pipe data includes: cooling main pipe water supply temperature data decowp_temp_in. .

[0057] In one embodiment, the refrigeration machine frequency data includes: the refrigeration machine frequency at multiple times; the cooling side inlet temperature data includes: the cooling side inlet temperature at multiple times; the cooling side outlet temperature data includes: the cooling side outlet temperature at multiple times; the cooling side flow data includes: the cooling side flow at multiple times; the cooling tower frequency data includes: the cooling tower frequency at multiple times; the cooling tower energy consumption data includes: the cooling tower energy consumption at multiple times; the outlet water temperature data includes: the outlet water temperature at multiple times; the wet bulb temperature data includes: the wet bulb temperature at multiple times; the dry bulb temperature data includes: the dry bulb temperature at multiple times; the cooling main water supply temperature data includes: the cooling main water supply temperature at multiple times.

[0058] In a specific embodiment, the operation data of the refrigeration unit in the past period of time is obtained as the historical operation data. It should be noted that the past period of time may be the past two months or the past year, and the present invention is not limited to this.

[0059] It should be noted that the manner of preprocessing the acquired historical operation data of the refrigeration unit in this embodiment is the same as the manner of preprocessing the current operation data in the above embodiment, so it will not be repeatedly explained here.

[0060] The following will be combined with the attached Figure 2 A detailed explanation of how the cooling tower energy consumption model is constructed for each cooling tower is provided:

[0061] like Figure 2As shown in the process, the cooling tower frequency data and cooling tower energy consumption data of cooling tower A in the refrigeration unit are obtained from the preprocessed historical operation data, and the cooling tower frequency data of cooling tower A is used as the input of the model, and the cooling tower energy consumption data of cooling tower A is used as the output of the model to construct the cooling tower energy consumption data set of cooling tower A. The constructed cooling tower energy consumption data set of cooling tower A is divided according to the ratio of training set: test set = 4:1, and the cooling tower energy consumption training set and cooling tower energy consumption test set corresponding to cooling tower A are obtained.

[0062] The cooling tower energy consumption training set of cooling tower A is input into the constructed cubic relationship fitting curve for training, and the cooling tower energy consumption test set of cooling tower A is used for verification to determine the final weight parameters to obtain the cooling tower energy consumption model of cooling tower A.

[0063] The formula of the cubic relationship fitting curve refers to the following formula 1:

[0064] P=(c1×F+c2×F 2 +c3×F 3 )+c4; (Formula 1);

[0065] Among them, c1, c2, c3 and c4 represent weight parameters, F represents cooling tower frequency data, and P represents cooling tower energy consumption data.

[0066] It should be noted that the method of constructing the cooling tower energy consumption model of the remaining cooling towers in the refrigeration unit is the same as that of cooling tower A, so it will not be repeated here.

[0067] In one embodiment, a method for constructing a cooling tower outlet water temperature model for each cooling tower includes: preprocessing the acquired historical operation data of the refrigeration unit to obtain the preprocessed historical operation data; constructing an outlet water temperature data set for each cooling tower based on the preprocessed historical operation data; and inputting the constructed outlet water temperature data set for each cooling tower into an echo state network for training to obtain a cooling tower outlet water temperature model for each cooling tower.

[0068] In one embodiment, the operating data includes: chiller data, cooling tower data, environmental data and cooling main pipe data; wherein, the chiller data includes: chiller frequency data dech_freq, cooling side inlet temperature data dech_temp_in, cooling side outlet temperature data dech_temp_out and cooling side flow data dech_flow; the cooling tower data includes: cooling tower frequency data freq, cooling tower energy consumption data power and outlet water temperature data temp_out; the environmental data includes: wet bulb temperature data deth_wb_temp and dry bulb temperature data deth_temp; the cooling main pipe data includes: cooling main pipe water supply temperature data decowp_temp_in.

[0069] In one embodiment, the refrigeration machine frequency data includes: the refrigeration machine frequency at multiple times; the cooling side inlet temperature data includes: the cooling side inlet temperature at multiple times; the cooling side outlet temperature data includes: the cooling side outlet temperature at multiple times; the cooling side flow data includes: the cooling side flow at multiple times; the cooling tower frequency data includes: the cooling tower frequency at multiple times; the cooling tower energy consumption data includes: the cooling tower energy consumption at multiple times; the outlet water temperature data includes: the outlet water temperature at multiple times; the wet bulb temperature data includes: the wet bulb temperature at multiple times; the dry bulb temperature data includes: the dry bulb temperature at multiple times; the cooling main water supply temperature data includes: the cooling main water supply temperature at multiple times.

[0070] In a specific embodiment, the operation data of the refrigeration unit in the past period of time is obtained as the historical operation data. It should be noted that the past period of time may be the past two months or the past year, and the present invention is not limited to this.

[0071] It should be noted that the manner of preprocessing the acquired historical operation data of the refrigeration unit in this embodiment is the same as the manner of preprocessing the current operation data in the above embodiment, so it will not be repeatedly explained here.

[0072] The following will be combined with the attached Figure 2 A detailed explanation of how to construct the cooling tower outlet water temperature model for each cooling tower is provided:

[0073] like Figure 2As shown in the process, the wet bulb temperature data, dry bulb temperature data, final total heat data of the chiller, total opening number data of the cooling tower, cooling tower frequency data of cooling tower A and outlet water temperature data of cooling tower A are obtained from the pre-processed historical operation data of the refrigeration unit. The obtained wet bulb temperature data, dry bulb temperature data, final total heat data of the chiller, total opening number data of the cooling tower, and cooling tower frequency data of cooling tower A are used as the input of the cooling tower outlet water temperature model, and the outlet water temperature data of cooling tower A is used as the output of the cooling tower outlet water temperature model to construct the outlet water temperature data set of cooling tower A. The constructed outlet water temperature data set of cooling tower A is divided according to the ratio of training set: test set = 4:1 to obtain the corresponding outlet water temperature training set and outlet water temperature test set.

[0074] Since the water temperature out of the cooling tower is not only affected by the equipment frequency, but also controlled by the chiller and even the ambient temperature, there are many influencing factors, and the current data will be affected by historical data. Therefore, the formula method cannot be used to directly fit the curve, but the echo state network (ESN) is used to construct it.

[0075] It should be noted that the echo state network (ESN) is a new type of artificial neural network, whose topology includes an input layer, a hidden layer (i.e., a reservoir), and an output layer. The core structure of the ESN is a randomly generated and unchanging reservoir, which consists of a large number of sparsely connected neurons, has a short-term memory function, and can contain the operating state of the system.

[0076] The construction process specifically includes: determining Figure 3 The scale and topology of the ESN network shown in Figure 3 The input layer Nu, the reservoir state W res And the output layer Nv), select the appropriate number of hidden layer nodes, and build sparse recurrent connections through random connections, and set the key parameters of the ESN network, such as the leaky bucket coefficient, spectral radius, and weight matrix range.

[0077] The obtained training set of the outlet water temperature of cooling tower A (including wet bulb temperature data deth_wb_temp, dry bulb temperature data deth_temp, final total heat data of the chiller Q_sum, total opening number data of cooling tower open_sum, cooling tower frequency data freq of cooling tower A and outlet water temperature data temp_out of cooling tower A) is input into the ESN network, and the state is propagated through the sparse random connection of the network to obtain the output of the network. The output weight matrix is ​​trained using the historical target output and the output of the network to make the network's prediction as close to the actual value as possible. After the training is completed, the outlet water temperature test set of cooling tower A is used to verify the model effect, and the outlet water temperature model of cooling tower A is saved.

[0078] It should be noted that the method of constructing the cooling tower outlet water temperature model of the remaining cooling towers in the refrigeration unit is the same as that of cooling tower A, so it will not be repeated here.

[0079] In one embodiment, the monitoring simulation data of each cooling tower includes: energy consumption simulation data of each cooling tower and outlet water temperature simulation data of each cooling tower.

[0080] In one embodiment, based on a cooling tower energy consumption model constructed for each cooling tower, energy consumption simulation data for each cooling tower is obtained according to the cooling tower frequency data of each cooling tower in the preprocessed operating data; based on a cooling tower outlet water temperature model constructed for each cooling tower, according to the wet-bulb temperature data, dry-bulb temperature data, final total heat data of the chiller, total number of cooling tower openings data and cooling tower frequency data of each cooling tower in the preprocessed operating data, outlet water temperature simulation data for each cooling tower is obtained.

[0081] Step S104: Based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, equipment diagnosis is performed on each cooling tower using a set maximum deviation threshold.

[0082] In one embodiment, based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, using the set maximum deviation threshold, equipment diagnosis of each cooling tower includes: calculating the energy consumption error value of the cooling tower based on the energy consumption simulation data in the monitoring simulation data of each cooling tower and the actual energy consumption data in the actual operation data; calculating the outlet water temperature error value of the cooling tower based on the outlet water temperature simulation data in the monitoring simulation data of the cooling tower and the actual outlet water temperature data in the actual operation data; obtaining the total error value of the cooling tower based on the energy consumption error value and the outlet water temperature error value of the cooling tower according to the set weight; when the total error value of the cooling tower is greater than the set maximum deviation threshold, the cooling tower is diagnosed as having low efficiency; when the total error value of the cooling tower is not greater than the set maximum deviation threshold, the cooling tower is diagnosed as having normal efficiency.

[0083] In a specific embodiment, the weight of the energy consumption error value is set to a, and the weight of the outlet water temperature error value is set to b; wherein, a+b=1; the total error value=energy consumption error value*a+outlet water temperature error value*b.

[0084] In one embodiment, a=0.6 and b=0.4.

[0085] It should be noted that those skilled in the art can set the weight value according to the actual situation on site, and the present invention is not limited to this.

[0086] It should also be noted that as the cooling tower is used, the efficiency of the cooling tower may be affected by the water quality of the cooling water. When the cooling water contains a large amount of impurities, sediment, hard water or biological pollution, these substances will form mud, scale or biofilm inside the cooling tower, reducing the heat exchange efficiency of the cooling tower. In addition, if the fan of the cooling tower is dusty, the blades are damaged or the operation is abnormal, the fan's air volume will be reduced, affecting the cooling effect and reducing the refrigeration effect. Therefore, when a cooling tower is diagnosed as inefficient, it is necessary to clean the cooling tower and descale it.

[0087] Similar to the above-mentioned embodiment, the present invention also provides a cooling tower equipment diagnostic device based on deep learning.

[0088] The following provides specific embodiments in conjunction with the accompanying drawings:

[0089] like Figure 4 As shown, it is a structural schematic diagram of a cooling tower equipment diagnostic device based on deep learning in an embodiment of the present invention.

[0090] The cooling tower equipment diagnostic device 4 based on deep learning includes:

[0091] The collection module 41 is used to collect the current operation data of the refrigeration unit when the cooling pumps of the refrigeration unit are connected in parallel; wherein the refrigeration unit includes a plurality of cooling towers;

[0092] A preprocessing module 42, connected to the acquisition module 41, is used to preprocess the acquired current operation data to obtain the preprocessed current operation data;

[0093] A simulation module 43, connected to the preprocessing module 42, is used to obtain monitoring simulation data of each cooling tower based on the constructed cooling tower energy consumption model and cooling tower outlet water temperature model of each cooling tower and the preprocessed current operating data;

[0094] The effect diagnosis module 44 is connected to the simulation module 43 and is used to diagnose the cooling effect of each cooling tower based on the error value between the monitoring simulation data and the actual operation data of each cooling tower and using a set maximum deviation threshold.

[0095] It should be noted that the modules provided in this embodiment are similar to the methods provided above in implementation, so they will not be described in detail. It should also be noted that it should be understood that the division of the modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the preprocessing module 42 can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above preprocessing module 42. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0096] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0097] In one embodiment, the method of constructing a cooling tower energy consumption model for each cooling tower includes: preprocessing the acquired historical operation data of the refrigeration unit to obtain the preprocessed historical operation data; constructing a cooling tower energy consumption data set for each cooling tower based on the preprocessed historical operation data; inputting the constructed energy consumption data set for each cooling tower into the cooling tower frequency energy consumption model for training to obtain the cooling tower energy consumption model for each cooling tower.

[0098] In one embodiment, a method for constructing a cooling tower outlet water temperature model for each cooling tower includes: preprocessing the acquired historical operation data of the refrigeration unit to obtain the preprocessed historical operation data; constructing an outlet water temperature data set for each cooling tower based on the preprocessed historical operation data; and inputting the constructed outlet water temperature data set for each cooling tower into an echo state network for training to obtain a cooling tower outlet water temperature model for each cooling tower.

[0099] In one embodiment, the operating data includes: chiller data, cooling tower data, environmental data and cooling main pipe data; wherein the chiller data includes: chiller frequency data, cooling side inlet temperature data, cooling side outlet temperature data and cooling side flow data; the cooling tower data includes: cooling tower frequency data, cooling tower energy consumption data and outlet water temperature data; the environmental data includes: wet bulb temperature data and dry bulb temperature data; the cooling main pipe data includes: cooling main pipe water supply temperature data.

[0100] In one embodiment, the preprocessing method includes: based on the switching time of the number of cooling towers, removing the data in the unstable state in the operating data to obtain preliminary preprocessing data; marking the preliminary preprocessing data for the state of the cooling machine according to the cooling machine frequency data in the preliminary preprocessing data to obtain the marked preliminary preprocessing data; calculating the total heat data of the cooling machine based on the marked preliminary preprocessing data, and removing the null value of the calculated total heat data of the cooling machine to obtain the final total heat data of the cooling machine; screening the cooling tower state of the preliminary preprocessing data according to the cooling tower frequency data in the preliminary preprocessing data to obtain the total number of cooling towers opened data; removing null values ​​from the environmental data in the preliminary preprocessing data, and filtering the environmental data after the null values ​​are removed according to the set dry-bulb and wet-bulb temperature screening thresholds to obtain final environmental temperature data; removing null values ​​from the cooling main pipe data in the preliminary preprocessing data, and filtering the cooling main pipe data after the null values ​​are removed according to the set temperature screening thresholds to obtain final cooling main pipe data; integrating the cooling tower frequency data, the cooling tower energy consumption data, the final environmental temperature data, the final total heat data of the chiller, the total number of cooling tower openings data, and the outlet water temperature data according to the time of the data to obtain preprocessed operation data.

[0101] In one embodiment, calculating the total heat data of the refrigerator based on the marked preliminary preprocessing data includes: calculating the heat of each refrigerator at each moment based on the cooling side inlet temperature, cooling side outlet temperature and cooling side flow at each moment in the marked preliminary preprocessing data; calculating the total heat of the refrigerator at each moment based on the calculated heat of each refrigerator at each moment and the refrigerator state of each refrigerator at each moment, thereby obtaining the total heat data of the refrigerator.

[0102] In one embodiment, based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, using the set maximum deviation threshold, equipment diagnosis of each cooling tower includes: calculating the energy consumption error value of the cooling tower based on the energy consumption simulation data in the monitoring simulation data of each cooling tower and the actual energy consumption data in the actual operation data; calculating the outlet water temperature error value of the cooling tower based on the outlet water temperature simulation data in the monitoring simulation data of the cooling tower and the actual outlet water temperature data in the actual operation data; obtaining the total error value of the cooling tower based on the energy consumption error value and the outlet water temperature error value of the cooling tower according to the set weight; when the total error value of the cooling tower is greater than the set maximum deviation threshold, the cooling tower is diagnosed as having low efficiency; when the total error value of the cooling tower is not greater than the set maximum deviation threshold, the cooling tower is diagnosed as having normal efficiency.

[0103] like Figure 5 As shown, it is a schematic diagram of the structure of the electronic terminal in an embodiment of the present invention.

[0104] The terminal 5 comprises: a processor 52 and a memory 51; the memory 51 is used to store a computer program; the processor 52 is used to execute the computer program stored in the memory, so that the terminal 5 performs the following steps: Figure 1 The cooling tower equipment diagnosis method based on deep learning.

[0105] Optionally, the number of the memory 51 can be one or more, the number of the processor 52 can be one or more, and Figure 5 Take one as an example.

[0106] Optionally, the processor 52 in the control device will Figure 1 In the above steps, one or more instructions corresponding to the process of the application are loaded into the memory 51, and the processor 52 runs the application stored in the first memory, thereby achieving the following Figure 1 Various functions in the deep learning-based cooling tower equipment diagnosis method.

[0107] Optionally, the memory 51 may include but is not limited to high-speed random access memory and non-volatile memory. For example, one or more disk storage devices, flash memory devices or other non-volatile solid-state storage devices; the processor 52 may include but is not limited to a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0108] Optionally, the processor 52 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0109] The present invention also provides a computer-readable storage medium storing a computer program, wherein the computer program is executed as follows: Figure 1 The cooling tower equipment diagnostic method based on deep learning. The computer-readable storage medium may include, but is not limited to, a floppy disk, an optical disk, a CD-ROM (read-only disk memory), a magneto-optical disk, a ROM (read-only memory), a RAM (random access memory), an EPROM (erasable programmable read-only memory), an EEPROM (electrically erasable programmable read-only memory), a magnetic card or an optical card, a flash memory, or other types of media / machine-readable media suitable for storing machine-executable instructions. The computer-readable storage medium may be a product that is not connected to a computer device, or it may be a component that is connected to a computer device for use.

[0110] In some embodiments of the present invention, the computer readable and writable storage medium may include a read-only memory, a random access memory, an EEPROM, a CD-ROM or other optical disk storage device, a magnetic disk storage device or other magnetic storage device, a flash memory, a USB flash drive, a mobile hard disk, or any other medium that can be used to store the desired program code in the form of an instruction or data structure and can be accessed by a computer. In addition, any connection can be appropriately referred to as a computer-readable medium. For example, if the instruction is sent from a website, server or other remote source using a coaxial cable, a fiber optic cable, a twisted pair, a digital subscriber line (DSL), or wireless technologies such as infrared, radio and microwaves, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio and microwaves are included in the definition of the medium. However, it should be understood that computer readable and writable storage media and data storage media do not include connections, carriers, signals or other temporary media, but are intended to be non-temporary, tangible storage media. Disk and disc, as used in this application, includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers.

[0111] In summary, the present application provides a cooling tower equipment diagnosis method, device, terminal and medium based on deep learning, which collects the current operating data of the refrigeration unit when the cooling pump of the refrigeration unit is connected in parallel; pre-processes the collected current operating data to obtain the pre-processed operating data; based on the cooling tower energy consumption model of each cooling tower and the cooling tower outlet water temperature model constructed, obtain the monitoring simulation data of each cooling tower according to the pre-processed operating data; based on the error value between the monitoring simulation data and the actual operating data of each cooling tower, use the set maximum deviation threshold to perform equipment diagnosis on each cooling tower. Through the method of the present application, the equipment diagnosis of a single cooling tower is realized, and then the single cooling tower can be repaired in time. Therefore, the present application effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0112] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A cooling tower equipment diagnosis method based on deep learning, characterized in that: include: Collecting current operation data of the refrigeration unit when the cooling pumps of the refrigeration unit are connected in parallel; wherein the refrigeration unit includes a plurality of cooling towers; Preprocessing the collected current operation data to obtain the preprocessed current operation data; Based on the constructed cooling tower energy consumption model of each cooling tower and the cooling tower outlet water temperature model, monitoring simulation data of each cooling tower is obtained according to the pre-processed operation data; Among them, the methods of constructing the cooling tower energy consumption model of each cooling tower include: Preprocessing the acquired historical operation data of the refrigeration unit to obtain the preprocessed historical operation data; Based on the pre-processed historical operation data, a cooling tower energy consumption data set of each cooling tower is constructed; and wherein, it specifically includes: The cooling tower frequency data and cooling tower energy consumption data of each cooling tower in the refrigeration unit are obtained from the pre-processed historical operation data, and the cooling tower frequency data of each cooling tower is used as the input of the model, and the cooling tower energy consumption data of each cooling tower is used as the output of the model to construct a cooling tower energy consumption data set for each cooling tower; The constructed energy consumption data set of each cooling tower is input into the cooling tower frequency energy consumption model for training to obtain the cooling tower energy consumption model of each cooling tower; and wherein, it specifically includes: The cooling tower energy consumption data set of each cooling tower constructed is divided to obtain a cooling tower energy consumption training set and a cooling tower energy consumption test set corresponding to each cooling tower; the cooling tower energy consumption training set of each cooling tower is input into the constructed cubic relationship fitting curve for training, and the cooling tower energy consumption test set of each cooling tower is used for verification to determine the final weight parameter to obtain the cooling tower energy consumption model of the cooling tower; The methods for constructing the cooling tower outlet water temperature model for each cooling tower include: Preprocessing the acquired historical operation data of the refrigeration unit to obtain the preprocessed historical operation data; Based on the pre-processed historical operation data, a water temperature dataset of each cooling tower outlet is constructed; wherein, it specifically includes: Obtain wet-bulb temperature data, dry-bulb temperature data, final total heat data of the chiller, total opening number data of cooling towers, cooling tower frequency data of each cooling tower, and outlet water temperature data of each cooling tower from the pre-processed historical operation data of the refrigeration unit; use the obtained wet-bulb temperature data, dry-bulb temperature data, final total heat data of the chiller, total opening number data of cooling towers, and cooling tower frequency data of each cooling tower as inputs of the cooling tower outlet water temperature model; use the outlet water temperature data of each cooling tower as outputs of the cooling tower outlet water temperature model, and construct an outlet water temperature data set for each cooling tower; The constructed water temperature data set of each cooling tower outlet is input into the echo state network for training to obtain the cooling tower water temperature model of each cooling tower; Based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, equipment diagnosis is performed on each cooling tower using the set maximum deviation threshold; Among them, based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, using the set maximum deviation threshold, the equipment diagnosis of each cooling tower includes: Calculate the energy consumption error value of the cooling tower based on the energy consumption simulation data in the monitoring simulation data of each cooling tower and the actual energy consumption data in the actual operation data; Calculating the outlet water temperature error value of the cooling tower based on the outlet water temperature simulation data in the monitoring simulation data of the cooling tower and the actual outlet water temperature data in the actual operation data; According to the set weight, based on the energy consumption error value of the cooling tower and the outlet water temperature error value, the total error value of the cooling tower is obtained; When the total error value of the cooling tower is greater than a set maximum deviation threshold, the cooling tower is diagnosed as having low efficiency; When the total error value of the cooling tower is not greater than a set maximum deviation threshold, the cooling tower is diagnosed as having normal efficiency.

2. The cooling tower equipment diagnosis method based on deep learning according to any one of claim 1, characterized in that: The operating data includes: chiller data, cooling tower data, environmental data and cooling main pipe data; among them, the chiller data includes: chiller frequency data, cooling side inlet temperature data, cooling side outlet temperature data and cooling side flow data; the cooling tower data includes: cooling tower frequency data, cooling tower energy consumption data and outlet water temperature data; the environmental data includes: wet bulb temperature data and dry bulb temperature data; the cooling main pipe data includes: cooling main pipe water supply temperature data.

3. The cooling tower equipment diagnosis method based on deep learning according to claim 2 is characterized in that: Preprocessing methods include: Based on the number of cooling towers switching time, the unstable data in the operation data is removed to obtain preliminary preprocessing data; According to the cooling machine frequency data in the preliminary preprocessing data, marking the cooling machine status of the preliminary preprocessing data to obtain marked preliminary preprocessing data; Calculating the total heat data of the refrigerator based on the marked preliminary preprocessed data, and removing null values ​​from the calculated total heat data of the refrigerator to obtain the final total heat data of the refrigerator; According to the cooling tower frequency data in the preliminary preprocessing data, the preliminary preprocessing data is screened for cooling tower status to obtain total cooling tower opening quantity data; Remove null values ​​from the environmental data in the preliminary preprocessed data, and filter the environmental data after the null values ​​are removed according to the set dry-bulb and wet-bulb temperature screening thresholds to obtain final environmental temperature data; Remove null values ​​from the cooling main pipe data in the preliminary preprocessing data, and filter the cooling main pipe data after the null values ​​are removed according to a set temperature screening threshold to obtain final cooling main pipe data; According to the time of the data, the cooling tower frequency data, cooling tower energy consumption data, final ambient temperature data, final chiller total heat data, cooling tower total opening quantity data and tower outlet water temperature data are integrated to obtain the pre-processed operation data.

4. The cooling tower equipment diagnosis method based on deep learning according to claim 3 is characterized in that: Calculating the total heat data of the chiller based on the marked preliminary preprocessed data includes: Calculate the heat of each chiller at each moment based on the cooling side inlet temperature, cooling side outlet temperature and cooling side flow rate at each moment in the marked preliminary preprocessing data; Based on the calculated heat of each refrigerator at each moment and the refrigerator state of each refrigerator at each moment, the total heat of the refrigerator at each moment is calculated, and then the total heat data of the refrigerator is obtained.

5. A cooling tower equipment diagnostic device based on deep learning, characterized in that: include: A collection module, used for collecting current operation data of the refrigeration unit when the cooling pumps of the refrigeration unit are connected in parallel; wherein the refrigeration unit includes a plurality of cooling towers; A preprocessing module, connected to the acquisition module, for preprocessing the acquired current operation data to obtain the preprocessed current operation data; A simulation module connected to the preprocessing module, for obtaining monitoring simulation data of each cooling tower based on the constructed cooling tower energy consumption model of each cooling tower and the cooling tower outlet water temperature model according to the preprocessed operation data; Among them, the methods of constructing the cooling tower energy consumption model of each cooling tower include: Preprocessing the acquired historical operation data of the refrigeration unit to obtain the preprocessed historical operation data; Based on the pre-processed historical operation data, a cooling tower energy consumption data set of each cooling tower is constructed; and wherein, it specifically includes: The cooling tower frequency data and cooling tower energy consumption data of each cooling tower in the refrigeration unit are obtained from the pre-processed historical operation data, and the cooling tower frequency data of each cooling tower is used as the input of the model, and the cooling tower energy consumption data of each cooling tower is used as the output of the model to construct a cooling tower energy consumption data set for each cooling tower; The constructed energy consumption data set of each cooling tower is input into the cooling tower frequency energy consumption model for training to obtain the cooling tower energy consumption model of each cooling tower; and wherein, it specifically includes: The cooling tower energy consumption data set of each cooling tower constructed is divided to obtain a cooling tower energy consumption training set and a cooling tower energy consumption test set corresponding to each cooling tower; the cooling tower energy consumption training set of each cooling tower is input into the constructed cubic relationship fitting curve for training, and the cooling tower energy consumption test set of each cooling tower is used for verification to determine the final weight parameter to obtain the cooling tower energy consumption model of the cooling tower; The methods for constructing the cooling tower outlet water temperature model for each cooling tower include: Preprocessing the acquired historical operation data of the refrigeration unit to obtain the preprocessed historical operation data; Based on the pre-processed historical operation data, a water temperature dataset of each cooling tower outlet is constructed; wherein, it specifically includes: Obtain wet-bulb temperature data, dry-bulb temperature data, final total heat data of the chiller, total opening number data of cooling towers, cooling tower frequency data of each cooling tower, and outlet water temperature data of each cooling tower from the pre-processed historical operation data of the refrigeration unit; use the obtained wet-bulb temperature data, dry-bulb temperature data, final total heat data of the chiller, total opening number data of cooling towers, and cooling tower frequency data of each cooling tower as inputs of the cooling tower outlet water temperature model; use the outlet water temperature data of each cooling tower as outputs of the cooling tower outlet water temperature model, and construct an outlet water temperature data set for each cooling tower; The constructed water temperature data set of each cooling tower outlet is input into the echo state network for training to obtain the cooling tower water temperature model of each cooling tower; An effect diagnosis module, connected to the simulation module, is used to perform equipment diagnosis on each cooling tower based on the error value between the monitoring simulation data and the actual operation data of each cooling tower and using a set maximum deviation threshold; Among them, based on the error value between the monitoring simulation data and the actual operation data of each cooling tower, using the set maximum deviation threshold, the equipment diagnosis of each cooling tower includes: Calculate the energy consumption error value of the cooling tower based on the energy consumption simulation data in the monitoring simulation data of each cooling tower and the actual energy consumption data in the actual operation data; Calculating the outlet water temperature error value of the cooling tower based on the outlet water temperature simulation data in the monitoring simulation data of the cooling tower and the actual outlet water temperature data in the actual operation data; According to the set weight, based on the energy consumption error value of the cooling tower and the outlet water temperature error value, the total error value of the cooling tower is obtained; When the total error value of the cooling tower is greater than a set maximum deviation threshold, the cooling tower is diagnosed as having low efficiency; When the total error value of the cooling tower is not greater than a set maximum deviation threshold, the cooling tower is diagnosed as having normal efficiency.

6. An electronic terminal, characterized in that: include: Processor and memory; The memory is used to store computer programs; The processor is configured to execute the computer program stored in the memory, so as to enable the terminal to perform the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method described in any one of claims 1 to 4 is implemented.

Images