Water cooling system fault detection method and device, equipment, storage medium and product

Abstract

The invention discloses a water-cooling system fault detection method, device and equipment, a storage medium and a product, and relates to the technical field of wind turbine generator water-cooling system fault detection, and the method comprises the steps: obtaining the current operation data of a water-cooling system; the current operation data comprises the current temperature, the current water cooling pump pressure and the current three-way valve opening degree; inputting the current operation data into the flow prediction model to obtain the current flow of the water cooling system; the flow prediction model is obtained by training a water-cooling system operation sample, the water-cooling system operation sample comprises a temperature characteristic, a water-cooling pump pressure characteristic and a three-way valve opening characteristic of the water-cooling system at the same moment, and a label value of the water-cooling system operation sample is a flow value of the water-cooling system acquired by a flow sensor at the same moment; and determining the fault type of the water cooling system based on the current flow and the current water cooling pump pressure. The fault type of the water cooling system can be quickly and accurately determined.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbine water cooling system fault monitoring, and in particular to a water cooling system fault detection method, device, equipment, storage medium and product. Background Art

[0002] In the related art, in order to consider the cost of water cooling system construction, the water cooling system of wind turbines is generally not equipped with flow sensors. As a result, when the water cooling system of the wind turbine fails, the on-site technicians lack accurate flow data and find it difficult to promptly and accurately determine the type of failure of the water cooling system and eliminate it in a targeted manner, which will affect the safe and stable operation of the water cooling system. Summary of the invention

[0003] The main purpose of this application is to provide a water cooling system fault detection method, device, equipment, storage medium and product, aiming to solve the technical problem that it is difficult to quickly and accurately determine the type of water cooling system fault during the operation of the water cooling system.

[0004] To achieve the above objectives, the present application proposes a water cooling system fault detection method, comprising:

[0005] Obtain the current operating data of the water cooling system; the current operating data includes the current temperature, the current water cooling pump pressure and the current three-way valve opening;

[0006] The current operation data is input into the flow prediction model to obtain the current flow of the water cooling system; the flow prediction model is trained by the water cooling system operation samples, the water cooling system operation samples include the temperature characteristics of the water cooling system at the same time, the water cooling pump pressure characteristics and the three-way valve opening characteristics, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time;

[0007] Based on the current flow rate and the current water cooling pump pressure, determine the fault type of the water cooling system.

[0008] In one embodiment, the step of determining the fault type of the water cooling system based on the current flow rate and the current water cooling pump pressure also includes:

[0009] Determine the pressure compensation value corresponding to the current water cooling pump pressure based on the current temperature and a preset pressure compensation mapping table; the preset pressure compensation mapping table includes a corresponding relationship between temperature and pressure compensation value;

[0010] Correct the current water cooling pump pressure based on the pressure compensation value to obtain the corrected current water cooling pump pressure;

[0011] Based on the current flow rate and the current water cooling pump pressure, the steps to determine the fault type of the water cooling system include:

[0012] Based on the current flow rate and the corrected current water cooling pump pressure, determine the fault type of the water cooling system.

[0013] In one embodiment, the step of determining the fault type of the water cooling system based on the current flow rate and the current water cooling pump pressure includes:

[0014] Obtain the flow difference between the current flow and the flow at the previous moment and the pressure difference between the current water cooling pump pressure and the water cooling pump pressure at the previous moment;

[0015] Based on the flow difference and the pressure difference, a preset fault relationship mapping table is queried to determine the fault type of the water cooling system; the preset fault relationship mapping table includes the corresponding relationship between the input parameter combination and the water cooling system fault type; the input parameter combination includes the flow difference and the pressure difference.

[0016] In one embodiment, the step of querying a preset fault relationship mapping table based on the flow difference and the pressure difference to determine the fault type of the water cooling system includes:

[0017] When the pressure difference is greater than or equal to the first preset pressure difference and the flow difference is greater than or equal to the first preset flow difference, determining that the fault type of the water cooling system is a three-way valve fault;

[0018] When the pressure difference is greater than or equal to a first preset pressure difference and the flow difference is less than or equal to a second preset flow difference, determining that the fault type of the water cooling system is a blockage and / or a three-way valve fault;

[0019] When the pressure difference is less than or equal to the second preset pressure difference and the flow difference is less than or equal to the second preset flow difference, determining that the fault type of the water cooling system is a leakage fault;

[0020] When the pressure difference is less than or equal to the second preset pressure difference and the flow difference is greater than or equal to the first preset flow difference, determining that the fault type of the water cooling system is a leakage fault;

[0021] When the pressure difference is greater than or equal to the first preset pressure difference, and the flow difference is less than the first preset flow difference and greater than the second preset flow difference, determining that the fault type of the water cooling system is a sensor fault;

[0022] When the pressure difference is less than or equal to the second preset pressure difference, and the flow difference is less than the first preset flow difference and greater than the second preset flow difference, determining that the fault type of the water cooling system is a sensor fault;

[0023] Among them, the relationship between the first preset pressure difference and the second preset pressure difference is: the first preset pressure difference ≥ 0 ≥ the second preset pressure difference; the relationship between the first preset flow difference and the second preset flow difference is: the first preset flow difference ≥ 0 ≥ the second preset flow difference.

[0024] In one embodiment, before the step of inputting the current operation data into the flow prediction model to obtain the current flow of the water cooling system, the step further includes:

[0025] Obtain sample operation data of the initial model and the water cooling system; the sample operation data includes temperature, water cooling pump pressure, three-way valve opening, and water cooling system flow;

[0026] Normalize the sample running data based on formula 1 to obtain a training sample set;

[0027] Train the initial model based on the training sample set to obtain a traffic prediction model;

[0028] Among them, formula 1 is: θ i represents the i-th sample running data, θ min is the minimum value of the sample running data, θ max is the maximum value of the sample running data, Run the data for the normalized samples.

[0029] In one embodiment, the initial model includes an extreme learning machine model.

[0030] In addition, to achieve the above purpose, the present application also proposes a water cooling system fault detection device, the water cooling system fault detection device comprising:

[0031] A data acquisition module is used to acquire the current operating data of the water cooling system; the current operating data includes the current temperature, the current water cooling pump pressure and the current three-way valve opening;

[0032] The flow prediction module is used to input the current operation data into the flow prediction model to obtain the current flow of the water cooling system; the flow prediction model is obtained by training the water cooling system operation samples, the water cooling system operation samples include the temperature characteristics of the water cooling system at the same time, the water cooling pump pressure characteristics and the three-way valve opening characteristics, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time;

[0033] The fault determination module is used to determine the fault type of the water cooling system based on the current flow rate and the current water cooling pump pressure.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a water cooling system fault detection device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the water cooling system fault detection method as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the water cooling system fault detection method as described above are implemented.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the water cooling system fault detection method as described above are implemented.

[0037] One or more technical solutions proposed in this application have at least the following technical effects:

[0038] The water cooling system fault detection method provided by the present application obtains a flow prediction model through water cooling system operation sample training, wherein the water cooling system operation sample includes the temperature characteristics of the water cooling system at the same time, the water cooling pump pressure characteristics and the three-way valve opening characteristics, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time. Therefore, for a water cooling system without a flow sensor installed, its current flow value can also be predicted through the current operation data such as the current temperature of the water cooling system, the current water cooling pump pressure and the current three-way valve opening, and then a comprehensive fault analysis is performed based on the current flow and the current water cooling pump pressure to determine the fault type of the water cooling system, thereby helping technicians to quickly locate the fault, so as to carry out targeted maintenance on the water cooling system, and ensure the safe and stable operation of the water cooling system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the water cooling system fault detection method of the present application;

[0042] Figure 2This is a schematic diagram of the structure of a wind turbine water cooling system;

[0043] Figure 3 A flow chart of a traffic prediction model training process for an example;

[0044] Figure 4 A brief flowchart of a water cooling system fault detection method provided in Example 1 of the present application;

[0045] Figure 5 This is a schematic diagram of the module structure of the water cooling system fault detection device according to an embodiment of the present application;

[0046] Figure 6 Schematic diagram of the equipment structure of the hardware operating environment involved in the water cooling system fault detection method in the embodiment of the present application.

[0047] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0048] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0049] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0050] The main solution of the embodiment of the present application is: obtaining the current operating data of the water cooling system; the current operating data includes the current temperature, the current water cooling pump pressure and the current three-way valve opening; inputting the current operating data into the flow prediction model to obtain the current flow of the water cooling system; the flow prediction model is obtained by training the water cooling system operation samples, and the water cooling system operation samples include the temperature characteristics, water cooling pump pressure characteristics and three-way valve opening characteristics of the water cooling system at the same time, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time; based on the current flow and the current water cooling pump pressure, determine the fault type of the water cooling system.

[0051] In the related technologies, the water cooling system of wind turbines is generally not equipped with flow sensors in order to consider the construction cost of the water cooling system. As a result, when the wind turbine water cooling system fails, the on-site technicians lack accurate flow data and comprehensive data support, making it difficult to promptly and accurately determine the type of water cooling system failure and eliminate it in a targeted manner, which will affect the safe and stable operation of the water cooling system.

[0052] The present application provides a solution. For a water cooling system that does not have a flow sensor installed, current operating data such as the current temperature of the water cooling system, the current water cooling pump pressure, and the current three-way valve opening can be input into a flow prediction model to predict the current flow of the water cooling system more accurately. Therefore, a comprehensive fault analysis can be performed based on the current flow and the current water cooling pump pressure to determine the fault type of the water cooling system, thereby helping technicians to quickly locate the fault category, so as to perform targeted maintenance on the water cooling system and ensure the safe and stable operation of the water cooling system.

[0053] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, etc., or an electronic device capable of realizing the above functions, etc. The following takes the water cooling system fault detection device as an example to illustrate this embodiment and the following embodiments.

[0054] Based on this, the present application embodiment provides a water cooling system fault detection method, referring to Figure 1 , Figure 1 This is a flow chart of Example 1 of the water cooling system fault detection method of the present application.

[0055] In this embodiment, the water cooling system fault detection method may include steps S100 to S300:

[0056] Step S100, obtaining current operation data of the water cooling system.

[0057] The current operating data includes the current temperature, the current water cooling pump pressure and the current three-way valve opening.

[0058] Step S200, inputting the current operating data into the flow prediction model to obtain the current flow of the water cooling system.

[0059] Among them, the flow prediction model is trained through water cooling system operation samples. The water cooling system operation samples include the temperature characteristics of the water cooling system at the same time, the water cooling pump pressure characteristics and the three-way valve opening characteristics, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time.

[0060] Step S300, determining the fault type of the water cooling system based on the current flow rate and the current water cooling pump pressure.

[0061] Specifically, the water cooling system of a wind turbine generally includes a three-way valve, a water cooling pump, an external radiator, and a heat exchange device; Figure 2 As shown, Figure 2 A schematic diagram of the structure of a wind turbine water cooling system is shown; Figure 2In the water cooling system of wind turbines, the heat exchange equipment is a heat exchanger. The water cooling pump can push the cooling water to circulate in the water cooling system. The cooling water is pressurized and transported to the heat exchanger. The heat exchange between the cooling water and the cooled device can be achieved through the heat exchanger to reduce the temperature of the cooled device. In the water cooling system of wind turbines, sensors can be used to collect the current operation data of the water cooling system.

[0062] The current operating data may include but is not limited to the current temperature of the water cooling system, the current water cooling pump pressure and the current three-way valve opening; the current temperature may be the current ambient temperature of the water cooling system measured by a thermometer, or in order to obtain more accurate temperature data, a temperature sensor or thermometer may be installed at a key position of the water cooling system, such as the water outlet or the water return port, to read a more accurate current temperature of the water cooling system. The current water cooling pump pressure may be measured by a pressure sensor, such as Figure 2 As shown, pressure sensors are respectively provided at the inlet and outlet of the water cooling pump. The pressure values ​​at both ends of the water cooling pump can be monitored in real time through the pressure sensors. The current water cooling pump pressure of the water cooling system can be obtained by calculating the difference between the outlet pressure and the inlet pressure of the water cooling pump. The current three-way valve opening can be monitored by a displacement sensor or a potentiometer installed on the three-way valve.

[0063] The current operating data of the water cooling system is then input into the preset flow prediction model. The flow prediction model can predict the flow based on the current temperature, the current water cooling pump pressure, the current three-way valve opening and other data, and output the estimated current flow of the water cooling system. It can be understood that the preset flow prediction model can be regarded as a virtual sensor. The virtual sensor receives and processes the current operating data of the water cooling system to obtain the corresponding current flow. Compared with the use of physical flow sensors, its cost is lower.

[0064] The above flow prediction model is obtained by training the water cooling system operation samples. The water cooling system operation samples may include the temperature characteristics, water cooling pump pressure characteristics and three-way valve opening characteristics of the water cooling system at the same time. The label value (output value) of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time; the temperature characteristic may be the ambient temperature value or the temperature value of the key position of the water cooling system measured at the ambient temperature, the water cooling pump pressure characteristic may be the water cooling pump pressure value, and the three-way valve opening characteristic is the three-way valve opening value. It should be noted that, based on the structural cost of the water cooling system, a physical flow sensor is generally not set in the water cooling system, so the flow prediction model can be obtained by machine learning model training as a virtual flow sensor to detect the current flow of the water cooling system; however, in order to train the flow prediction model to better predict the flow of the water cooling system, in the model training stage, a flow sensor can be installed in the water cooling system first, and the flow value of the water cooling system corresponding to the temperature characteristics, water cooling pump pressure characteristics and three-way valve opening characteristics at each time can be collected to obtain a comprehensive and accurate water cooling system operation sample for model training. After the model training is completed, the flow prediction model obtained can be widely used in water cooling systems without physical flow sensors, replacing physical flow sensors in the form of virtual sensors, reducing the construction cost of the water cooling system. In a feasible implementation, steps A100 to A300 may be included before step S200 to obtain the flow prediction model:

[0065] Step A100, obtaining the initial model and sample operation data of the water cooling system.

[0066] Among them, the sample operation data includes temperature, water cooling pump pressure, three-way valve opening and water cooling system flow.

[0067] Step A200, normalize the sample running data based on formula 1 to obtain a training sample set.

[0068] Step A300: Train the initial model based on the training sample set to obtain a traffic prediction model.

[0069] Among them, formula 1 is: θ i represents the i-th sample running data, θ min is the minimum value of the sample running data, θ max is the maximum value of the sample running data, Run the data for the normalized samples.

[0070] Specifically, a neural network model can be selected as the initial model for model training; the initial model can be a linear regression model, a support vector regression model, or as a feasible implementation method, the initial model can also be an extreme learning machine model. The hidden layer parameters (such as weights and biases) of the extreme learning machine model are randomly generated. During the training process, only the weights of the output layer need to be trained, so the model training time can be significantly reduced; and the randomly generated hidden layer parameters have a certain degree of randomness during the training process, so that the model is not easy to overfit when facing noisy data, and the trained model has better robustness. Compared with other neural network models, the overall performance of the extreme learning machine model is better, so it is preferred that the extreme learning machine model can be used as the initial model to carry out model training. Then collect sample operation data of the water cooling system, wherein the sample operation data may include data such as temperature, water cooling pump pressure, three-way valve opening, and flow rate of the water cooling system. For example, in one example, 7 temperature points T can be taken in a temperature range of 20°C to 70°C with a step size of 10°C. m (m∈[1,7]), for each temperature point, under the ambient pressure condition of 0 to 50 bar, 5 pressure points P are taken with a step size of 10 bar. j (j∈[1,5]), and then for each combination of pressure point and temperature point, under the condition of 0~100% three-way valve opening, take 20 three-way valve opening points X with a step size of 5%. k (k∈[1,20]); then the flow sensor is used to measure the flow rate Q of the water cooling system at various temperature points, pressure points and three-way valve opening points. mjk , so that multiple sets of sample operation data (T m , P j , X k , Q mjk ).

[0071] In order to eliminate the dimensional influence between different types of sample operation data, formula 1 can be used to normalize each sample operation data and adjust the sample operation data to the standard range. All normalized sample operation data can constitute a training sample set. During model training, the training sample set can be divided into a training set and a validation set (or test set). The training set is used for model training, and the validation set can be used to verify the model training results and optimize the model. In this way, the initial model can be trained based on the training sample set to obtain the final traffic prediction model.

[0072] like Figure 3 As shown, Figure 3The figure is a flow prediction model training process diagram for an example. After the aforementioned data processing is performed on the sample operation data such as the pressure signal time series, the temperature signal time series, the three-way valve opening time series and the flow signal time series, the data is input into the extreme learning machine model for model training to obtain the flow prediction model. Subsequently, the flow prediction model can be used to estimate the flow in a water cooling system without a physical flow sensor, thereby comprehensively determining the fault type of the water cooling system based on the estimated current flow of the water cooling system and the current water cooling pump pressure.

[0073] Specifically, the current flow rate and the current water pump pressure can be compared with standard data to analyze and determine the fault type of the water cooling system. The standard data can be obtained by consulting the technical documents of the water cooling pump and the cooling system to obtain the flow rate and pressure range during normal operation, and then comparing the current flow rate and the current water pump pressure with the standard data to determine the parameters with large deviations, and determine the fault type accordingly. For example, when the current water cooling pump pressure is too high, it is because the water cooling pump is overloaded, or there is a blockage in the pipeline, which increases the pressure on the water cooling pump. Or as a feasible implementation method, step S300 can specifically include steps S310 to S320:

[0074] Step S310, obtaining the flow difference between the current flow and the flow at the previous moment and the pressure difference between the current water cooling pump pressure and the water cooling pump pressure at the previous moment.

[0075] Step S320, querying a preset fault relationship mapping table based on the flow difference and the pressure difference to determine the fault type of the water cooling system.

[0076] The preset fault relationship mapping table includes the corresponding relationship between the input parameter combination and the water cooling system fault type, and the input parameter combination includes the flow difference and the pressure difference.

[0077] Specifically, the water cooling system flow and water cooling pump pressure at the previous moment of the current operation can be obtained, and then the flow difference between the current flow and the flow at the previous moment, as well as the pressure difference between the current water cooling pump pressure and the water cooling pump pressure at the previous moment can be calculated; thus, the preset fault relationship mapping table can be queried according to the calculated pressure difference and flow difference to determine the current fault type of the water cooling system. The preset fault relationship mapping table records the correspondence between the flow difference and the pressure difference and the water cooling system fault type. By querying the fault relationship mapping table, the flow difference and the pressure difference can be matched with the relationship in the table to more accurately determine the fault type of the water cooling system. In a feasible implementation, the above step S320 can specifically include steps S321 to S326:

[0078] Step S321: When the pressure difference is greater than or equal to the first preset pressure difference and the flow difference is greater than or equal to the first preset flow difference, determine that the fault type of the water cooling system is a three-way valve fault.

[0079] Step S322: When the pressure difference is greater than or equal to the first preset pressure difference and the flow difference is less than or equal to the second preset flow difference, determine that the fault type of the water cooling system is blockage and / or three-way valve failure.

[0080] Step S323: When the pressure difference is less than or equal to the second preset pressure difference and the flow difference is less than or equal to the second preset flow difference, determine that the fault type of the water cooling system is a leakage fault.

[0081] Step S324: When the pressure difference is less than or equal to the second preset pressure difference and the flow difference is greater than or equal to the first preset flow difference, determine that the fault type of the water cooling system is a leakage fault.

[0082] Step S325: When the pressure difference is greater than or equal to the first preset pressure difference, and the flow difference is less than the first preset flow difference and greater than the second preset flow difference, determine that the fault type of the water cooling system is a sensor fault.

[0083] Step S326: When the pressure difference is less than or equal to the second preset pressure difference, and the flow difference is less than the first preset flow difference and greater than the second preset flow difference, determine that the fault type of the water cooling system is a sensor fault.

[0084] Among them, the relationship between the first preset pressure difference and the second preset pressure difference is: the first preset pressure difference ≥ 0 ≥ the second preset pressure difference; the relationship between the first preset flow difference and the second preset flow difference is: the first preset flow difference ≥ 0 ≥ the second preset flow difference.

[0085] Specifically, the pressure difference = current water cooling pump pressure - water cooling pump pressure at the previous moment; the flow difference = current flow - flow at the previous moment; when the pressure difference is greater than or equal to the first preset pressure difference and the flow difference is greater than or equal to the first preset flow difference, it can be determined that the fault type of the water cooling system is a three-way valve failure. It can be understood that the above situation means that the current flow and the current water cooling pump pressure both increase suddenly compared to the previous moment. This phenomenon indicates that the three-way valve fails to correctly regulate the flow of cooling water in the system, and therefore the corresponding fault type is a three-way valve failure.

[0086] When the pressure difference is greater than or equal to the first preset pressure difference and the flow difference is less than or equal to the second preset flow difference, it indicates that the current flow rate has suddenly decreased, while the current water cooling pump pressure has suddenly increased. In the actual operation of the system, blockage usually causes a decrease in flow and an increase in pressure. A three-way valve failure may cause abnormal flow and pressure changes. In particular, improper adjustment of the three-way valve may cause a decrease in flow and may cause a local pressure increase. Therefore, when the pressure difference is greater than or equal to the first preset pressure difference and the flow difference is less than or equal to the second preset flow difference, the corresponding water cooling system fault type is blockage and / or three-way valve failure.

[0087] When the pressure difference is less than or equal to the second preset pressure difference and the flow difference is less than or equal to the second preset flow difference, it indicates that both the current flow and the current water cooling pump pressure suddenly decrease. When there is a leak in the water cooling system, the water cooling pump pressure difference and the system flow difference usually decrease at the same time; when the pressure difference is less than or equal to the second preset pressure difference and the flow difference is greater than or equal to the first preset flow difference, it indicates that the current flow suddenly increases and the current water cooling pump pressure suddenly decreases; a leak in the water cooling system will cause a sudden drop in the water cooling pump pressure, and when leaking, fluid loss will cause a decrease in the actual flow; but if the leak occurs at the water inlet or outlet of the system, it may cause the fluid to directly lose from the pump outlet, causing the actual flow to increase; therefore, when the current water cooling pump pressure suddenly decreases and the current flow suddenly increases or decreases, it can be determined that the fault type of the water cooling system is a leak.

[0088] When the pressure difference is greater than or equal to the first preset pressure difference, and the flow difference is less than the first preset flow difference and greater than the second preset flow difference, it indicates that the current flow of the water cooling system is within the normal fluctuation range, and the current flow can be regarded as unchanged compared with the flow at the previous moment, while the current water cooling pump pressure shows a sudden increase; when the pressure difference is less than or equal to the second preset pressure difference, and the flow difference is less than the first preset flow difference and greater than the second preset flow difference, it indicates that the current flow of the water cooling system is within the normal fluctuation range, and the current water cooling pump pressure shows a sudden increase. In both cases, the current flow of the water cooling system is within the normal fluctuation range, indicating that the water cooling system is operating normally, and the current water cooling pump pressure has abnormal fluctuations of sudden increase or decrease, indicating that it may be due to a fault in the pressure sensor in the water cooling system, which affects the accurate measurement of the water cooling pump pressure. Therefore, the fault type of the water cooling system at this time is a sensor fault.

[0089] In addition, since the sensitivity of the pressure sensor will change with the temperature in actual applications, in order to ensure that the fault type of the water cooling system can be determined more accurately using the current water cooling pump pressure and the current flow rate, steps B100 to B200 may be included before step S300 to compensate and correct the measured current water cooling pump pressure:

[0090] Step B100, determining a pressure compensation value corresponding to the current water cooling pump pressure based on the current temperature and a preset pressure compensation mapping table.

[0091] The preset pressure compensation mapping table includes the corresponding relationship between temperature and pressure compensation value.

[0092] Step B200, correcting the current water cooling pump pressure based on the pressure compensation value to obtain the corrected current water cooling pump pressure.

[0093] Specifically, the preset pressure compensation mapping table includes the correspondence between temperature and pressure compensation value. For example, there is a preset pressure compensation value corresponding to the temperature range of 20-40℃. Within the temperature range of 20-40℃, for every 5℃ increase in temperature, the corresponding current water cooling pump pressure increases by a pressure compensation value. The preset pressure compensation value can be set according to empirical data or industry standards in long-term operation. The corresponding pressure compensation value can be determined by querying the preset pressure compensation mapping table according to the current temperature of the water cooling system; thus, the current water cooling pump pressure measured by the pressure sensor can be corrected according to the pressure compensation value to obtain the corrected current water cooling pump pressure to eliminate the influence of temperature on the pressure sensor. At this time, the fault type of the water cooling system can be determined based on the current flow rate and the corrected current water cooling pump pressure, so that the operator can perform targeted abnormal processing. The specific implementation can refer to the above content and will not be repeated here.

[0094] It can be understood that in the water cooling system fault detection method provided in the present embodiment, a flow prediction model can be obtained by training the water cooling system operation samples, wherein the water cooling system operation samples include the temperature characteristics of the water cooling system at the same time, the water cooling pump pressure characteristics and the three-way valve opening characteristics, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time. Therefore, for a water cooling system without an installed physical flow sensor, a more accurate current flow value of the water cooling system can be obtained by predicting the current operation data such as the measured current temperature of the water cooling system, the current water cooling pump pressure and the current three-way valve opening, and then a comprehensive fault analysis is performed based on the current flow value and the current water cooling pump pressure to determine the fault type of the water cooling system, thereby helping technicians to quickly locate the fault, so as to carry out targeted maintenance of the water cooling system, and ensure the safe and stable operation of the water cooling system.

[0095] For example, to help understand the implementation process of the water cooling system fault detection method in the first embodiment of the present application, please refer to Figure 4 , Figure 4 A brief flow chart of an exemplary water cooling system fault detection method is provided, specifically:

[0096] like Figure 4 As shown, the virtual flow sensor (i.e., the flow prediction model) can obtain the current temperature of the water cooling system, the current three-way valve opening, and the current water cooling pump pressure collected by the pressure sensor. Based on the above data, the current flow of the water cooling system can be predicted. At the same time, the pressure compensation system can also obtain the current temperature, and determine the pressure compensation value of the pressure sensor at the current temperature based on the current temperature and the preset pressure compensation mapping table, so as to compensate and correct the current water cooling pump pressure and obtain the corrected current water cooling pump pressure. Based on the current flow, the corrected current water cooling pump pressure and the fault warning strategy, the fault type of the water cooling system can be warned and output. The fault warning strategy can be a preset fault mapping table as shown in Table 1.

[0097] Table 1

[0098] Failure level Current water cooling pump pressure Current traffic Fault type high Surge Surge Three-way valve failure high Surge Sudden reduction Blockage / three-way valve failure middle Sudden reduction Sudden reduction leakage middle Sudden reduction Surge leakage Low Surge constant Sensor failure Low Sudden reduction constant Sensor failure

[0099] According to the change in the current water cooling pump pressure and current flow rate compared with the relevant data at the previous moment, the preset fault mapping table shown in Table 1 can be queried to determine the fault type and corresponding fault level of the water cooling system. Therefore, the technicians can perform targeted maintenance according to the specific fault type in the table to ensure the stability and safety of the operation of the water cooling system.

[0100] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the water cooling system fault detection method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0101] This application also provides a water cooling system fault detection device, please refer to Figure 5 , the water cooling system fault detection device comprises:

[0102] The data acquisition module 10 is used to acquire the current operation data of the water cooling system; the current operation data includes the current temperature, the current water cooling pump pressure and the current three-way valve opening;

[0103] The flow prediction module 20 is used to input the current operation data into the flow prediction model to obtain the current flow of the water cooling system; the flow prediction model is obtained by training the water cooling system operation samples, the water cooling system operation samples include the temperature characteristics of the water cooling system at the same time, the water cooling pump pressure characteristics and the three-way valve opening characteristics, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time;

[0104] The fault determination module 30 is used to determine the fault type of the water cooling system based on the current flow rate and the current water cooling pump pressure.

[0105] The water cooling system fault detection device provided by the present application adopts the water cooling system fault detection method in the above embodiment, which can solve the technical problem that it is difficult to quickly and accurately determine the type of water cooling system fault during the operation of the water cooling system. Compared with the relevant technology, the beneficial effects of the water cooling system fault detection device provided by the present application are the same as the beneficial effects of the water cooling system fault detection method provided by the above embodiment, and the other technical features in the above water cooling system fault detection device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0106] The present application provides a water cooling system fault detection device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the water cooling system fault detection method in the above-mentioned embodiment one.

[0107] Reference below Figure 6 , which shows a schematic diagram of the structure of a water cooling system fault detection device suitable for implementing the embodiment of the present application. The water cooling system fault detection device in the embodiment of the present application may include but is not limited to mobile terminals such as laptop computers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), etc., and fixed terminals such as desktop computers, etc. Figure 6 The water cooling system fault detection device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0108] like Figure 6As shown, the water cooling system fault detection device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the water cooling system fault detection device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the water cooling system fault detection device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a water cooling system fault detection device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0109] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0110] The water cooling system fault detection device provided by the present application adopts the water cooling system fault detection method in the above embodiment, which can solve the technical problem that it is difficult to quickly and accurately determine the type of water cooling system fault during the operation of the water cooling system. Compared with the relevant technology, the beneficial effects of the water cooling system fault detection device provided by the present application are the same as the beneficial effects of the water cooling system fault detection method provided by the above embodiment, and the other technical features in the water cooling system fault detection device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0111] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0112] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0113] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the water cooling system fault detection method in the above-mentioned embodiment.

[0114] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0115] The computer-readable storage medium may be included in the water cooling system fault detection device; or may exist independently without being assembled into the water cooling system fault detection device.

[0116] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the water cooling system fault detection device, the water cooling system fault detection device: obtains the current operating data of the water cooling system; the current operating data includes the current temperature, the current water cooling pump pressure and the current three-way valve opening; inputs the current operating data into the flow prediction model to obtain the current flow of the water cooling system; the flow prediction model is obtained by training the water cooling system operation samples, the water cooling system operation samples include the temperature characteristics, water cooling pump pressure characteristics and three-way valve opening characteristics of the water cooling system at the same time, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time; based on the current flow and the current water cooling pump pressure, the fault type of the water cooling system is determined.

[0117] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0118] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0119] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0120] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned water cooling system fault detection method, and can solve the technical problem that it is difficult to quickly and accurately determine the type of water cooling system fault during the operation of the water cooling system. Compared with the related art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the water cooling system fault detection method provided by the above-mentioned embodiment, and will not be repeated here.

[0121] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned water cooling system fault detection method when executed by a processor.

[0122] The computer program product provided by the present application can solve the technical problem that it is difficult to quickly and accurately determine the type of water cooling system fault during the operation of the water cooling system. Compared with the related art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the water cooling system fault detection method provided by the above embodiment, and will not be repeated here.

[0123] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A water cooling system fault detection method, characterized in that: The water cooling system fault detection method comprises: Acquire current operating data of the water cooling system; the current operating data includes current temperature, current water cooling pump pressure and current three-way valve opening; The current operation data is input into a flow prediction model to obtain the current flow of the water cooling system; the flow prediction model is obtained by training water cooling system operation samples, the water cooling system operation samples include the temperature characteristics of the water cooling system at the same time, the water cooling pump pressure characteristics and the three-way valve opening characteristics, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time; Based on the current flow rate and the current water cooling pump pressure, a fault type of the water cooling system is determined.

2. The water cooling system fault detection method according to claim 1, characterized in that: The step of determining the fault type of the water cooling system based on the current flow rate and the current water cooling pump pressure also includes: Determine the pressure compensation value corresponding to the current water cooling pump pressure based on the current temperature and a preset pressure compensation mapping table; the preset pressure compensation mapping table includes a corresponding relationship between temperature and pressure compensation value; Correcting the current water cooling pump pressure based on the pressure compensation value to obtain the corrected current water cooling pump pressure; The step of determining the fault type of the water cooling system based on the current flow rate and the current water cooling pump pressure comprises: Based on the current flow rate and the corrected current water cooling pump pressure, a fault type of the water cooling system is determined.

3. The water cooling system fault detection method according to claim 1, characterized in that: The step of determining the fault type of the water cooling system based on the current flow rate and the current water cooling pump pressure comprises: Obtaining a flow difference between the current flow and the flow at a previous moment and a pressure difference between the current water cooling pump pressure and the water cooling pump pressure at a previous moment; Based on the flow difference and the pressure difference, a preset fault relationship mapping table is queried to determine the fault type of the water cooling system; the preset fault relationship mapping table includes a corresponding relationship between an input parameter combination and a water cooling system fault type; the input parameter combination includes a flow difference and a pressure difference.

4. The water cooling system fault detection method according to claim 3, characterized in that: The step of querying a preset fault relationship mapping table based on the flow difference and the pressure difference to determine the fault type of the water cooling system comprises: When the pressure difference is greater than or equal to a first preset pressure difference and the flow difference is greater than or equal to a first preset flow difference, determining that the fault type of the water cooling system is a three-way valve fault; When the pressure difference is greater than or equal to a first preset pressure difference and the flow difference is less than or equal to a second preset flow difference, determining that the fault type of the water cooling system is a blockage and / or a three-way valve fault; When the pressure difference is less than or equal to a second preset pressure difference and the flow difference is less than or equal to a second preset flow difference, determining that the fault type of the water cooling system is a leakage fault; When the pressure difference is less than or equal to a second preset pressure difference and the flow difference is greater than or equal to a first preset flow difference, determining that the fault type of the water cooling system is a leakage fault; When the pressure difference is greater than or equal to a first preset pressure difference, and the flow difference is less than the first preset flow difference and greater than a second preset flow difference, determining that the fault type of the water cooling system is a sensor fault; When the pressure difference is less than or equal to the second preset pressure difference, and the flow difference is less than the first preset flow difference and greater than the second preset flow difference, determining that the fault type of the water cooling system is a sensor fault; Among them, the relationship between the first preset pressure difference and the second preset pressure difference is: first preset pressure difference ≥ 0 ≥ second preset pressure difference; the relationship between the first preset flow difference and the second preset flow difference is: first preset flow difference ≥ 0 ≥ second preset flow difference.

5. The water cooling system fault detection method according to claim 1, characterized in that: Before the step of inputting the current operation data into the flow prediction model to obtain the current flow of the water cooling system, the step further includes: Obtaining sample operation data of the initial model and the water cooling system; the sample operation data includes temperature, water cooling pump pressure, three-way valve opening, and water cooling system flow; Normalizing the sample operation data based on formula 1 to obtain a training sample set; Training the initial model based on the training sample set to obtain the traffic prediction model; Among them, formula 1 is: θ i represents the i-th sample running data, θ min is the minimum value of the sample running data, θ max is the maximum value of the sample running data, Run the data for the normalized samples.

6. The water cooling system fault detection method according to claim 5, characterized in that: The initial model includes an extreme learning machine model.

7. A water cooling system fault detection device, characterized in that: The water cooling system fault detection device comprises: A data acquisition module, used to acquire current operating data of the water cooling system; the current operating data includes current temperature, current water cooling pump pressure and current three-way valve opening; A flow prediction module is used to input the current operation data into a flow prediction model to obtain the current flow of the water cooling system; the flow prediction model is obtained by training the water cooling system operation samples, the water cooling system operation samples include the temperature characteristics of the water cooling system at the same time, the water cooling pump pressure characteristics and the three-way valve opening characteristics, and the label value of the water cooling system operation sample is the flow value of the water cooling system collected by the flow sensor at the same time; A fault determination module is used to determine the fault type of the water cooling system based on the current flow rate and the current water cooling pump pressure.

8. A water cooling system fault detection device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the water cooling system fault detection method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the water cooling system fault detection method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the water cooling system fault detection method according to any one of claims 1 to 6 are implemented.

Images