Method and device for determining a cause of a cooling system failure, and medium

Abstract

The application discloses a cooling system fault cause determination method and device and medium, and belongs to the technical field of wind power generation. According to the actual temperature of the cooling object in a preset time period and the reference temperature of the cooling object corresponding to the fan in different operating states, the actual operating state of the fan in the preset time period is determined, the accurate division of the operating state of the fan is realized, and on this basis, the actual temperature fluctuation data of the cabin temperature in the actual operating state is determined according to the cabin temperature of the cabin in the preset time period, the quantitative heat dissipation effect of the cooling system is realized, and according to the quantitative heat dissipation effect, that is, the actual temperature fluctuation data, the fault cause of the cooling system can be positioned more accurately.

Description

Technical Field

[0001] This application relates to the field of wind power generation technology, and in particular to a method, apparatus and medium for determining the cause of cooling system failure. Background Technology

[0002] Cooling systems are a crucial component of wind turbine generators. For example, generator cooling systems dissipate the significant heat generated during generator operation, ensuring stable operation. Similarly, gearbox cooling systems cool the gearbox, ensuring stable operation. A malfunction in the cooling system can easily lead to overheating and generator shutdown, and may even damage components such as the generator and gearbox. Therefore, fault diagnosis of the wind turbine generator's cooling system and determination of the cause of the malfunction are of paramount importance for the safe operation of the generator set.

[0003] The current diagnostic methods cannot accurately determine the cause of a cooling system malfunction. Summary of the Invention

[0004] This application provides a method, apparatus, and medium for determining the cause of a cooling system failure, which can accurately locate the cause of the failure when the cooling system of a wind turbine generator fails.

[0005] In a first aspect, embodiments of this application provide a method for determining the cause of a cooling system failure, including:

[0006] Obtain the operating data of the wind turbine generator set within a preset time period. The operating data includes at least the nacelle temperature and the actual temperature of the object being cooled. The object being cooled is the object in the wind turbine generator set that is cooled by the cooling system.

[0007] Based on the actual temperature of the object being cooled within a preset time period, and the reference temperature of the object being cooled corresponding to the fan of the cooling system under different operating states, the actual operating state of the fan within the preset time period is determined.

[0008] Based on the cabin temperature within a preset time period, determine the actual temperature fluctuation data of the cabin under actual operating conditions;

[0009] Based on actual temperature fluctuation data, determine the cause of the cooling system failure.

[0010] Secondly, embodiments of this application provide a device for determining the cause of a cooling system failure, comprising:

[0011] The acquisition module is used to acquire the operating data of the wind turbine generator set within a preset time period. The operating data includes at least the nacelle temperature and the actual temperature of the object being cooled. The object being cooled is the object in the wind turbine generator set cooled by the cooling system.

[0012] The determination module is used to determine the actual operating state of the fan within a preset time period based on the actual temperature of the object being cooled within a preset time period and the reference temperature of the object being cooled corresponding to the fan of the cooling system under different operating states; to determine the actual temperature fluctuation data of the engine compartment temperature under the actual operating state based on the engine compartment temperature within the preset time period; and to determine the cause of the cooling system failure based on the actual temperature fluctuation data.

[0013] Thirdly, embodiments of this application provide a device for determining the cause of a cooling system failure, comprising:

[0014] processor;

[0015] Memory is used to store computer program instructions;

[0016] When computer program instructions are executed by the processor, the method described in the first aspect is implemented.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the method described in the first aspect.

[0018] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0019] This application embodiment determines the actual operating state of the fan within a preset time period based on the actual temperature of the object being cooled and the reference temperature of the object being cooled corresponding to different operating states of the fan, thus achieving accurate division of the fan's operating state. On this basis, based on the cabin temperature within the preset time period, the actual temperature fluctuation data of the cabin temperature under the actual operating state is determined, thereby quantifying the heat dissipation effect of the cooling system. Based on the quantified heat dissipation effect, i.e., the actual temperature fluctuation data, the cause of cooling system failure can be located more accurately. Attached Figure Description

[0020] The features, advantages, and technical effects of exemplary embodiments of this application will now be described with reference to the accompanying drawings.

[0021] Figure 1 A flowchart illustrating a method for determining the cause of a cooling system failure, provided in an embodiment of this application;

[0022] Figure 2 A flowchart for determining a reference temperature of a cooling object is provided in an embodiment of this application;

[0023] Figure 3 A schematic diagram of the probability density curve of a generator winding provided in an embodiment of this application;

[0024] Figure 4 A flowchart illustrating another method for determining the cause of a cooling system failure, provided in an embodiment of this application;

[0025] Figure 5 A flowchart for determining the target operating state of a fan is provided in an embodiment of this application;

[0026] Figure 6 A schematic diagram illustrating the temperature change of a generator winding over time, provided as an embodiment of this application;

[0027] Figure 7 A flowchart illustrating another method for determining the cause of a cooling system failure, provided in an embodiment of this application;

[0028] Figure 8 A flowchart illustrating another method for determining the cause of a cooling system failure, provided in an embodiment of this application;

[0029] Figure 9 A schematic diagram illustrating the heat dissipation effect provided in an embodiment of this application;

[0030] Figure 10 A schematic diagram illustrating the trend of temperature difference z when a fan is running at high speed, as provided in an embodiment of this application.

[0031] Figure 11 A flowchart illustrating another method for determining the cause of a cooling system failure, provided in an embodiment of this application;

[0032] Figure 12 A schematic diagram illustrating a generator overheating and shutdown caused by the fan not switching to high speed, as provided in an embodiment of this application.

[0033] Figure 13 A structural diagram of a device for determining the cause of a cooling system failure provided in an embodiment of this application;

[0034] Figure 14 This is a structural diagram of a device for determining the cause of a cooling system failure, provided in an embodiment of this application.

[0035] In the accompanying drawings, the same parts use the same reference numerals. The drawings are not drawn to scale. Detailed Implementation

[0036] The features and exemplary embodiments of various aspects of this application will now be described in detail. Numerous specific details are set forth in the following detailed description to provide a comprehensive understanding of this application. However, it will be apparent to those skilled in the art that this application can be implemented without requiring some of these specific details. The following description of embodiments is merely intended to provide a better understanding of this application by illustrating examples. In the accompanying drawings and the following description, at least some well-known structures and techniques are not shown to avoid unnecessarily obscuring the application; and, for clarity, the dimensions of some structures may be exaggerated. Furthermore, the features, structures, or characteristics described below can be combined in any suitable manner in one or more embodiments.

[0037] The directional terms used in the following description refer to the directions shown in the figures and are not intended to limit the specific structure of the cable-stayed tower and wind turbine generator set of this application. It should also be noted in the description of this application that, unless otherwise explicitly specified and limited, the terms "installation" and "connection" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to direct connections or indirect connections. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0038] When diagnosing the cooling system of a fan, related technologies typically use simple threshold judgment methods or machine learning or deep learning methods to identify units with significantly excessive errors. However, these methods are difficult to accurately pinpoint the cause of the fault, which is detrimental to the stable operation of the unit.

[0039] Therefore, this application provides a method, apparatus, and medium for determining the cause of a cooling system failure, which can accurately locate the cause of the failure when the cooling system of a wind turbine generator fails.

[0040] This application uses a direct air-cooled wind turbine generator set as an example. The cooling system utilizes suction to create negative pressure within the nacelle, drawing in ambient air. This air enters the generator through the air inlet, cooling the stator and rotor before being exhausted from the nacelle through the generator's outlet. The cooling system's heat dissipation capacity is regulated by a cooling fan, whose operating speed is dynamically adjusted based on changes in the generator winding temperature.

[0041] The method, apparatus, and medium for determining the cause of cooling system failures provided in this application will be described below with reference to specific embodiments and accompanying drawings. The method for determining the cause of cooling system failures provided in this application can be applied to devices such as laptops, desktops, tablets, and servers, and can also be applied to fan controllers. This application uses an application to a fan controller as an example to illustrate the method for determining the cause of cooling system failures.

[0042] Figure 1 A flowchart illustrating a method for determining the cause of a cooling system failure, as provided in this application embodiment, is shown below. Figure 1 As shown, the method for determining the cause of the cooling system failure may include the following steps:

[0043] S110. Obtain the operating data of the wind turbine generator set within a preset time period.

[0044] The operational data includes at least the nacelle temperature and the actual temperature of the object being cooled, which refers to the objects in the wind turbine generator set cooled by the cooling system.

[0045] S120. Based on the actual temperature of the object being cooled within a preset time period and the reference temperature of the object being cooled corresponding to different operating states of the cooling system's fan, determine the actual operating state of the fan within the preset time period.

[0046] S130. Based on the cabin temperature within a preset time period, determine the actual temperature fluctuation data of the cabin temperature under actual operating conditions.

[0047] S140. Determine the cause of the cooling system failure based on the actual temperature fluctuation data.

[0048] This application embodiment determines the actual operating state of the fan within a preset time period based on the actual temperature of the object being cooled and the reference temperature of the object being cooled corresponding to different operating states of the fan, thus achieving accurate division of the fan's operating state. On this basis, based on the cabin temperature within the preset time period, the actual temperature fluctuation data of the cabin temperature under the actual operating state is determined, thereby quantifying the heat dissipation effect of the cooling system. Based on the quantified heat dissipation effect, i.e., the actual temperature fluctuation data, the cause of cooling system failure can be located more accurately.

[0049] The above steps are explained in detail below:

[0050] In S110, the preset time period can be, for example, a time period before the current time. In actual application, the preset time period can change with time, so that the cooling system of the unit can be monitored in real time to ensure the safe operation of the unit.

[0051] The object to be cooled here can be a component in the fan that is suitable for direct air cooling, such as a generator or gearbox. For example, when the object to be cooled is a generator, the above-mentioned actual temperature can be the actual temperature of the generator windings; when the object to be cooled is a gearbox, the above-mentioned actual temperature can be the actual oil temperature of the gearbox.

[0052] The nacelle temperature is the ambient temperature inside the unit, which changes systematically with the switching of the cooling system's heat dissipation mode. For example, when the cooling fan switches from off to low speed or from low speed to high speed, the nacelle temperature decreases during the short period of time due to the increased heat dissipation capacity. The temperature difference between the nacelle and ambient temperatures decreases, and the temperature change trajectory is a monotonically decreasing convex curve, eventually reaching a state of thermal equilibrium. The characteristics are reversed when the cooling fan switches from low speed to off or from high speed to low speed. This application's embodiments characterize the heat dissipation effect of the water cooling system by identifying the rapidly changing portion of the temperature curve based on the characteristics of the nacelle temperature change and calculating the corresponding temperature change amplitude.

[0053] The nacelle temperature and the actual temperature of the object being cooled can be measured by the corresponding temperature sensors and uploaded to the Supervisory Control and Data Acquisition (SCADA) system. That is, the wind turbine controller can obtain the unit's nacelle temperature and the actual temperature of the object being cooled within a preset time period from the SCADA system.

[0054] In some embodiments, the above-mentioned operating data may also include generator speed, ambient temperature, generator rated power, and wind turbine fault status.

[0055] In some embodiments, after obtaining the initial operating data of the unit, the operating data can be preprocessed, for example, data with values ​​exceeding the measurement range or not conforming to physical laws can be deleted to improve data quality, thereby more accurately determining the cause of cooling system failure.

[0056] Taking the inclusion of fan fault status in the operational data as an example, in some embodiments, the operational data can be arranged in chronological order and grouped according to the fan fault status. For example, when the time interval between adjacent operational data is less than a set value (e.g., 600s) and the corresponding fan is fault-free (fan fault status is 0), the operational data can be marked as 1; otherwise, it is marked as 0. This achieves the division of the operational data status, and the operational data can be grouped according to the data status. For example, if the data status is (0,0,1,1,1,0,1,0,0), then its corresponding group number is (1,1,2,2,2,3,4,5,5). The data volume of each group is counted. Operational data with a data volume greater than a set value, such as 600, and a data status of 1 can be marked as valid data. Subsequently, the cause of cooling system failure can be identified based on the valid data, resulting in higher accuracy.

[0057] In some embodiments, to ensure the quantity of operational data, if the time interval between two adjacent operational data groups exceeds the sampling interval, data interpolation can be performed on the effective data groups obtained above. Interpolation methods can include, for example, linear interpolation or mean interpolation. Data interpolation can enrich the operational data and ensure that the identified fault causes have some reference value.

[0058] In the S120, in practical applications, the cooling fan can include four operating states: low speed switching to stop state (also known as stop state), high speed switching to low speed state, stop switching to low speed state, and low speed switching to high speed state (also known as high speed state).

[0059] The reference temperature for the object being cooled is the temperature corresponding to the fan's operating state change. For example, when the object being cooled is a generator, the reference temperature can be the generator winding temperature corresponding to the fan's operating state change. The reference temperature for the object being cooled differs depending on the fan's operating state. This reference temperature can be obtained from a configuration file or determined by considering the temperature trend characteristics of the engine compartment. The specific determination process can be found in the following embodiment. The configuration file can pre-store the reference temperatures for the object being cooled corresponding to different fan operating states.

[0060] Based on the actual temperature of the object being cooled and the reference temperature of the object being cooled corresponding to different operating states of the fan, the actual operating state of the fan within a preset time period can be identified.

[0061] In S130, the actual temperature fluctuation data of the cabin temperature under actual operating conditions can include the temperature fluctuation trend of the cabin temperature under actual operating conditions, such as an upward or downward trend, and the temperature fluctuation value. Based on the cabin temperature within a preset time period, the actual temperature fluctuation data of the cabin temperature under actual operating conditions can be obtained.

[0062] In S140, for example, the cause of the cooling system failure can be obtained based on the actual temperature fluctuation data and the reference temperature fluctuation trend corresponding to the actual operating state.

[0063] Taking actual temperature fluctuation data, including actual temperature fluctuation trends, as an example, if the actual temperature fluctuation trend differs from the reference temperature fluctuation trend corresponding to the actual operating state, the cause of the cooling system failure can be determined to be abnormal fan operation. If the actual temperature fluctuation trend is the same as the reference temperature fluctuation trend corresponding to the actual operating state, the cause of the cooling system failure can be further determined based on the trend type of the actual temperature fluctuation trend and the change range of the cabin temperature under the trend type. The specific determination process can be found in the following embodiments.

[0064] This application embodiment quantifies the heat dissipation capacity of the cooling system by using actual temperature fluctuation data of the computer compartment temperature under the actual operating conditions of the fan. Based on the quantified heat dissipation capacity, the cause of the fault can be located more accurately.

[0065] The following is combined Figure 2 The process for determining the reference temperature of the object being cooled is explained, and may specifically include the following steps S210-S230.

[0066] S210. Based on the cabin temperature within a preset time period, determine the first trend characteristic sequence of cabin temperature within the preset time period.

[0067] The first trend feature sequence is used to characterize the trend change of cabin temperature at each sampling time. For example, the first trend feature sequence may include the trend feature of cabin temperature at each sampling time. The trend feature can be represented by 0, -1 and 1, where 0 indicates that the trend of cabin temperature has not changed, -1 indicates that cabin temperature is decreasing, and 1 indicates that cabin temperature is increasing.

[0068] For example, the first trend characteristic sequence of cabin temperature over a preset time period can be determined in the following way:

[0069] The cabin temperatures at each sampling time are arranged in chronological order to obtain the cabin temperature sequence;

[0070] Differential processing is performed on the cabin temperature in the cabin temperature sequence to obtain the differential processing result sequence;

[0071] The differential processing results in the differential processing result sequence are processed according to the sign function to obtain the trend characteristics of cabin temperature at each sampling time.

[0072] For example, by arranging the cabin temperatures at each sampling time in chronological order, a cabin temperature sequence can be obtained. Differential processing of the cabin temperature sequence can be performed, for example, by subtracting adjacent cabin temperatures, thereby obtaining... in, This represents the sequence of results from the differential processing.

[0073] Using symbolic functions By processing the data, the trend characteristics of the cabin temperature at each sampling time can be obtained. For example, in, This represents the first trend characteristic sequence.

[0074]

[0075] For example, when hour, when hour, 0, when hour, Thus, a first trend feature sequence consisting of 0, -1, and 1 can be obtained, providing a basis for subsequently determining the reference temperature of the object to be cooled.

[0076] This application embodiment, by performing differential processing on the cabin temperature and combining it with a sign function, can identify the trend changes in cabin temperature and obtain the trend characteristics of cabin temperature, providing a more accurate basis for subsequently determining the reference temperature of the cooling object corresponding to the fan in different states.

[0077] In some embodiments, before S210, the cabin temperature can be smoothed. This application embodiment does not limit the specific method of smoothing; for example, local weighted regression, moving average, kernel smoothing, etc., can be used to smooth the cabin temperature. That is, in some embodiments, the above cabin temperature sequence... It could be the smoothed cabin temperature.

[0078] Taking the smoothing of cabin temperature using a moving average method as an example, assuming, for instance, This is a time series of cabin temperatures sampled at equal intervals. Let l be a time series, where l is the number of the valid data set and n is the number of data sets in l. For xl After smoothing, the cabin temperature at any point in the sequence is... The m-term moving average of i = 1, 2, ..., n is:

[0079]

[0080] By smoothing the cabin temperature, short-term fluctuations and random disturbances in the cabin temperature in the time series can be eliminated, improving the accuracy of the cabin temperature and thus enabling a more accurate determination of the reference temperature of the object being cooled.

[0081] S220. Based on the first trend feature sequence, determine at least one starting moment when the cabin temperature changes according to the target trend and the temperature change is greater than or equal to the first set threshold.

[0082] The target trend here can be, for example, an upward trend or a downward trend. For instance, when the cabin temperature is changing in an upward trend, the starting time when the change in temperature is greater than or equal to a first set threshold can be determined based on the cabin temperature sequence, and then the actual temperature of the object to be cooled can be obtained at that starting time.

[0083] Taking a generator as an example, the winding temperature of the generator winding at each initial moment can be obtained.

[0084] S230. Based on the actual temperature of the object being cooled at each initial moment, determine the reference temperature of the object being cooled corresponding to the fan under different operating states.

[0085] For example, the reference temperature of the object being cooled by the fan under different operating conditions can be determined in the following way:

[0086] Kernel density estimation is performed on the actual temperature of the object being cooled at each initial moment to obtain the probability density curve corresponding to the object being cooled.

[0087] Based on the temperature corresponding to the local extreme point of the probability density curve, determine the reference temperature of the object being cooled by the fan under different operating conditions.

[0088] The local extrema here can include local maxima. The generator winding temperature corresponding to the local maximum is the winding reference temperature at the time of fan state transition. Taking the generator as the object being cooled as an example... Figure 3An example is provided of a probability density curve for a generator winding, where A, B, C, and D are local maxima. Based on this probability density curve, the winding reference temperature when the fan switches from low speed to shutdown is pha1 (second reference temperature), the winding reference temperature when the fan switches from shutdown to low speed is pha12 (fourth reference temperature), the winding reference temperature when the fan switches from low speed to high speed is pha3 (first reference temperature), and the winding reference temperature when the fan switches from high speed to low speed is pha32 (third reference temperature). That is, the first reference temperature, the third reference temperature, the fourth reference temperature, and the second reference temperature decrease sequentially.

[0089] According to the embodiment of this application, the temperature of the object to be cooled is extracted at the starting moment when the temperature trend of the cabin exceeds a first set value based on the trend characteristics of the cabin temperature. Then, the kernel density estimation of the temperature of the object to be cooled at the starting moment is performed to obtain a probability density curve. Based on the probability density curve, the reference temperature of the object to be cooled when the fan state switches can be obtained, so that the actual operating state of the fan can be accurately determined based on the reference temperature, and thus the cause of the cooling system failure can be accurately determined.

[0090] For example, a machine learning model or deep learning model can be used to determine the reference temperature of the cooling object corresponding to the fan in different operating states, by combining the actual temperature of the cooling object at each initial moment.

[0091] This application embodiment identifies the trend changes in cabin temperature, and then determines the reference temperature of the cooling object corresponding to the fan under different operating states based on the trend characteristics of cabin temperature. This allows the actual operating state of the fan to be accurately determined based on the reference temperature, and thus the cause of the cooling system failure can be accurately determined.

[0092] Taking a preset time period that includes multiple sampling times as an example, Figure 4 A flowchart illustrating another method for determining the cause of a cooling system failure, provided in an embodiment of this application. Figure 4 and Figure 1 The difference is that, Figure 1 S120 in the text can be further refined into Figure 4 S410-S430 in the series.

[0093] S410. For each sampling time, if the generator winding temperature at that sampling time is greater than the first reference temperature, determine that the actual operating state of the fan at that sampling time is high-speed operation.

[0094] For example, for each sampling time, if the generator winding temperature at that sampling time is greater than pha3, it can be determined that the actual operating state of the fan at that sampling time is a high-speed operating state. In some embodiments, when the fan is in a high-speed operating state, the fan can be marked as 4 to indicate that the fan is in a high-speed operating state.

[0095] S420. If the generator winding temperature at the sampling time is lower than the second reference temperature, determine that the actual operating state of the fan at the sampling time is the shutdown operating state.

[0096] For example, if the generator winding temperature at the sampling time is less than pha1, it can be determined that the actual operating state of the fan at the sampling time is a shutdown operating state. In some embodiments, when the fan is in a shutdown operating state, the fan can be marked as 1 to indicate that the fan is in a shutdown operating state.

[0097] S430. If the generator winding temperature at the sampling time is greater than or equal to the second reference temperature and less than or equal to the first reference temperature, the actual operating state of the fan at the sampling time is determined as the target operating state.

[0098] The target operating state differs from both the high-speed operating state and the shutdown operating state. For example, the target operating state can be represented by 0. That is, when the generator winding temperature at the sampling moment is greater than or equal to pha1 and less than or equal to pha3, the fan can be marked as 0, indicating that the specific state of the fan is temporarily uncertain and needs to be further determined later.

[0099] Understandably, the actual temperature fluctuation data of the engine compartment will be different when the fan switches from a stopped state to a low speed state and from a high speed state to a low speed state. In order to accurately identify the cause of the cooling system failure, it is necessary to further optimize the target operating state to clarify whether the fan switches from a stopped state to a low speed state or from a high speed state to a low speed state.

[0100] For example, suppose To smooth the temperature of a set of generator windings, let u l If the fan is in its actual operating state, then:

[0101]

[0102] Based on the reference temperature of the generator winding corresponding to the fan under different operating conditions, and combined with the actual temperature of the generator winding at each sampling time, the actual operating state of the fan at each sampling time can be determined, providing a more accurate basis for subsequent identification of the cause of cooling system failure.

[0103] Taking the target operating state as an example, which includes a first target operating state and a second target operating state, for instance, as follows: Figure 5 As shown, the above S430 may include the following S4301-S4302.

[0104] S4301. Divide the actual operating state of the fan at each sampling time to obtain at least one operating state sequence.

[0105] According to the above embodiment, for each sampling time, a fan state can be obtained, specifically 1, 4, or 0. Based on the fan state at each sampling time, the above u can be... l The process is divided to obtain at least one sequence of running states. Each sequence of running states may include at least one running state, and all running states contained in the same sequence are identical.

[0106] For example, assuming the running state at the first sampling moment belongs to running state sequence 1, for subsequent sampling moments, if the running state at the next sampling moment is the same as the running state at the previous sampling moment, then the running state at the next sampling moment and the running state at the previous sampling moment belong to the same running state sequence. If the running state at the next sampling moment is different from the running state at the previous sampling moment, then the number of the running state sequence to which the running state at the next sampling moment belongs is incremented by 1.

[0107] For example,

[0108] Among them, v l This represents the sequence of running states. For example, suppose the running state at the first sampling time belongs to running state sequence 1. For the second sampling time, i.e., i = 2, if... If the fan's operating state at the second sampling time is the same as its operating state at the first sampling time, then the fan's operating state at the second sampling time also belongs to operating state sequence 1; that is, the second sampling time and the first sampling time belong to the same operating state sequence 1. If If the fan's operating state at the second sampling time is different from its operating state at the first sampling time, then the number of the operating state sequence to which the fan belongs at the second sampling time is increased by 1 based on the number of the operating state sequence to which it belongs at the first sampling time. That is, the operating state sequence to which the fan belongs at the second sampling time is operating state sequence 2. By analogy, at least one operating state sequence can be obtained, providing a basis for further optimization of the target operating state.

[0109] S4302. Based on the sequence characteristics of each operating state sequence and the actual operating state of the fan in each operating state sequence, the target operating state is divided to obtain the first target operating state and the second target operating state.

[0110] The sequence features here may include, but are not limited to, the number of running state sequences and sequence identifiers. Based on the number of running state sequences and sequence identifiers, combined with the actual running state of the fan in each running state sequence, the target running state can be divided to obtain the first target running state and the second target running state, thereby achieving optimization of the target running state.

[0111] This application embodiment divides the fan's operating state into multiple operating state sequences. Based on the sequence characteristics of the operating state sequences and the actual operating state of the fan in each operating state sequence, the target operating state can be optimized to determine whether the fan is switching from a high-speed operating state to a low-speed operating state or from a stopped operating state to a low-speed operating state, so that the cause of the cooling system failure can be determined more accurately.

[0112] Taking sequence features including sequence number and sequence identifier as an example, S4302 above may include the following steps:

[0113] If the number of sequences is greater than or equal to the second set threshold, determine the first running state sequence to which the target running state belongs;

[0114] Based on the second operating state of the fan in the second operating state sequence and the generator winding temperature at the corresponding moment in the first operating state sequence, the target operating state is divided into a first target operating state and a second target operating state. The second operating state sequence is the sequence preceding the first operating state sequence.

[0115] For example, the second threshold can be set to 2. That is, when the operating state sequence is greater than or equal to 2, the operating state sequence to which the target operating state belongs can be recorded as the first operating state sequence. The operating state of the fan in the previous operating state sequence (the second operating state sequence) and the generator winding temperature of the generator winding at the time corresponding to the first operating state sequence can be obtained. Based on the operating state of the fan in the previous operating state sequence and the generator winding temperature of the generator winding at the time corresponding to the first operating state sequence, the target operating state can be divided into a first target operating state and a second target operating state. The first target operating state and the second target operating state are different operating states, thereby clarifying the target operating state and providing an accurate basis for subsequently determining the cause of the fault.

[0116] Once the sequence of operating states to which the target operating state belongs is determined, the start and end times of that sequence can be determined, providing a basis for the division of the target operating state.

[0117] In practical applications, the sequence of the previous running state of the target running state may be the sequence corresponding to running state 4 or the sequence corresponding to running state 1. The first target running state and the second target running state obtained by the two divisions are different.

[0118] For example, when the second operating state is a high-speed operating state, the first moment when the generator winding temperature first falls below the third reference temperature within the first operating state sequence is determined.

[0119] The actual operating state corresponding to the sampling time less than the first time in the first operating state sequence is determined as the first target operating state, and the actual operating state corresponding to the sampling time greater than or equal to the first time in the first operating state sequence is determined as the second target operating state.

[0120] The first target operating state is a high-speed operating state, and the second target operating state is a low-speed operating state.

[0121] For example, the current running state sequence corresponds to a high-speed running state, that is... When k represents the k-th running state sequence to which the target running state belongs, we can let t ′ for The time corresponding to the first time it is less than Pha32. If the generator winding temperature is represented, then:

[0122]

[0123] In other words, when the previous operating state sequence is a high-speed operating state sequence, the moment when the generator winding temperature in the first operating state sequence first falls below Pha32 can be determined. This moment is the dividing point between the first target operating state and the second target operating state. At this time, the operating states in the first operating state sequence that are lower than this dividing point can be defined as high-speed operating states, and the operating states in the first operating state sequence that are higher than or equal to this dividing point can be defined as low-speed operating states, which can be represented by 3. That is, the fan switches from a high-speed operating state to a low-speed operating state. Thus, the target operating state can be clearly defined as the switch from a high-speed operating state to a low-speed operating state.

[0124] For example, when the second operating state is a low-speed operating state, the second moment when the generator winding temperature first falls below the fourth reference temperature within the first operating state sequence is determined.

[0125] The actual operating state corresponding to the sampling time less than the second time in the first operating state sequence is determined as the first target operating state, and the actual operating state corresponding to the sampling time greater than or equal to the second time in the first operating state sequence is determined as the second target operating state.

[0126] The first target operating state is the shutdown operating state, and the second target operating state is the low-speed operating state.

[0127] For example, the current running state sequence corresponds to the shutdown running state, that is... At that time, t can be made ′ for If the value first exceeds Pha12 at the specified time, then:

[0128]

[0129] In other words, when the current operating state sequence is a high-speed operating state sequence, the moment when the generator winding temperature first exceeds Pha12 within the first operating state sequence can be determined. This moment is the dividing point between the first target operating state and the second target operating state. At this time, the operating states within the first operating state sequence that are less than this dividing point can be defined as shutdown operating states, and the operating states within the first operating state sequence that are greater than or equal to this dividing point can be defined as low-speed operating states, which can be represented by 2. That is, the fan switches from the shutdown operating state to the low-speed operating state. Thus, the target operating state can be clearly defined as the switch from the shutdown operating state to the low-speed operating state.

[0130] For example, such as Figure 6 As shown, based on the relationship between the generator winding temperature and pha1 and pha3, the time series corresponding to the generator winding temperature can be divided into four regions: region A, region B, region C, and region D. In regions B and D, the fan's operating state is 1, while in regions A and C, the fan's operating state is 0. Taking optimized region C as an example, the operating state corresponding to the previous sequence in region C is 1. According to the above embodiment, the moment t when the generator winding temperature first exceeds pha12 in region C can be determined. s After optimization, t p To t s The period between is the shutdown state, t s To t q The interval is a low-speed operating state.

[0131] This application embodiment divides the target operating state based on the operating state of the fan in the previous sequence of the target operating state and the temperature of the generator winding at each moment in the sequence to which the target operating state belongs. This achieves optimization of the target operating state and clarifies whether the fan switches from a high-speed operating state to a low-speed operating state or from a shutdown operating state to a low-speed operating state, providing a basis for accurately determining the cause of cooling system failure.

[0132] Taking a generator as an example, in some embodiments, the actual operating status of the fan within a preset time period can be identified by combining the trend characteristics of the generator winding temperature and the moment when it crosses the corresponding reference temperature. The following will combine... Figure 7 The process of determining the actual operating status of the fan is explained. Figure 7 A flowchart illustrating another method for determining the cause of a cooling system failure, provided in an embodiment of this application. Figure 7 and Figure 1 The difference is that, Figure 1 S120 in the text can be further refined into Figure 7 S710-S740.

[0133] S710. Determine the changing trend of generator winding temperature based on the second trend characteristic sequence of generator winding temperature within a preset time period.

[0134] The process for determining the second trend feature sequence can be found in the first trend feature sequence, and will not be repeated here for brevity. The trend features here can include an upward trend or a downward trend. For example, when an element in the second trend feature sequence is greater than 0, it indicates that the generator winding is in an upward trend; when an element in the second trend feature sequence is less than 0, it indicates that the generator winding is in a downward trend.

[0135] S720. When the trend of change is upward, determine the first target time for the first crossing of the fourth reference temperature and the second target time for the first crossing of the first reference temperature.

[0136] For example, when the generator winding temperature is on an upward trend, the first target time when the generator winding temperature first crosses pha12 and the second target time when the generator winding temperature first crosses pha3 can be determined by combining the generator winding temperature sequence.

[0137] S730. When the trend of change is downward, determine the third target time when the second reference temperature is first crossed and the fourth target time when the second reference temperature is first crossed.

[0138] Similarly, when the generator winding temperature is decreasing, the third target time when the generator winding temperature first crosses pha1 and the fourth target time when the generator winding temperature first crosses pha32 can be determined by combining the generator winding temperature sequence.

[0139] S740. Determine the actual operating status of the fan within a preset time period based on the first target time, the second target time, the third target time, and the fourth target time.

[0140] By combining the moment when the generator winding temperature first crosses pha1, pha32, pha12 and pha3, the actual operating status of the fan within a preset time period can be determined.

[0141] For example, the fan's operating state at the second target time can be determined as a high-speed operating state and the fan's operating state at the fourth target time can be determined as a shutdown operating state;

[0142] The actual operating state of the fan at the third target time is determined based on the actual operating state of the fan at the second target time, and the actual operating state of the fan at the first target time is determined based on the actual operating state of the fan at the fourth target time.

[0143] Based on the actual operating status of the fan at the first target time, the second target time, the third target time, and the fourth target time, determine the actual operating status of the fan at other times within the preset time period.

[0144] For example, when the generator winding temperature is rising and it crosses pha3 for the first time, the operating state at the second target time corresponding to pha3 can be determined as a high-speed operating state; and when the generator winding temperature is falling and it crosses pha32 for the first time, the operating state at the fourth target time corresponding to pha32 can be determined as a shutdown operating state.

[0145] The actual operating state of the fan at the third target time can be determined based on the actual operating state of the fan at the second target time, and the actual operating state of the fan at the first target time can be determined based on the actual operating state of the fan at the fourth target time. For example, if the fan's operating state at the time preceding the third target time (i.e., the second target time) is high-speed operation, then the fan's operating state at the third target time is 3, i.e., low-speed operation, indicating that the fan has switched from high-speed to low-speed operation. If the fan's operating state at the time preceding the first target time (i.e., the fourth target time) is stopped, then the fan's operating state at the first target time is 2, i.e., low-speed, indicating that the fan has switched from stopped to low-speed operation.

[0146] Once the actual operating status of the fan at the first, second, third, and fourth target times is determined, the actual operating status of the fan at other times within the preset time period can be determined based on the actual operating status of the fan at the first, second, third, and fourth target times.

[0147] The embodiments of this application can also combine the changing trend of the generator windings and the moment when the corresponding reference temperature is first crossed to determine the actual operating status of the fan within a preset time period, thereby improving the flexibility and diversity of the determination method.

[0148] Figure 8 A flowchart illustrating another method for determining the cause of a cooling system failure, provided in an embodiment of this application. Figure 8 and Figure 1 The difference is that, Figure 1 S130 in the middle can be further refined into Figure 8 S810-S840 in the series.

[0149] S810. Determine the initial moment when the fan enters the actual operating state based on the first trend characteristic sequence.

[0150] For example, based on the first trend characteristic sequence of cabin temperature, the moment when the fan operating state switches can be determined. (Reference) Figure 6 The moment when the fan switches from the off state to the low-speed running state can be determined as t. s Then time t can be used as the starting point. s This is determined as the initial time.

[0151] S820. Determine the end time of the trend characteristic subsequence based on the trend characteristic subsequence to which the cabin temperature belongs at the initial moment.

[0152] The trend feature subsequence is obtained by dividing the first trend feature sequence. Continuing the example above, exemplarily, based on time t... s It can be determined that the cabin temperature at time t s The trend feature subsequence to which it belongs can be used to determine the end time t of the trend feature subsequence. t .

[0153] S830, Determine the temperature difference between the initial and final moments of the cabin.

[0154] For example, the cabin temperature can be determined over a time period t. s To t t The temperature difference. For example, in, Indicates the temperature difference value. Let the cabin temperature at time tt Temperature value, Let the cabin temperature at time t s Temperature value. Figure 9 An exemplary method is provided A schematic diagram, in which t m t is the moment when the fan switches from low-speed operation to shutdown. n For t m The end time of the trend feature subsequence to which the current time belongs.

[0155] S840. Based on the temperature difference, determine the actual temperature fluctuation data of the engine room under actual operating conditions.

[0156] In some embodiments, the temperature difference can be directly determined as the actual temperature fluctuation data of the cabin temperature under the actual operating conditions.

[0157] In some embodiments, the corresponding operation state of the fan during different operating states within a preset time period can also be determined. For each By conducting trend analysis, we can obtain The fluctuation trend. This application does not limit the specific trend analysis method used; for example, the Mann-Kendall trend detection method, regression analysis, etc., can be used to determine the trend. The fluctuation trend.

[0158] The following uses the Mann-Kendall trend detection method to determine... Taking the fluctuation trend as an example, specifically, the trend detection statistic S is:

[0159]

[0160] Where g is the number of groups into which the temperature difference z is grouped according to its numerical value, and t p Z represents the number of elements in each group. MK Approximately normal distribution, given a significance level α, compare Z... MK With the normal distribution quantile Z 1-α This allows us to determine whether there is a significant trend change in the temperature difference z of the fan.

[0161] Figure 10 This diagram illustrates the trend of the temperature difference z when the fan is running at high speed. Based on the Mann-Kendall trend analysis, |Z MK |>Z 1-α The time series of temperature difference z shows a significant upward trend, and the red curve represents the changing trend of temperature difference z.

[0162] Based on the trend characteristics of the cabin temperature and the operating status of the fan, this application embodiment can determine the difference in cabin temperature when the fan operating status changes, and then determine the actual temperature fluctuation data of the cabin temperature based on the difference in cabin temperature, providing an accurate basis for diagnosing the cause of the fault.

[0163] Taking actual temperature fluctuation data, including actual temperature fluctuation trends, as an example, Figure 11 A flowchart illustrating another method for determining the cause of a cooling system failure, provided in an embodiment of this application. Figure 11 and Figure 1 The difference is that, Figure 1 S140 in the middle can be further refined into Figure 11 S1100-S1110. In practical applications, either S1100 or S1110 is executed.

[0164] S1100. If the actual temperature fluctuation trend differs from the reference temperature fluctuation trend corresponding to the actual operating state, the cause of the cooling system failure is determined to be abnormal fan operation.

[0165] Based on the cooling system's heat dissipation principle, when the fan switches from a stopped state to a low-speed operating state or from a low-speed operating state to a high-speed operating state (or vice versa), the engine compartment temperature should show a decreasing (increasing) trend due to the increased (decreased) heat dissipation capacity, with a corresponding theoretical temperature difference z<0 (z>0). Therefore, by considering the fan's actual operating state, the actual temperature fluctuation trend, and the reference temperature fluctuation trend corresponding to the actual operating state, potential risks and hazards in the generator cooling system can be identified.

[0166] For example, if the actual temperature fluctuation trend is different from the reference temperature fluctuation trend corresponding to the actual operating state, it can be preliminarily determined that the cause of the cooling system failure is abnormal fan operation.

[0167] like Figure 12 As shown, at time t1, the generator winding temperature reaches the high-speed start-up condition of the fan, and the corresponding temperature difference z>0 is inconsistent with the sign of the reference temperature difference z<0. Therefore, it can be determined that the fan has not switched to high-speed operation mode, i.e., the fan is operating abnormally. Since the fan has not switched to high-speed operation, the generator's heat dissipation demand is not fully met, and heat accumulates until the generator temperature exceeds the limit at time t2. It continues to operate until time t3, when the unit shuts down due to high-temperature operation failure.

[0168] S1110. When the actual temperature fluctuation trend is the same as the reference temperature fluctuation trend corresponding to the actual operating state, the cause of the cooling system failure shall be determined according to the trend type of the actual temperature fluctuation trend and the change range of the cabin temperature under the trend type.

[0169] For example, if the actual temperature fluctuation trend is the same as the reference temperature fluctuation trend corresponding to the actual operating state, the cause of the cooling system failure can be further determined based on the trend type of the actual temperature fluctuation trend and the magnitude of the change in cabin temperature under that trend type.

[0170] For example, if the trend type is upward and the change in cabin temperature under the upward type is greater than a third set threshold, the cause of the cooling system failure is determined to be a decline in cooling effect.

[0171] For example, such as Figure 10 As shown, when the temperature difference shows an upward trend and the change exceeds the third set threshold, it can be preliminarily determined that the cause of the cooling system failure is a decline in cooling effect. Further on-site maintenance and troubleshooting can then determine the specific cause. For example, after on-site maintenance and troubleshooting, it was found that the problem was caused by clogged filter cotton in the engine compartment. After replacing the filter cotton, the heat dissipation effect of the cooling system was restored, that is, the temperature difference showed a downward trend.

[0172] Based on whether the actual temperature fluctuation trend of the engine compartment temperature is the same as the reference temperature fluctuation trend, this application embodiment can not only identify potential overheating hazards in the unit in advance, but also identify the cause of the fault. Moreover, the heat dissipation effect of the cooling system can be quantified based on the temperature difference of the engine compartment temperature, which has good application value.

[0173] Based on the same inventive concept, embodiments of this application also provide a device for determining the cause of a cooling system failure, which is described below in conjunction with... Figure 13 The apparatus for determining the cause of cooling system failure provided in the embodiments of this application will be described.

[0174] Figure 13 A structural diagram of a device for determining the cause of a cooling system failure provided in an embodiment of this application is shown below. Figure 13 As shown, the cooling system malfunction determination device 1300 may include:

[0175] The acquisition module 1301 is used to acquire the operating data of the wind turbine generator set within a preset time period. The operating data includes at least the nacelle temperature and the actual temperature of the object being cooled. The object being cooled is the object in the wind turbine generator set cooled by the cooling system.

[0176] The determination module 1302 is used to determine the actual operating status of the fan within a preset time period based on the actual temperature of the object being cooled within a preset time period and the reference temperature of the object being cooled corresponding to the fan of the cooling system under different operating states; to determine the actual temperature fluctuation data of the engine compartment temperature under the actual operating state based on the engine compartment temperature within the preset time period; and to determine the cause of the cooling system failure based on the actual temperature fluctuation data.

[0177] This application embodiment determines the actual operating state of the fan within a preset time period based on the actual temperature of the object being cooled and the reference temperature of the object being cooled corresponding to different operating states of the fan, thus achieving accurate division of the fan's operating state. On this basis, based on the cabin temperature within the preset time period, the actual temperature fluctuation data of the cabin temperature under the actual operating state is determined, thereby quantifying the heat dissipation effect of the cooling system. Based on the quantified heat dissipation effect, i.e., the actual temperature fluctuation data, the cause of cooling system failure can be located more accurately.

[0178] In some embodiments, the determining module 1302 is further configured to: determine a first trend feature sequence of the cabin temperature within a preset time period based on the cabin temperature within a preset time period; determine at least one starting moment when the cabin temperature changes according to the target trend and the temperature change is greater than or equal to a first set threshold based on the first trend feature sequence; and determine a reference temperature of the cooling object corresponding to the fan in different operating states based on the actual temperature of the cooling object at each starting moment.

[0179] In some embodiments, the preset time period includes multiple sampling times, and the first trend feature sequence includes the trend features of cabin temperature at each sampling time.

[0180] Module 1302 is defined as including:

[0181] The arrangement unit is used to arrange the cabin temperatures at each sampling time in chronological order to obtain the cabin temperature sequence;

[0182] The processing unit is used to perform differential processing on the cabin temperature in the cabin temperature sequence to obtain a differential processing result sequence; and to process each differential processing result in the differential processing result sequence according to the sign function to obtain the trend characteristics of the cabin temperature at each sampling time.

[0183] In some embodiments, the determining module 1302 is specifically used for:

[0184] Kernel density estimation is performed on the actual temperature of the object being cooled at each initial moment to obtain the probability density curve corresponding to the object being cooled.

[0185] Based on the temperature corresponding to the local extreme point of the probability density curve, determine the reference temperature of the object being cooled by the fan under different operating conditions.

[0186] In some embodiments, the object to be cooled includes a generator, the actual temperature includes the generator winding temperature, and the reference temperature includes a first reference temperature, a second reference temperature, a third reference temperature, and a fourth reference temperature, wherein the first reference temperature, the third reference temperature, the fourth reference temperature, and the second reference temperature decrease sequentially.

[0187] In some embodiments, the preset time period includes multiple sampling times;

[0188] Module 1302 is specifically used for:

[0189] For each sampling time, if the generator winding temperature at the sampling time is greater than the first reference temperature, the actual operating state of the fan at the sampling time is determined to be high-speed operation.

[0190] If the generator winding temperature at the sampling time is lower than the second reference temperature, the actual operating state of the fan at the sampling time is determined to be the shutdown operating state.

[0191] If the generator winding temperature at the sampling time is greater than or equal to the second reference temperature and less than or equal to the first reference temperature, the actual operating state of the fan at the sampling time is determined as the target operating state. The target operating state is different from the high-speed operating state and the shutdown operating state.

[0192] In some embodiments, the target operating state includes a first target operating state and a second target operating state;

[0193] Module 1302 is specifically used for:

[0194] The actual operating state of the fan at each sampling time is divided to obtain at least one operating state sequence;

[0195] Based on the sequence characteristics of each operating state sequence and the actual operating state of the fan in each operating state sequence, the target operating state is divided to obtain the first target operating state and the second target operating state.

[0196] In some embodiments, sequence features include sequence number and sequence identifier;

[0197] Module 1302 is specifically used for:

[0198] If the number of sequences is greater than or equal to the second set threshold, determine the first running state sequence to which the target running state belongs;

[0199] Based on the second operating state of the fan in the second operating state sequence and the generator winding temperature at the corresponding moment in the first operating state sequence, the target operating state is divided into a first target operating state and a second target operating state. The second operating state sequence is the sequence preceding the first operating state sequence.

[0200] In some embodiments, the determining module 1302 is specifically used for:

[0201] When the second operating state is a high-speed operating state, determine the first moment when the generator winding temperature first falls below the third reference temperature within the first operating state sequence;

[0202] The actual operating state corresponding to the sampling time less than the first time in the first operating state sequence is determined as the first target operating state, and the actual operating state corresponding to the sampling time greater than or equal to the first time in the first operating state sequence is determined as the second target operating state.

[0203] The first target operating state is a high-speed operating state, and the second target operating state is a low-speed operating state.

[0204] In some embodiments, the determining module 1302 is specifically used for:

[0205] When the second operating state is a low-speed operating state, determine the second moment when the generator winding temperature first falls below the fourth reference temperature within the first operating state sequence;

[0206] The actual operating state corresponding to the sampling time less than the second time in the first operating state sequence is determined as the first target operating state, and the actual operating state corresponding to the sampling time greater than or equal to the second time in the first operating state sequence is determined as the second target operating state.

[0207] The first target operating state is the shutdown operating state, and the second target operating state is the low-speed operating state.

[0208] In some embodiments, the determining module 1302 is specifically used for:

[0209] The trend of generator winding temperature change is determined based on the second trend characteristic sequence of generator winding temperature within a preset time period.

[0210] When the trend of change is upward, determine the first target time for the first crossing of the fourth reference temperature and the second target time for the first crossing of the first reference temperature;

[0211] When the trend of change is downward, determine the third target time and the fourth target time for the first crossing of the second reference temperature;

[0212] Based on the first target time, the second target time, the third target time, and the fourth target time, determine the actual operating status of the fan within the preset time period.

[0213] In some embodiments, the determining module 1302 is specifically used for:

[0214] The fan's operating state at the second target time is determined to be high-speed operation, and the fan's operating state at the fourth target time is determined to be shutdown operation.

[0215] The actual operating state of the fan at the third target time is determined based on the actual operating state of the fan at the second target time, and the actual operating state of the fan at the first target time is determined based on the actual operating state of the fan at the fourth target time.

[0216] Based on the actual operating status of the fan at the first target time, the second target time, the third target time, and the fourth target time, determine the actual operating status of the fan at other times within the preset time period.

[0217] In some embodiments, the determining module 1302 is specifically used for:

[0218] Based on the first trend characteristic sequence, determine the initial moment when the fan enters the actual operating state;

[0219] Based on the trend feature subsequence to which the cabin temperature belongs at the initial moment, the end moment of the trend feature subsequence is determined. The trend feature subsequence is obtained by dividing the first trend feature sequence.

[0220] Determine the temperature difference between the initial and final moments of the cabin.

[0221] Based on the temperature difference, determine the actual temperature fluctuation data of the cabin under actual operating conditions.

[0222] In some embodiments, the actual temperature fluctuation data includes the actual temperature fluctuation trend;

[0223] Module 1302 is specifically used for:

[0224] When the actual temperature fluctuation trend differs from the reference temperature fluctuation trend corresponding to the actual operating state, the cause of the cooling system failure is determined to be abnormal fan operation.

[0225] When the actual temperature fluctuation trend is the same as the reference temperature fluctuation trend corresponding to the actual operating state, the cause of the cooling system failure is determined based on the trend type of the actual temperature fluctuation trend and the magnitude of the change in cabin temperature under the trend type.

[0226] In some embodiments, the determining module 1302 is specifically used for:

[0227] If the trend type is upward and the change in cabin temperature under the upward type is greater than the third set threshold, the cause of the cooling system failure is determined to be a decline in cooling effect.

[0228] Based on the same inventive concept, embodiments of this application also provide a device for determining the cause of a cooling system failure. This device can be, for example, an electronic device such as a tablet computer, laptop computer, or PDA, or a fan controller. The following describes... Figure 14 The device for determining the cause of cooling system failure provided in the embodiments of this application will be described in detail.

[0229] like Figure 14 As shown, the device 1400 for determining the cause of cooling system failure may include a processor 1401 and a memory 1402 for storing computer program instructions.

[0230] Processor 1401 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that may be configured to implement the embodiments of this application.

[0231] Memory 1402 may include mass storage for data or instructions. For example, and not limitingly, memory 1402 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 1402 may include removable or non-removable (or fixed) media, or memory 1402 may be non-volatile solid-state memory. In one instance, memory 1402 may be read-only memory (ROM). In one instance, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0232] The processor 1401 reads and executes computer program instructions stored in memory 1402 to achieve... Figures 1-13 The method in the illustrated embodiment achieves... Figures 1-12 The corresponding technical effects achieved by the methods in the illustrated embodiments are described briefly and will not be elaborated further here.

[0233] In one example, the device 1400 for determining the cause of a cooling system malfunction may further include a communication interface 1403 and a bus 1404. For example, Figure 14As shown, the processor 1401, memory 1402, and communication interface 1403 are connected through bus 1404 and complete communication with each other.

[0234] The communication interface 1403 is mainly used to realize communication between various modules, devices and / or equipment in the embodiments of this application.

[0235] Bus 1404 includes hardware, software, or both, that couples together the components of cooling system failure determination device 1400. For example, and not as a limitation, bus 1404 may include Accelerated GraphicsPort (AGP) or other graphics buses, Extended Industry Standard Architecture (EISA) buses, Front Side Bus (FSB), Hyper Transport (HT) interconnects, Industry Standard Architecture (ISA) buses, Infinite Bandwidth Interconnects, Low Pin Count (LPC) buses, memory buses, Microchannel Architecture (MCA) buses, Peripheral Component Interconnect (PCI) buses, PCI-Express (PCI-X) buses, Serial Advanced Technology Attachment (SATA) buses, Video Electronics Standards Association Local (VLB) buses, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 1404 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0236] The cooling system failure cause determination device 1400, after acquiring the operating data of the wind turbine generator set within a preset time period, can execute the cooling system failure cause determination method in this application embodiment, thereby achieving a combination of... Figures 1-12 The method for determining the cause of cooling system failure is described. Figure 13 The device described is for determining the cause of cooling system failure.

[0237] Furthermore, in conjunction with the methods for determining the cause of cooling system failures in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the methods for determining the cause of cooling system failures in the above embodiments.

[0238] Furthermore, in conjunction with the methods for determining the causes of cooling system failures in the above embodiments, this application embodiment can provide a computer program product to implement this method. This computer program product includes a computer program that, when executed by a processor, implements any of the methods for determining the causes of cooling system failures in the above embodiments.

[0239] Although this application has been described with reference to preferred embodiments, various modifications can be made thereto and components can be replaced with equivalents without departing from the scope of this application. In particular, the technical features mentioned in the various embodiments can be combined in any manner, provided there is no structural conflict. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for determining the cause of a cooling system failure, characterized in that, include: The system acquires the operating data of the wind turbine generator set within a preset time period. The operating data includes at least the nacelle temperature and the actual temperature of the object being cooled, where the object being cooled is the object in the wind turbine generator set cooled by the cooling system. Based on the actual temperature of the object being cooled within the preset time period, and the reference temperature of the object being cooled corresponding to different operating states of the fan in the cooling system, the actual operating state of the fan within the preset time period is determined. Based on the cabin temperature during the preset time period, determine the actual temperature fluctuation data of the cabin temperature under the actual operating conditions. Based on the actual temperature fluctuation data, the cause of the cooling system failure is determined.

2. The method according to claim 1, characterized in that, The method further includes: Based on the cabin temperature within the preset time period, a first trend characteristic sequence of cabin temperature within the preset time period is determined; Based on the first trend feature sequence, determine at least one starting moment when the cabin temperature changes according to the target trend and the temperature change is greater than or equal to a first set threshold. Based on the actual temperature of the object being cooled at each of the initial times, the reference temperature of the object being cooled corresponding to the fan under different operating states is determined.

3. The method according to claim 2, characterized in that, The preset time period includes multiple sampling times, and the first trend feature sequence includes the trend features of the cabin temperature at each of the sampling times; The step of determining a first trend characteristic sequence of cabin temperature within a preset time period based on the cabin temperature within that preset time period includes: Arrange the cabin temperatures at each sampling time in chronological order to obtain a cabin temperature sequence; The cabin temperatures in the cabin temperature sequence are differentially processed to obtain a differential processing result sequence; The differential processing results in the differential processing result sequence are processed according to the sign function to obtain the trend characteristics of the cabin temperature at each sampling time.

4. The method according to claim 2, characterized in that, The step of determining the reference temperature of the cooled object corresponding to different operating states of the fan based on the actual temperature of the cooled object at each of the initial times includes: Kernel density estimation is performed on the actual temperature of the object being cooled at each of the initial times to obtain the probability density curve corresponding to the object being cooled. Based on the temperature corresponding to the local extreme point of the probability density curve, the reference temperature of the object being cooled by the fan under different operating states is determined.

5. The method according to any one of claims 1-4, characterized in that, The object to be cooled includes a generator, the actual temperature includes the generator winding temperature, and the reference temperature includes a first reference temperature, a second reference temperature, a third reference temperature, and a fourth reference temperature, wherein the first reference temperature, the third reference temperature, the fourth reference temperature, and the second reference temperature decrease sequentially.

6. The method according to claim 5, characterized in that, The preset time period includes multiple sampling times; The step of determining the actual operating state of the fan within the preset time period based on the actual temperature of the object being cooled within the preset time period and the reference temperature of the object being cooled corresponding to different operating states of the fan in the cooling system includes: For each sampling time, if the generator winding temperature at the sampling time is greater than the first reference temperature, the actual operating state of the fan at the sampling time is determined to be a high-speed operating state. If the generator winding temperature at the sampling time is lower than the second reference temperature, the actual operating state of the fan at the sampling time is determined to be a shutdown operating state. If the generator winding temperature at the sampling time is greater than or equal to the second reference temperature and less than or equal to the first reference temperature, the actual operating state of the fan at the sampling time is determined to be the target operating state, which is different from both the high-speed operating state and the shutdown operating state.

7. The method according to claim 6, characterized in that, The target operating state includes a first target operating state and a second target operating state; Determining the actual operating state of the fan at the sampling time as the target operating state includes: The actual operating state of the fan at each of the sampling times is divided to obtain at least one operating state sequence; Based on the sequence characteristics of each of the operating state sequences and the actual operating state of the fan in each of the operating state sequences, the target operating state is divided to obtain a first target operating state and a second target operating state.

8. The method according to claim 7, characterized in that, The sequence features include sequence number and sequence identifier; The step of dividing the target operating state into a first target operating state and a second target operating state based on the sequence characteristics of each operating state sequence and the actual operating state of the fan in each operating state sequence includes: If the number of sequences is greater than or equal to a second set threshold, determine the first running state sequence to which the target running state belongs; Based on the second operating state of the fan in the second operating state sequence and the generator winding temperature at the corresponding time in the first operating state sequence, the target operating state is divided to obtain a first target operating state and a second target operating state, wherein the second operating state sequence is the previous sequence of the first operating state sequence.

9. The method according to claim 8, characterized in that, The step of dividing the target operating state into a first target operating state and a second target operating state based on the second operating state of the fan in the second operating state sequence and the generator winding temperature at the corresponding time in the first operating state sequence includes: When the second operating state is a high-speed operating state, determine the first moment when the generator winding temperature first falls below the third reference temperature within the first operating state sequence. The actual operating state corresponding to the sampling time less than the first time in the first operating state sequence is determined as the first target operating state, and the actual operating state corresponding to the sampling time greater than or equal to the first time in the first operating state sequence is determined as the second target operating state. The first target operating state is a high-speed operating state, and the second target operating state is a low-speed operating state.

10. The method according to claim 8, characterized in that, The step of dividing the target operating state into a first target operating state and a second target operating state based on the second operating state of the fan in the second operating state sequence and the generator winding temperature at the corresponding time in the first operating state sequence includes: When the second operating state is a low-speed operating state, determine the second moment when the generator winding temperature first falls below the fourth reference temperature within the first operating state sequence. The actual operating state corresponding to the sampling time less than the second time in the first operating state sequence is determined as the first target operating state, and the actual operating state corresponding to the sampling time greater than or equal to the second time in the first operating state sequence is determined as the second target operating state. The first target operating state is a shutdown operating state, and the second target operating state is a low-speed operating state.

11. The method according to claim 6, characterized in that, The step of determining the actual operating state of the fan within the preset time period based on the actual temperature of the object being cooled within the preset time period and the reference temperature of the object being cooled corresponding to different operating states of the fan in the cooling system includes: The changing trend of the generator winding temperature is determined based on the second trend characteristic sequence of the generator winding temperature within the preset time period. If the trend of change is upward, determine the first target time when the fourth reference temperature is first crossed and the second target time when the first reference temperature is first crossed. If the trend of change is downward, determine the third target time when the second reference temperature is first crossed and the fourth target time when the second reference temperature is first crossed. The actual operating state of the fan within the preset time period is determined based on the first target time, the second target time, the third target time, and the fourth target time.

12. The method according to claim 11, characterized in that, Determining the actual operating state of the fan within the preset time period based on the first target time, the second target time, the third target time, and the fourth target time includes: The operating state of the fan at the second target time is determined to be a high-speed operating state, and the operating state of the fan at the fourth target time is determined to be a shutdown operating state; The actual operating state of the fan at the third target time is determined based on the actual operating state of the fan at the second target time, and the actual operating state of the fan at the first target time is determined based on the actual operating state of the fan at the fourth target time; Based on the actual operating status of the fan at the first target time, the second target time, the third target time, and the fourth target time, the actual operating status of the fan at other times within the preset time period is determined.

13. The method according to any one of claims 2-4, characterized in that, The step of determining the actual temperature fluctuation data of the cabin temperature under the actual operating conditions based on the cabin temperature within the preset time period includes: Based on the first trend feature sequence, determine the initial moment when the fan enters the actual operating state; Based on the trend feature subsequence to which the cabin temperature belongs at the initial time, the end time of the trend feature subsequence is determined, wherein the trend feature subsequence is obtained by dividing the first trend feature sequence; Determine the temperature difference between the cabin temperature at the initial time and the end time; Based on the temperature difference, the actual temperature fluctuation data of the cabin temperature under the actual operating conditions is determined.

14. The method according to any one of claims 1-4, characterized in that, The actual temperature fluctuation data includes the actual temperature fluctuation trend; The step of determining the cause of the cooling system malfunction based on the actual temperature fluctuation data includes: If the actual temperature fluctuation trend differs from the reference temperature fluctuation trend corresponding to the actual operating state, the cause of the cooling system failure is determined to be the abnormal operation of the fan. If the actual temperature fluctuation trend is the same as the reference temperature fluctuation trend corresponding to the actual operating state, the cause of the cooling system failure is determined based on the trend type of the actual temperature fluctuation trend and the change range of the cabin temperature under the trend type.

15. The method according to claim 14, characterized in that, The step of determining the cause of the cooling system malfunction based on the trend type of the actual temperature fluctuation trend and the magnitude of the cabin temperature change under the trend type includes: If the trend type is upward and the change in cabin temperature under the upward trend is greater than a third set threshold, the cause of the cooling system failure is determined to be a decline in cooling effect.

16. A device for determining the cause of a cooling system failure, characterized in that, include: The acquisition module is used to acquire the operating data of the wind turbine generator set within a preset time period. The operating data includes at least the nacelle temperature and the actual temperature of the object being cooled. The object being cooled is the object in the wind turbine generator set that is cooled by the cooling system. The determination module is used to determine the actual operating state of the fan during the preset time period based on the actual temperature of the object being cooled and the reference temperature of the object being cooled corresponding to different operating states of the fan of the cooling system; to determine the actual temperature fluctuation data of the nacelle temperature during the preset time period based on the nacelle temperature; and to determine the cause of the cooling system failure based on the actual temperature fluctuation data.

17. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, the method as described in any one of claims 1-15 is implemented.

Images